{ "$schema": "https://agentskills.site/schemas/skills-export-v1.json", "schemaVersion": "1.0.0", "generatedAt": "2026-08-18", "source": "https://agentskills.site/skills/", "license": { "id": "CC-BY-4.0", "attribution": "Data compiled by AgentSkills.site — https://agentskills.site", "terms": "https://agentskills.site/about/#reusing-this-data" }, "disclaimer": "Two inspection tiers: \"catalogued\" means canonical metadata only (name, description, capabilities, source); \"inspected\" means the primary source was read in full and carries a decision-support profile (whatItDoes, whenToUse, notFor, etc). Agent-support evidence carries two tiers: \"confirmed\" (the skill's own source or vendor states it works with that agent) and \"portable\" (it only reaches that agent through the shared SKILL.md format and a directory convention). Neither tier is a claim that anything here was run or tested — see /about/.", "counts": { "skills": 86, "inspected": 39, "sources": 15, "creators": 13, "topics": 9, "capabilities": 26 }, "capabilities": [ { "id": "agent-migration", "label": "Migrating from another agent", "keywords": [ "migrate", "migration", "switch from", "switching from", "import my skills", "move from claude", "move from cursor", "move from codex", "bring my skills" ], "order": 1 }, { "id": "planning-workflow", "label": "Planning and orchestration", "keywords": [ "orchestrate", "orchestration", "parallel agents", "planning workflow", "project workflow", "break down the task", "fan out tasks" ], "order": 2 }, { "id": "skill-authoring", "label": "Writing your own skills", "keywords": [ "write a skill", "write my own skill", "create a skill", "author a skill", "build a skill", "make a skill", "skill creator", "custom skill", "build a plugin", "create a plugin" ], "order": 2 }, { "id": "development-discipline", "label": "Development discipline", "keywords": [ "tdd", "test-driven", "test driven development", "systematic debugging", "planning discipline", "development methodology" ], "order": 3 }, { "id": "integration-connectivity", "label": "Tool and API integration", "keywords": [ "mcp server", "api integration", "sdk", "connect to", "cuda", "gpu", "robotics", "physical ai", "workflow automation", "cli design" ], "order": 3 }, { "id": "security-review", "label": "Security review", "keywords": [ "security", "vulnerability", "vuln", "threat model", "threat modeling", "cve", "exploit", "pentest", "penetration test" ], "order": 4 }, { "id": "code-review", "label": "Code review", "keywords": [ "code review", "review my code", "review the pr", "review pull request", "pr review", "review changes", "review" ], "order": 5 }, { "id": "github-workflow", "label": "GitHub PR workflow", "keywords": [ "pull request", "pull requests", "github actions", "failing ci", "ci failure", "pr comments" ], "order": 5 }, { "id": "design-implementation", "label": "Design implementation", "keywords": [ "design", "figma", "frontend", "ui component", "css", "tailwind", "layout", "implement the design", "implement design" ], "order": 6 }, { "id": "documentation-authoring", "label": "Turning material into a skill", "keywords": [ "turn into a skill", "book to skill", "convert documentation", "extract from a book" ], "order": 6 }, { "id": "documentation", "label": "Documentation and knowledge capture", "keywords": [ "keep docs updated", "agents.md maintenance", "documentation canvas", "architecture walkthrough", "knowledge base", "docs reliability", "documentation" ], "order": 6 }, { "id": "database", "label": "Database and backend", "keywords": [ "database", "postgres", "postgresql", "sql query", "supabase", "schema design", "row-level security", "database migration", "connection pooling" ], "order": 6 }, { "id": "data-document-processing", "label": "Document generation", "keywords": [ "pdf", "docx", "word doc", "excel", "spreadsheet", "powerpoint", "pptx", "xlsx", "generate a document" ], "order": 6 }, { "id": "testing-qa", "label": "Testing and QA", "keywords": [ "testing", "qa", "e2e", "playwright", "browser test", "visual test", "accessibility", "responsive", "cross-browser", "content qa" ], "order": 7 }, { "id": "debugging", "label": "Debugging", "keywords": [ "debug", "debugging", "fix a bug", "root cause", "systematic debugging" ], "order": 7 }, { "id": "deployment-cicd", "label": "Deployment and CI", "keywords": [ "deploy", "deployment", "ci pipeline", "release process", "failing checks" ], "order": 8 }, { "id": "performance-monitoring", "label": "Performance and monitoring", "keywords": [ "performance", "site speed", "monitor", "monitoring", "core web vitals", "lighthouse", "analytics", "search console", "pagespeed", "search-performance" ], "order": 9 }, { "id": "seo-content", "label": "SEO & content", "keywords": [ "seo audit", "technical seo", "site architecture", "schema markup", "structured data", "content strategy", "app store optimization" ], "order": 10 }, { "id": "programmatic-seo", "label": "Programmatic SEO", "keywords": [ "programmatic seo", "pseo", "pages at scale", "template pages", "directory pages", "location pages" ], "order": 10 }, { "id": "cro", "label": "Conversion rate optimization", "keywords": [ "conversion rate optimization", "landing page optimization", "signup flow", "onboarding flow", "paywall optimization", "popup optimization" ], "order": 10 }, { "id": "content-copy", "label": "Content & copy", "keywords": [ "cold email", "email sequence", "social content", "video content", "sms marketing" ], "order": 10 }, { "id": "copywriting", "label": "Copywriting", "keywords": [ "copywriting", "landing page copy", "value proposition", "marketing copy", "headline copy" ], "order": 10 }, { "id": "paid-measurement", "label": "Paid media & measurement", "keywords": [ "paid ads", "ad creative", "ab testing", "marketing analytics", "attribution model" ], "order": 10 }, { "id": "growth-retention", "label": "Growth & retention", "keywords": [ "referral program", "churn prevention", "lead magnet", "community marketing", "influencer marketing" ], "order": 10 }, { "id": "sales-gtm", "label": "Sales & GTM", "keywords": [ "revops", "sales enablement", "product launch", "pricing strategy", "competitor analysis", "prospecting" ], "order": 10 }, { "id": "marketing-strategy", "label": "Marketing strategy", "keywords": [ "marketing plan", "marketing psychology", "customer research", "marketing ideas" ], "order": 10 } ], "topics": [ { "id": "marketing", "label": "Marketing", "description": "SEO, conversion optimization, copywriting, paid media, growth, and go-to-market — from Corey Haines's marketingskills collection plus the site's own picks.", "capabilityIds": [ "seo-content", "programmatic-seo", "cro", "content-copy", "copywriting", "paid-measurement", "growth-retention", "sales-gtm", "marketing-strategy" ] }, { "id": "design-ui", "label": "Design & UI", "description": "Implementing design systems, UI components, and frontend layout from a design or spec.", "capabilityIds": [ "design-implementation" ] }, { "id": "development", "label": "Development", "description": "General coding discipline, code review, GitHub PR workflow, API/SDK integration, and documentation.", "capabilityIds": [ "development-discipline", "code-review", "github-workflow", "integration-connectivity", "documentation", "documentation-authoring", "data-document-processing" ] }, { "id": "testing-qa", "label": "Testing & QA", "description": "Browser testing, visual and accessibility QA, and systematic debugging.", "capabilityIds": [ "testing-qa", "debugging" ] }, { "id": "databases", "label": "Databases", "description": "Schema design, query performance, migrations, and Postgres/Supabase-specific guidance.", "capabilityIds": [ "database" ] }, { "id": "security", "label": "Security", "description": "Codebase audit preparation and repository-grounded threat modeling.", "capabilityIds": [ "security-review" ] }, { "id": "devops-deployment", "label": "DevOps & Deployment", "description": "Deploying and operating applications, including cloud-specific guidance.", "capabilityIds": [ "deployment-cicd" ] }, { "id": "agent-workflows", "label": "Agent Workflows", "description": "Writing skills and plugins, migrating between agents, and orchestrating multi-agent work.", "capabilityIds": [ "agent-migration", "planning-workflow", "skill-authoring" ] }, { "id": "performance-monitoring", "label": "Performance & Monitoring", "description": "Analytics, event tracking, and network-level performance auditing.", "capabilityIds": [ "performance-monitoring" ] } ], "creators": [ { "id": "anthropic", "name": "Anthropic", "kind": "organization", "provenance": "official", "url": "https://github.com/anthropics" }, { "id": "openai", "name": "OpenAI", "kind": "organization", "provenance": "official", "url": "https://github.com/openai" }, { "id": "cursor", "name": "Cursor", "kind": "organization", "provenance": "official", "url": "https://github.com/cursor" }, { "id": "trailofbits", "name": "Trail of Bits", "kind": "organization", "provenance": "vendor", "url": "https://github.com/trailofbits" }, { "id": "nvidia", "name": "NVIDIA", "kind": "organization", "provenance": "vendor", "url": "https://github.com/NVIDIA" }, { "id": "supabase", "name": "Supabase", "kind": "organization", "provenance": "vendor", "url": "https://github.com/supabase" }, { "id": "awslabs", "name": "AWS Labs", "kind": "organization", "provenance": "vendor", "url": "https://github.com/awslabs" }, { "id": "n8n", "name": "n8n", "kind": "organization", "provenance": "vendor", "url": "https://github.com/n8n-io" }, { "id": "posthog", "name": "PostHog", "kind": "organization", "provenance": "vendor", "url": "https://github.com/PostHog" }, { "id": "obra", "name": "obra (Jesse Vincent)", "kind": "individual", "provenance": "community", "url": "https://github.com/obra" }, { "id": "virgiliojr94", "name": "virgiliojr94", "kind": "individual", "provenance": "community", "url": "https://github.com/virgiliojr94" }, { "id": "spencerpauly", "name": "spencerpauly", "kind": "individual", "provenance": "community", "url": "https://github.com/spencerpauly" }, { "id": "coreyhaines31", "name": "Corey Haines", "kind": "individual", "provenance": "community", "url": "https://github.com/coreyhaines31" } ], "sources": [ { "id": "obra-superpowers", "name": "obra/superpowers", "creatorId": "obra", "repoUrl": "https://github.com/obra/superpowers", "description": "A structured development methodology plugin for Claude Code — brainstorming, planning, TDD, debugging, and review.", "license": "MIT" }, { "id": "anthropics-skills", "name": "anthropics/skills", "creatorId": "anthropic", "repoUrl": "https://github.com/anthropics/skills", "description": "Anthropic's own reference skills: document generation, skill authoring, the Claude API, and design tooling.", "knownSkillCount": 17 }, { "id": "trailofbits-skills", "name": "trailofbits/skills", "creatorId": "trailofbits", "repoUrl": "https://github.com/trailofbits/skills", "description": "Trail of Bits's security research and audit-workflow skills.", "license": "CC-BY-SA-4.0" }, { "id": "nvidia-skills", "name": "NVIDIA/skills", "creatorId": "nvidia", "repoUrl": "https://github.com/NVIDIA/skills", "description": "NVIDIA's router across GPU acceleration, CUDA, robotics, and Physical AI workflows.", "license": "Apache-2.0" }, { "id": "virgiliojr94-book-to-skill", "name": "virgiliojr94/book-to-skill", "creatorId": "virgiliojr94", "repoUrl": "https://github.com/virgiliojr94/book-to-skill", "description": "Converts a document into a structured, reusable skill.", "license": "MIT" }, { "id": "openai-codex", "name": "openai/codex", "creatorId": "openai", "repoUrl": "https://github.com/openai/codex", "description": "The Codex agent itself — its bundled sample skills live here.", "license": "Apache-2.0" }, { "id": "openai-skills", "name": "openai/skills", "creatorId": "openai", "repoUrl": "https://github.com/openai/skills", "description": "OpenAI's curated Codex skill catalog (now deprecated in favor of openai/plugins, but still installable)." }, { "id": "cursor-docs", "name": "Cursor — Agent Skills (official docs)", "creatorId": "cursor", "repoUrl": "https://cursor.com/docs/context/skills", "description": "Cursor's own documentation for its bundled, no-install skills." }, { "id": "cursor-plugins", "name": "cursor/plugins", "creatorId": "cursor", "repoUrl": "https://github.com/cursor/plugins", "description": "Cursor's manually reviewed first-party plugin marketplace.", "license": "MIT" }, { "id": "spencerpauly-awesome-cursor-skills", "name": "spencerpauly/awesome-cursor-skills", "creatorId": "spencerpauly", "repoUrl": "https://github.com/spencerpauly/awesome-cursor-skills", "description": "A community collection organized by whether a skill is Cursor-native or portable.", "license": "CC0-1.0" }, { "id": "supabase-agent-skills", "name": "supabase/agent-skills", "creatorId": "supabase", "repoUrl": "https://github.com/supabase/agent-skills", "description": "Supabase's official skills for database, auth, edge functions, and Postgres performance.", "license": "MIT" }, { "id": "awslabs-agent-plugins", "name": "awslabs/agent-plugins", "creatorId": "awslabs", "repoUrl": "https://github.com/awslabs/agent-plugins", "description": "AWS's official plugins for architecting, deploying, and operating on AWS.", "license": "Apache-2.0" }, { "id": "n8n-io-skills", "name": "n8n-io/skills", "creatorId": "n8n", "repoUrl": "https://github.com/n8n-io/skills", "description": "n8n's official skills, paired with its instance-level MCP server.", "license": "Apache-2.0" }, { "id": "posthog-skills", "name": "PostHog/skills", "creatorId": "posthog", "repoUrl": "https://github.com/PostHog/skills", "description": "PostHog's official skills for analytics, feature flags, and error tracking.", "license": "MIT" }, { "id": "coreyhaines31-marketingskills", "name": "coreyhaines31/marketingskills", "creatorId": "coreyhaines31", "repoUrl": "https://github.com/coreyhaines31/marketingskills", "description": "Marketing skills for AI coding agents — CRO, copywriting, SEO, analytics, and growth engineering, built for technical marketers and founders.", "license": "MIT", "knownSkillCount": 49 } ], "skills": [ { "id": "superpowers", "name": "superpowers", "description": "A structured development methodology bundling brainstorming, planning, TDD, systematic debugging, and code review into one workflow rather than one narrow task.", "capabilities": [ "development-discipline", "debugging", "code-review" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" } ], "sourceId": "obra-superpowers", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-claude-code-skills/", "whatItDoes": [ "Bundles skills for brainstorming, planning, test-driven development, systematic debugging, and code review into one opinionated development methodology.", "Ships its own self-hosted plugin marketplace (`superpowers-dev`) rather than distributing as a loose SKILL.md." ], "whenToUse": [ "You want Claude Code to actually follow a repeatable process — plan, then TDD, then review — rather than freehand its way through a task.", "You're standardizing how a team's agent works across a whole project, not just one job." ], "notFor": [ "You need one narrow capability. This installs a whole methodology, not a composable single skill.", "You don't intend to follow the workflow it enforces — its value is entirely in the discipline, not in any one sub-skill used alone." ], "dependencies": [ "Claude Code plugin marketplace (`superpowers-dev`)" ], "caveat": "It's opinionated about process, not just capability — it only helps if you actually work the way it wants you to.", "workflowFit": "Brainstorm → plan → TDD implementation → systematic debugging → code review.", "topicIds": [ "development", "testing-qa" ], "url": "https://agentskills.site/skills/superpowers/" }, { "id": "document-skills", "name": "document-skills", "description": "Anthropic's official bundle for generating and editing Word, PDF, PowerPoint, and Excel files, with descriptions tuned to trigger on phrases like \"the deck\" or \"Word doc.\"", "capabilities": [ "data-document-processing" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" } ], "dependencies": [ "Claude Code plugin marketplace" ], "sourceId": "anthropics-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-claude-code-skills/", "whatItDoes": [ "Bundles four Anthropic-authored skills — `docx`, `pdf`, `pptx`, `xlsx` — each with a long, specific description tuned to trigger on exact phrasing like \"the deck\" or \"Word doc.\"" ], "whenToUse": [ "You want Claude Code to generate or edit an actual Office/PDF file, not just describe one in chat." ], "notFor": [ "You want a single document format — installing this pulls in all four, not one at a time, through the plugin route." ], "caveat": "Proprietary-licensed, not MIT — read the LICENSE.txt before redistributing, even though using it inside Claude Code is unrestricted.", "topicIds": [ "development" ], "url": "https://agentskills.site/skills/document-skills/" }, { "id": "example-skills", "name": "example-skills", "description": "Anthropic's reference bundle: skill-creator, mcp-builder, webapp-testing, frontend-design, canvas-design, theme-factory, and more — twelve skills installed together as one plugin.", "capabilities": [ "skill-authoring", "testing-qa", "design-implementation", "integration-connectivity" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" } ], "dependencies": [ "Claude Code plugin marketplace" ], "sourceId": "anthropics-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-claude-code-skills/", "whatItDoes": [ "One plugin bundling twelve Anthropic reference skills at once, including `skill-creator`, `mcp-builder`, `webapp-testing`, `frontend-design`, `canvas-design`, `theme-factory`, and `brand-guidelines`.", "`skill-creator` specifically runs Anthropic's eval workflow — a with-skill-vs-without-skill benchmark across isolated subagent runs, plus a blind A/B between two versions of a skill." ], "whenToUse": [ "You want Anthropic's own reference implementations for building, testing, or evaluating skills, or for frontend/design/MCP work.", "You specifically want `skill-creator`'s eval workflow to check whether a skill you wrote actually helps." ], "notFor": [ "You only want one of the twelve — the plugin route installs all twelve together (though nothing stops copying a single skill's folder into `~/.claude/skills/` by hand)." ], "caveat": "It's a twelve-skill grab-bag, not twelve independent listings — evaluate it as one bundle, not by any single sub-skill's name.", "topicIds": [ "design-ui", "development", "testing-qa", "agent-workflows" ], "url": "https://agentskills.site/skills/example-skills/" }, { "id": "claude-api", "name": "claude-api", "description": "Claude API and SDK documentation, packaged so Claude can reference method signatures directly while you build an LLM-powered app.", "capabilities": [ "integration-connectivity" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" } ], "sourceId": "anthropics-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-claude-code-skills/", "whatItDoes": [ "A single, narrow official skill packaging Claude API and SDK documentation so Claude references it directly instead of guessing at method signatures." ], "whenToUse": [ "You're building an app on the Claude API or SDK and want accurate method signatures rather than a model's memory of them." ], "notFor": [ "Your project doesn't touch the Claude API — it has no use outside that context." ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/claude-api/" }, { "id": "audit-context-building", "name": "audit-context-building", "description": "Reads a codebase function by function, records what each one assumes and depends on, and writes the results to files instead of filling up the conversation — built for pre-audit codebase understanding.", "capabilities": [ "security-review" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" }, { "agent": "cursor", "tier": "portable", "note": "Trail of Bits publishes to the open SKILL.md standard rather than declaring Cursor support directly." } ], "sourceId": "trailofbits-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-claude-code-skills/", "whatItDoes": [ "Reads a codebase function by function and records what each one assumes and depends on.", "Writes the results to files rather than keeping the accumulated context in the conversation — built specifically so a later security review starts from a durable map instead of a fresh read." ], "whenToUse": [ "Before a security review or audit of a codebase you don't already know well." ], "notFor": [ "You already understand the codebase well — this is a context-building step, not the review itself.", "You need the audit or review; pair it with something like `security-threat-model` for that half of the job." ], "caveat": "CC-BY-SA-4.0, a share-alike license — worth knowing before forking or redistributing it.", "related": [ { "skillId": "security-threat-model", "note": "Different agents, same phase of the job — audit-context-building maps a codebase before review, security-threat-model produces the review's output." } ], "workflowFit": "Codebase mapping → threat modeling / audit → remediation.", "topicIds": [ "security" ], "url": "https://agentskills.site/skills/audit-context-building/" }, { "id": "nvidia-skills", "name": "nvidia-skills", "description": "NVIDIA's own router across GPU acceleration, CUDA, agent training, inference, robotics, Physical AI, and simulation workflows.", "capabilities": [ "integration-connectivity" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" }, { "agent": "codex", "tier": "confirmed", "note": "NVIDIA's own repository states it is built to work in both Claude Code and Codex." }, { "agent": "cursor", "tier": "portable", "note": "Published to the open SKILL.md standard; not NVIDIA-declared Cursor support specifically." } ], "sourceId": "nvidia-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-claude-code-skills/", "whatItDoes": [ "Acts as a router across NVIDIA's own catalog: GPU acceleration, CUDA, agent training, data loading, inference, robotics, Physical AI, Omniverse, and simulation workflows." ], "whenToUse": [ "Your work touches GPU/CUDA programming, robotics, or NVIDIA's Physical AI stack." ], "notFor": [ "None of the above apply to your project — it's genuinely irrelevant otherwise." ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/nvidia-skills/" }, { "id": "book-to-skill", "name": "book-to-skill", "description": "Converts a PDF, EPUB, DOCX, or plain-text document into a structured skill, extracting frameworks and mental models rather than producing a summary.", "capabilities": [ "documentation-authoring" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" } ], "dependencies": [ "Shell access to run its extraction script" ], "sourceId": "virgiliojr94-book-to-skill", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-claude-code-skills/", "whatItDoes": [ "Converts a PDF, EPUB, DOCX, or plain-text document into a structured skill, extracting frameworks and mental models rather than producing a summary of the text." ], "whenToUse": [ "You have a book, spec, or long document you want turned into something Claude can apply as a repeatable skill, not just recall." ], "notFor": [ "You want a summary, not a skill — this specifically extracts reusable frameworks, which is a different output." ], "operationalSurface": [ "Runs its own extraction script, which needs shell and file access on first use." ], "caveat": "It needs shell access to run its own extraction script — the repo deliberately leaves `allowed-tools` out of its frontmatter to stay agent-neutral, so each host agent prompts for permission on first use rather than the skill pre-approving itself. Review what the script does before granting it.", "workflowFit": "Source document → book-to-skill → new reusable skill → skill-creator eval.", "topicIds": [ "development" ], "url": "https://agentskills.site/skills/book-to-skill/" }, { "id": "codex-skill-creator", "name": "skill-creator", "description": "Codex's own bundled tool for authoring a new skill, invoked with $skill-creator.", "capabilities": [ "skill-authoring" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "sourceId": "openai-codex", "sourceFileUrl": "https://github.com/openai/codex/tree/main/codex-rs/skills/src/assets/samples", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "Bundled with Codex — asks what the workflow does and whether it needs scripts, then writes the SKILL.md and supporting files." ], "whenToUse": [ "Writing a new Codex skill and want the scaffolding done for you rather than hand-authoring frontmatter." ], "notFor": [ "The `description` it produces is still worth editing yourself — a vague description won't trigger reliably." ], "workflowFit": "Idea → $skill-creator scaffold → edit the description for reliable triggering → use.", "topicIds": [ "agent-workflows" ], "url": "https://agentskills.site/skills/codex-skill-creator/" }, { "id": "review-agent", "name": "review-agent", "description": "Codex's bundled skill for reviewing changes — the current in-box option, no install needed.", "capabilities": [ "code-review" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "sourceId": "openai-codex", "sourceFileUrl": "https://github.com/openai/codex/tree/main/codex-rs/skills/src/assets/samples", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "The in-box option for reviewing changes in Codex — bundled, no install step." ], "whenToUse": [ "You want a code review inside Codex without installing anything first." ], "related": [ { "skillId": "cursor-review-builtins", "note": "The equivalent bundled review option on Cursor." }, { "skillId": "thermos", "note": "A much deeper, opt-in Cursor review plugin for when the built-in review isn't strict enough." } ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/review-agent/" }, { "id": "gh-fix-ci", "name": "gh-fix-ci", "description": "Inspects failing PR checks with gh, fetches the GitHub Actions logs, summarizes the failure, then proposes a fix plan and implements it only after explicit approval.", "capabilities": [ "deployment-cicd", "github-workflow" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "dependencies": [ "gh CLI", "GitHub Actions" ], "sourceId": "openai-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "Uses `gh` to inspect failing PR checks and fetch the GitHub Actions logs, summarizes the failure, then proposes a fix plan and implements it only after explicit approval.", "Treats non-Actions CI providers (e.g. Buildkite) as explicitly out of scope — it reports the details URL rather than pretending to handle them." ], "whenToUse": [ "A PR's GitHub Actions checks are failing and you want a triaged fix plan before anything gets changed." ], "notFor": [ "Your CI runs on a non-GitHub-Actions provider — it names this limitation itself rather than silently failing." ], "operationalSurface": [ "Executes `gh` CLI commands", "Reads GitHub Actions logs over the network", "Writes code changes only after your explicit approval" ], "caveat": "It references an optional `create-plan` skill that lived in the catalog's now-removed `.experimental` folder — that specific collaboration point no longer resolves.", "related": [ { "skillId": "gh-address-comments", "note": "The companion skill for working through PR review comments once CI is green." } ], "workflowFit": "Failing CI → triage → fix plan (approval gate) → implementation.", "topicIds": [ "development", "devops-deployment" ], "url": "https://agentskills.site/skills/gh-fix-ci/" }, { "id": "gh-address-comments", "name": "gh-address-comments", "description": "Finds the open PR for your current branch and works through its review comments with the gh CLI, checking gh auth status first rather than failing halfway through.", "capabilities": [ "github-workflow", "code-review" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "dependencies": [ "gh CLI" ], "sourceId": "openai-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "Finds the open PR for your current branch and works through its review comments using the `gh` CLI.", "Verifies `gh auth status` first and prompts you to authenticate rather than failing partway through — its own notes flag that sandboxing may block that check and that the command needs escalated permissions." ], "whenToUse": [ "You have an open PR with review comments and want them worked through systematically rather than one at a time from memory." ], "operationalSurface": [ "Executes `gh` CLI commands", "Reads and can act on PR review comments over the network" ], "related": [ { "skillId": "gh-fix-ci", "note": "The companion skill for triaging failing checks before or alongside working through review comments." } ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/gh-address-comments/" }, { "id": "codex-playwright", "name": "playwright", "description": "Drives a real browser from the terminal for navigation, form filling, screenshots, and data extraction — CLI-first, and won't write @playwright/test files unless asked.", "capabilities": [ "testing-qa" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "sourceId": "openai-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "Drives a real browser from the terminal for navigation, form filling, screenshots, and data extraction, using a bundled wrapper script so it works even without `playwright-cli` installed globally." ], "whenToUse": [ "You want the agent to actually operate a browser — click through a flow, take a screenshot, extract data — from the terminal." ], "notFor": [ "You want a `@playwright/test` test suite written — its instructions are explicit that it won't pivot to that unless you ask; \"automate the browser\" and \"write me a test suite\" are treated as different requests." ], "operationalSurface": [ "Drives a real browser", "Reads pages and can extract data from them" ], "related": [ { "skillId": "cursor-browser-qa-suite", "note": "The equivalent job on Cursor, built on Cursor's own browser and accessibility tree instead of a CLI wrapper." } ], "topicIds": [ "testing-qa" ], "url": "https://agentskills.site/skills/codex-playwright/" }, { "id": "security-threat-model", "name": "security-threat-model", "description": "Produces a repository-grounded threat model — trust boundaries, assets, attacker capabilities, abuse paths, mitigations — written to a markdown file. Roughly half its description is negative triggers.", "capabilities": [ "security-review" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "sourceId": "openai-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "Produces a repository-grounded threat model — trust boundaries, assets, attacker capabilities, abuse paths, mitigations — written to a Markdown file." ], "whenToUse": [ "You want a structured threat model grounded in the actual repository, not a generic security checklist." ], "notFor": [ "General architecture summaries, code review, or non-security design work — roughly half its own description is negative triggers spelling this out." ], "operationalSurface": [ "Reads the repository", "Writes a Markdown file with the resulting threat model" ], "related": [ { "skillId": "audit-context-building", "note": "Different agents, same phase of the job — audit-context-building maps a codebase before review; this produces the review's output." } ], "workflowFit": "Codebase mapping → threat modeling → mitigation planning → implementation.", "topicIds": [ "security" ], "url": "https://agentskills.site/skills/security-threat-model/" }, { "id": "migrate-to-codex", "name": "migrate-to-codex", "description": "Migrates instruction files, skills, agents, and MCP config from another agent into Codex's own files, without touching the source agent's files.", "capabilities": [ "agent-migration" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "sourceId": "openai-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "Migrates instruction files, skills, agents, and MCP config from another agent into Codex's own files (`AGENTS.md`, `.codex/`, `.agents/`, `~/.codex/`) once you've picked a target." ], "whenToUse": [ "You're moving a project from another agent — Claude Code in particular — into Codex and want the switching cost handled for you." ], "notFor": [ "You want to keep the source agent's setup intact for later — it's careful not to touch the source agent's files, but confirm that's still the behavior you expect before running it." ], "operationalSurface": [ "Writes to Codex config paths (`AGENTS.md`, `.codex/`, `.agents/`, `~/.codex/`)", "Does not modify the source agent's files or unrelated config, per its own instructions" ], "topicIds": [ "agent-workflows" ], "url": "https://agentskills.site/skills/migrate-to-codex/" }, { "id": "codex-pdf", "name": "pdf", "description": "Reads, creates, and reviews PDFs where layout matters, rendering pages for visual checks rather than only extracting text.", "capabilities": [ "data-document-processing" ], "agents": [ { "agent": "codex", "tier": "confirmed" } ], "dependencies": [ "Python environment (reportlab, pdfplumber, pypdf)" ], "sourceId": "openai-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-codex-skills/", "whatItDoes": [ "Reads, creates, and reviews PDFs where layout matters, rendering pages for visual checks rather than only extracting text." ], "whenToUse": [ "The PDF's layout is part of what you're checking or producing, not just the text content." ], "notFor": [ "You just need text extracted — a simpler text-only tool covers that without the Python dependency." ], "operationalSurface": [ "Reads and writes PDF files", "Renders pages for visual inspection" ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/codex-pdf/" }, { "id": "cursor-review-builtins", "name": "Cursor's built-in review skills", "description": "/review, /review-bugbot, and /review-security ship with Cursor by default — general review, automated bug-hunting review, and a security-focused review, with nothing to install.", "capabilities": [ "code-review", "security-review" ], "agents": [ { "agent": "cursor", "tier": "confirmed" } ], "overlaps": [ { "skillId": "parallel-code-review", "note": "Cursor already ships three review skills for free — install parallel-code-review only if you specifically want its four-subagent breadth." } ], "sourceId": "cursor-docs", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-cursor-skills/", "whatItDoes": [ "Three bundled slash commands: `/review` (general), `/review-bugbot` (automated bug-hunting review), and `/review-security` (security-focused)." ], "whenToUse": [ "You want a code review in Cursor without installing anything — this is what's already in the box." ], "notFor": [ "You specifically need the four-subagent breadth `parallel-code-review` provides — the built-ins don't fan out across parallel specialist passes." ], "related": [ { "skillId": "review-agent", "note": "The equivalent bundled review option on Codex." } ], "topicIds": [ "development", "security" ], "url": "https://agentskills.site/skills/cursor-review-builtins/" }, { "id": "cursor-create-skill", "name": "/create-skill", "description": "Cursor's built-in skill for writing a new skill, the recommended starting point over hand-authoring frontmatter.", "capabilities": [ "skill-authoring" ], "agents": [ { "agent": "cursor", "tier": "confirmed" } ], "sourceId": "cursor-docs", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-cursor-skills/", "whatItDoes": [ "Writes a new Cursor skill for you — the documented starting point over hand-authoring frontmatter." ], "whenToUse": [ "Authoring a single new skill for Cursor." ], "notFor": [ "You're building a full plugin — multiple skills plus agents, rules, and commands together — `create-plugin` scaffolds at that larger scope." ], "related": [ { "skillId": "create-plugin", "note": "Same job at a different scope — this writes one skill; create-plugin scaffolds a whole marketplace-ready plugin (skills, agents, rules, commands together)." } ], "topicIds": [ "agent-workflows" ], "url": "https://agentskills.site/skills/cursor-create-skill/" }, { "id": "parallel-code-review", "name": "parallel-code-review", "description": "Runs four read-only subagents in parallel — security, performance, correctness, readability — and merges the results into one prioritized review.", "capabilities": [ "code-review", "security-review" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native — depends on Cursor's parallel subagents." } ], "dependencies": [ "Cursor subagents" ], "overlaps": [ { "skillId": "cursor-review-builtins", "note": "Cursor already ships three review skills for free — install this only if you specifically want the four-subagent breadth." } ], "sourceId": "spencerpauly-awesome-cursor-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-cursor-skills/", "whatItDoes": [ "Fans four read-only subagents across security, performance, correctness, and readability, then merges the results into one prioritized report." ], "whenToUse": [ "You want a genuinely multi-angle review and are willing to spend the extra subagent time to get it." ], "notFor": [ "Cursor's built-in `/review-security` and `/review-bugbot` already cover your need — check those first since they cost nothing to try." ], "operationalSurface": [ "Runs four parallel, read-only subagent passes over the diff — no writes" ], "topicIds": [ "development", "security" ], "url": "https://agentskills.site/skills/parallel-code-review/" }, { "id": "cursor-browser-qa-suite", "name": "Cursor browser QA skills", "description": "A family of skills built on Cursor's built-in browser and accessibility tree — visual QA, responsive testing, dark-mode testing, and accessibility auditing.", "capabilities": [ "testing-qa" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native — built on Cursor's browser and accessibility tree." } ], "dependencies": [ "Cursor's built-in browser" ], "sourceId": "spencerpauly-awesome-cursor-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-cursor-skills/", "whatItDoes": [ "Consolidates four related skills from the same repository — visual QA, responsive testing, dark-mode testing, and accessibility auditing — all built on Cursor's own browser and accessibility tree." ], "whenToUse": [ "You want visual, responsive, dark-mode, or accessibility QA driven directly inside Cursor." ], "operationalSurface": [ "Drives Cursor's built-in browser", "Reads the accessibility tree" ], "related": [ { "skillId": "codex-playwright", "note": "The equivalent job on Codex, CLI-first instead of built on Cursor's browser." } ], "topicIds": [ "testing-qa" ], "url": "https://agentskills.site/skills/cursor-browser-qa-suite/" }, { "id": "network-request-auditing", "name": "network-request-auditing", "description": "Uses the browser's network log to flag failed requests, slowness, duplicates, and risky payloads after real user interactions.", "capabilities": [ "testing-qa", "performance-monitoring" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native — built on Cursor's browser network log." } ], "dependencies": [ "Cursor's built-in browser" ], "sourceId": "spencerpauly-awesome-cursor-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-cursor-skills/", "whatItDoes": [ "Reads the browser's network log after real user interactions to flag failed requests, slowness, duplicate calls, and risky payloads." ], "whenToUse": [ "You want network-level QA — not visual QA — after driving a flow in Cursor's browser." ], "operationalSurface": [ "Reads the browser's network log" ], "topicIds": [ "testing-qa", "performance-monitoring" ], "url": "https://agentskills.site/skills/network-request-auditing/" }, { "id": "adding-analytics", "name": "adding-analytics", "description": "Adds PostHog event tracking, page views, feature flags, and session replay to a web app.", "capabilities": [ "performance-monitoring" ], "agents": [ { "agent": "cursor", "tier": "confirmed" } ], "dependencies": [ "PostHog account" ], "overlaps": [ { "skillId": "posthog-official-skills", "note": "PostHog now publishes its own official skill collection — check it first, since it's maintained directly by the product this skill wraps." } ], "sourceId": "spencerpauly-awesome-cursor-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "sitePage": "/best-cursor-skills/", "whatItDoes": [ "Adds PostHog event tracking, page views, feature flags, and session replay to a web app." ], "whenToUse": [ "You're wiring up PostHog analytics in a Cursor project and want a community skill that already knows the setup steps." ], "notFor": [ "You'd rather use PostHog's own maintained skill collection — see the overlap note." ], "topicIds": [ "performance-monitoring" ], "url": "https://agentskills.site/skills/adding-analytics/" }, { "id": "supabase", "name": "supabase", "description": "Supabase's official, comprehensive skill covering Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, and Queues, plus client-library and SSR integration.", "capabilities": [ "database" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" }, { "agent": "cursor", "tier": "confirmed", "note": "Supabase's README names Cursor explicitly among \"18+ AI agents\" it's compatible with, distributed via the open Agent Skills format rather than a Cursor-specific mechanism." } ], "dependencies": [ "A Supabase project", "Optionally the Supabase CLI or Supabase MCP server" ], "sourceId": "supabase-agent-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Comprehensive Supabase development skill covering every core product: Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, and Queues.", "Covers client libraries and SSR integrations (`supabase-js`, `@supabase/ssr`) across Next.js, React, SvelteKit, Astro, and Remix, plus troubleshooting auth (sessions, JWTs, cookies, RLS) and using the Supabase CLI or MCP server." ], "whenToUse": [ "Building or debugging any part of a Supabase-backed app — auth, schema, edge functions, or client integration." ], "notFor": [ "You only need Postgres performance guidance — `supabase-postgres-best-practices` is the narrower, purpose-built entry for that." ], "related": [ { "skillId": "supabase-postgres-best-practices", "note": "Same source repository — this is the broad platform skill; the other is the narrow Postgres performance subset." } ], "caveat": "Codex isn't named in Supabase's own compatibility list (\"Claude Code, GitHub Copilot, Cursor, Cline, and many others\") — that's a real omission, not an oversight on our part.", "topicIds": [ "databases" ], "url": "https://agentskills.site/skills/supabase/" }, { "id": "supabase-postgres-best-practices", "name": "supabase-postgres-best-practices", "description": "Postgres performance-optimization guidelines from Supabase, covering query performance, connection management, schema design, RLS, and monitoring — prioritized by impact.", "capabilities": [ "database" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" }, { "agent": "cursor", "tier": "confirmed", "note": "Same compatibility statement as the general supabase skill — named explicitly among Supabase's 18+ supported agents." } ], "dependencies": [ "A Postgres or Supabase database to apply the guidance to" ], "sourceId": "supabase-agent-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Postgres performance-optimization guidance across eight categories, each prioritized by impact: query performance and RLS (critical), connection management (critical), schema design (high), concurrency/locking (medium-high), data access patterns (medium), and monitoring (low-medium)." ], "whenToUse": [ "Writing SQL, designing a schema, reviewing a performance problem, configuring connection pooling, or working with Row-Level Security." ], "notFor": [ "General Supabase platform work outside Postgres performance — the broader `supabase` skill covers that." ], "related": [ { "skillId": "supabase", "note": "Same source repository — the general platform skill this one narrows down from." } ], "topicIds": [ "databases" ], "url": "https://agentskills.site/skills/supabase-postgres-best-practices/" }, { "id": "databases-on-aws", "name": "databases-on-aws", "description": "Database guidance for the AWS portfolio — schema design, queries, migrations, and multi-tenant patterns — currently available for Aurora DSQL.", "capabilities": [ "database" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" }, { "agent": "codex", "tier": "confirmed", "note": "AWS's repo states Agent Plugins format support across Claude Code, Codex, and Cursor; only deploy-on-aws is separately confirmed listed in the Cursor Marketplace." } ], "sourceId": "awslabs-agent-plugins", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Database guidance for the AWS database portfolio: schema design, queries, migrations, and multi-tenant patterns." ], "whenToUse": [ "Designing or migrating a database on AWS, specifically on Aurora DSQL today." ], "notFor": [ "You need guidance for an AWS database service other than Aurora DSQL — AWS's own plugin table marks the rest of the portfolio \"Some Services Available (Aurora DSQL)\" only, not RDS, DynamoDB, or others yet." ], "caveat": "Named for the whole AWS database portfolio, but currently scoped to Aurora DSQL — don't assume broader engine coverage from the name.", "related": [ { "skillId": "deploy-on-aws", "note": "Same repository and marketplace — deployment guidance for what you build after the schema is designed." } ], "topicIds": [ "databases" ], "url": "https://agentskills.site/skills/databases-on-aws/" }, { "id": "deploy-on-aws", "name": "deploy-on-aws", "description": "Deploys applications to AWS with architecture recommendations, cost estimates, and infrastructure-as-code — one plugin in AWS's own Agent Plugins repository.", "capabilities": [ "deployment-cicd" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" }, { "agent": "codex", "tier": "confirmed" }, { "agent": "cursor", "tier": "confirmed", "note": "Listed directly in the Cursor Marketplace, per AWS's own install instructions." } ], "dependencies": [ "AWS account and credentials" ], "sourceId": "awslabs-agent-plugins", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Deploys applications to AWS with architecture recommendations, cost estimates, and infrastructure-as-code deployment." ], "whenToUse": [ "Deploying an application to AWS and you want architecture and cost guidance alongside the actual IaC." ], "notFor": [ "You need broad AWS database guidance rather than deployment — see `databases-on-aws`, currently scoped to Aurora DSQL." ], "operationalSurface": [ "Produces architecture recommendations, cost estimates, and IaC", "Can drive real AWS infrastructure changes if you act on its output" ], "caveat": "AWS's own README is explicit about the limits: \"Always review generated code before deployment\" and \"follow the principle of least privilege\" — it's an accelerator, not a replacement for review.", "related": [ { "skillId": "databases-on-aws", "note": "Same repository and marketplace — database guidance for what you deploy." } ], "workflowFit": "Architecture design → deploy-on-aws → operate on AWS.", "topicIds": [ "devops-deployment" ], "url": "https://agentskills.site/skills/deploy-on-aws/" }, { "id": "n8n-skills", "name": "n8n Skills", "description": "n8n's own bundle pairing 13 workflow-lifecycle skills with its instance-level MCP server, so an agent builds and edits n8n workflows correctly the first time.", "capabilities": [ "integration-connectivity" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" }, { "agent": "codex", "tier": "confirmed", "note": "Requires Codex ≥0.142.0 for root-plugin marketplace support, per n8n's own README." } ], "dependencies": [ "An n8n instance (Cloud or self-hosted, ≥2.2.0) with instance-level MCP enabled", "The `n8n-mcp` MCP server (auto-configured for Claude Code; added manually via `codex mcp add` for Codex)" ], "sourceId": "n8n-io-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Pairs 13 capability skills — covering sub-workflow reuse, expressions, loops/pagination, AI agents, error handling, credentials, Data Tables, and debugging — with n8n's instance-level MCP server.", "Ships a SessionStart hook that loads a routing skill every session and PreToolUse hooks that pull in the matching skill before high-impact MCP calls." ], "whenToUse": [ "You're building or editing n8n workflows through an agent connected to n8n's MCP server." ], "notFor": [ "You don't have a running n8n instance — this is guidance for driving n8n's MCP server well, not a general workflow-automation skill.", "You're on Cursor — n8n's own README says Cursor support doesn't exist yet and is open to contributors." ], "operationalSurface": [ "Calls the n8n MCP server to read, build, and edit workflows", "Hooks fire automatically at session start and before high-impact MCP tool calls" ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/n8n-skills/" }, { "id": "posthog-official-skills", "name": "PostHog skills (official)", "description": "PostHog's own official skill collection for analytics integration, feature flags, error tracking, and LLM analytics, auto-generated from PostHog's docs on every release.", "capabilities": [ "performance-monitoring" ], "agents": [ { "agent": "claude-code", "tier": "confirmed" } ], "overlaps": [ { "skillId": "adding-analytics", "note": "PostHog now publishes its own official skill collection — check it first, since it's maintained directly by the product this skill wraps." } ], "sourceId": "posthog-skills", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Official skills for the PostHog platform — analytics integration, feature flags, error tracking, and LLM analytics — generated by PostHog's own `context-mill` tool and updated automatically on each release." ], "whenToUse": [ "Integrating PostHog into a Claude Code project and want the vendor-maintained version rather than a community wrapper." ], "notFor": [ "You're not on Claude Code — no Codex or Cursor install path is documented." ], "caveat": "The same repository also ships separate \"team\" and \"community\" skill folders — this entry covers only the official PostHog-product skills, not those.", "topicIds": [ "performance-monitoring" ], "url": "https://agentskills.site/skills/posthog-official-skills/" }, { "id": "thermos", "name": "thermos", "description": "Runs two parallel Cursor subagents — a deep correctness/security audit and a strict maintainability rubric — and synthesizes both into one prioritized branch review.", "capabilities": [ "security-review", "code-review" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native plugin — parallel subagents and Cursor's own hook/plugin system, not a portable SKILL.md." } ], "dependencies": [ "Cursor subagents" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/thermos", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Runs two subagents in parallel over a diff: `thermo-nuclear-review` (bugs, breakages, security, devex, feature-gate leaks) and `thermo-nuclear-code-quality-review` (a strict maintainability rubric — code-judo, a 1k-line rule, spaghetti, boundary violations), then synthesizes deduplicated, prioritized findings." ], "whenToUse": [ "You want a deliberately harsh, deep review of a branch before merging — beyond what a general-purpose `/review` gives you." ], "notFor": [ "A quick sanity check is enough — the built-in `/review` or `/review-bugbot` are lighter-weight for that." ], "operationalSurface": [ "Reads `git diff` and the full contents of changed files", "Runs two parallel subagent passes; no writes or network calls documented" ], "overlaps": [ { "skillId": "cursor-team-kit", "note": "cursor-team-kit bundles the same thermo-nuclear-code-quality-review skill as one of its 17 — installing both gets you that reviewer twice." } ], "related": [ { "skillId": "review-agent", "note": "The equivalent bundled review option on Codex, far lighter-weight than thermos." } ], "topicIds": [ "development", "security" ], "url": "https://agentskills.site/skills/thermos/" }, { "id": "cursor-team-kit", "name": "Cursor Team Kit", "description": "A 17-skill Cursor plugin for CI, code review, shipping, and test reliability — loop-on-ci, review-and-ship, fix-ci, get-pr-comments, weekly-review, and more, installed together.", "capabilities": [ "code-review", "deployment-cicd", "testing-qa", "github-workflow" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native plugin — built around Cursor subagents and the plugin/hook system." } ], "dependencies": [ "Cursor subagents (for CI watching and code-quality review)", "`gh` CLI (PR/CI skills)", "Playwright (`run-smoke-tests`)" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/cursor-team-kit", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Bundles 17 skills for internal-style team workflows without third-party service integrations: watching and fixing CI (`loop-on-ci`, `fix-ci`), shipping (`review-and-ship`, `new-branch-and-pr`), PR hygiene (`get-pr-comments`, `make-pr-easy-to-review`, `pr-review-canvas`), and reporting (`weekly-review`, `what-did-i-get-done`).", "Also includes `thermo-nuclear-code-quality-review` — the same strict maintainability rubric `thermos` uses — and `verify-this`, a baseline/treatment claim-checker." ], "whenToUse": [ "You want a broad, ready-made set of CI/review/shipping workflows in Cursor without wiring up third-party services." ], "notFor": [ "You only want one job from the kit — the marketplace route installs all 17 together; there's no per-skill install." ], "operationalSurface": [ "Executes shell, `gh`, and Playwright commands", "Reads and writes git branches, commits, and PRs", "Reads GitHub Actions logs over the network" ], "caveat": "It's a 17-skill bundle installed as one plugin — you can't cherry-pick just `fix-ci` without pulling in the rest of the kit through the marketplace route.", "overlaps": [ { "skillId": "thermos", "note": "cursor-team-kit bundles the same thermo-nuclear-code-quality-review skill as thermos — installing both gets you that reviewer twice." }, { "skillId": "pr-review-canvas", "note": "pr-review-canvas is bundled inside cursor-team-kit as well as distributed as its own standalone plugin — the same skill either way." } ], "related": [ { "skillId": "gh-fix-ci", "note": "The equivalent CI-fixing job on Codex (`gh-fix-ci`/`fix-ci` solve the same problem on different agents)." }, { "skillId": "gh-address-comments", "note": "The equivalent PR-comment job on Codex (compare to the kit's `get-pr-comments`)." } ], "topicIds": [ "development", "testing-qa", "devops-deployment" ], "url": "https://agentskills.site/skills/cursor-team-kit/" }, { "id": "orchestrate", "name": "orchestrate", "description": "Fans a large task out across parallel Cursor cloud agents via the Cursor SDK — planners publish tasks, workers hand off, a script reconciles the tree from disk and git.", "capabilities": [ "planning-workflow" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Built on the Cursor TypeScript SDK and Cursor cloud agents — not a portable skill." } ], "dependencies": [ "`bun` on PATH", "A Cursor API key (`CURSOR_API_KEY`)", "Optional: a Slack app and bot token, for run visibility in a Slack thread" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/orchestrate", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Fans a large task out across parallel Cursor cloud agents: planners publish tasks, workers hand results back up, and a script reconciles the whole tree from disk and git so the spawn/wait/handoff loop keeps converging without long-running agent state." ], "whenToUse": [ "A task is genuinely large enough to split across multiple parallel cloud agents with planner/worker/verifier roles." ], "notFor": [ "A single-repo task a normal agent session handles fine — this carries real operational weight (API keys, optional Slack app) for jobs that don't need it." ], "operationalSurface": [ "Spawns and coordinates parallel Cursor cloud agents", "Executes local shell scripts via `bun`", "Network access to the Cursor API and, optionally, Slack's API" ], "caveat": "This is infrastructure for fanning work across many cloud agents at once — real setup cost for a job most single-repo tasks don't have.", "related": [ { "skillId": "cursor-sdk", "note": "orchestrate is built directly on the Cursor SDK's auth model — its own docs point there for the full picture." } ], "workflowFit": "Task planning → parallel cloud-agent execution → handoff reconciliation → review.", "topicIds": [ "agent-workflows" ], "url": "https://agentskills.site/skills/orchestrate/" }, { "id": "continual-learning", "name": "continual-learning", "description": "Automatically and incrementally keeps AGENTS.md up to date, mining new session transcripts on a cadence and updating matching bullets in place rather than rewriting the file.", "capabilities": [ "documentation" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native — built on Cursor's stop hooks, subagents, and local hook-state files." } ], "dependencies": [ "Cursor `stop` hooks", "Cursor subagents (`agents-memory-updater`)" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/continual-learning", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Combines a `stop` hook, a `continual-learning` skill, and an `agents-memory-updater` subagent to mine new or changed session transcripts and update `AGENTS.md` incrementally — reading the existing file first and updating matching bullets in place rather than rewriting it." ], "whenToUse": [ "You want AGENTS.md to stay current with what the agent actually learns across sessions, without manually curating it." ], "notFor": [ "You want it to fire mid-conversation on demand — `disable-model-invocation: true` means it never self-triggers; only the `stop` hook cadence (10 turns / 120 minutes by default) invokes it." ], "operationalSurface": [ "Reads session transcripts", "Writes incremental edits to `AGENTS.md`", "Keeps local hook state under `.cursor/hooks/state/`" ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/continual-learning/" }, { "id": "agent-compatibility", "name": "agent-compatibility", "description": "Scores how well a repo holds up under agent workflows — startup, validation, and docs reliability — by pairing a published CLI scan with three focused review agents.", "capabilities": [ "testing-qa" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native plugin — the CLI itself is a separate published npm package the plugin runs." } ], "dependencies": [ "The published `agent-compatibility` npm CLI, run via `npx`" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/agent-compatibility", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Pairs a deterministic, published `agent-compatibility` CLI scan with three focused review agents — cold-start/bootstrap, small-change verification, and docs-reliability — and blends them into one \"Agent Compatibility Score\" (70% deterministic, 30% workflow) with a short list of the highest-leverage fixes." ], "whenToUse": [ "You want a repeatable score for how easily an agent can bootstrap, verify changes in, and trust the docs of a given repository." ], "notFor": [ "You want a general code review — this specifically audits agent-workflow ergonomics, not code quality or correctness." ], "operationalSurface": [ "Runs `npx agent-compatibility` against the repo", "Reads repository files, the startup path, and documentation", "No writes documented" ], "topicIds": [ "testing-qa" ], "url": "https://agentskills.site/skills/agent-compatibility/" }, { "id": "cli-for-agent", "name": "cli-for-agent", "description": "Design and review guidance for building CLIs meant to be driven by coding agents — non-interactive flags, layered --help, stdin/pipelines, fast errors, idempotency, --dry-run.", "capabilities": [ "integration-connectivity" ], "agents": [ { "agent": "cursor", "tier": "confirmed" } ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/cli-for-agent", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "A single skill encoding patterns for CLIs meant to be driven by coding agents: non-interactive flags first, layered `--help` with examples, stdin and pipelines, fast actionable errors, idempotency, `--dry-run`, and predictable command structure." ], "whenToUse": [ "Building or refactoring a CLI, writing subcommand help, or reviewing whether an existing tool will block agents — interactive prompts, missing examples, ambiguous errors." ], "notFor": [ "The CLI you're building isn't meant to be driven by an agent — this is specifically about agent-friendliness, not general CLI UX." ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/cli-for-agent/" }, { "id": "create-plugin", "name": "create-plugin", "description": "Meta-workflow for scaffolding a marketplace-ready Cursor plugin — manifest, skills, rules, agents, and commands together — plus a pre-submission quality check.", "capabilities": [ "skill-authoring" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Cursor-native — scaffolds Cursor's own plugin.json/skills/rules/agents/commands format." } ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/create-plugin", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Scaffolds a new plugin directory with manifest, components, and repository wiring (`create-plugin-scaffold`), then runs a pre-submission quality check against marketplace expectations (`review-plugin-submission`).", "Bundles a `plugin-architect` agent that helps design the plugin's structure and component mix for a concrete use case, plus a `plugin-quality-gates` rule that keeps manifests and paths valid." ], "whenToUse": [ "You're building a whole Cursor plugin — multiple skills, agents, rules, or commands together — not just one skill." ], "notFor": [ "You only need one skill authored — `/create-skill` is the right scope for that, without the plugin-level scaffolding." ], "related": [ { "skillId": "cursor-create-skill", "note": "Same job at a smaller scope — `/create-skill` writes one skill; this scaffolds a whole plugin around several." } ], "topicIds": [ "agent-workflows" ], "url": "https://agentskills.site/skills/create-plugin/" }, { "id": "cursor-sdk", "name": "cursor-sdk", "description": "Integration guidance for building on the Cursor TypeScript SDK (@cursor/sdk) — invocation patterns, runtime choice, auth, streaming, MCP, and error handling.", "capabilities": [ "integration-connectivity" ], "agents": [ { "agent": "cursor", "tier": "confirmed" } ], "dependencies": [ "The `@cursor/sdk` package, for the integration code being built" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/cursor-sdk", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Covers the three `@cursor/sdk` invocation patterns (`Agent.prompt`, `Agent.create` + `agent.send`, `Agent.resume`), runtime choice (local vs. cloud), auth, streaming, MCP configuration, and error handling.", "Keeps its main SKILL.md short and reads a reference file only when the task clearly falls into one — runtime choice, auth, error handling, streaming, MCP, advanced features, or integration patterns." ], "whenToUse": [ "Integrating, installing, or writing code against the Cursor SDK — CI review bots, triage automation, chat integrations, or webhooks that run Cursor agents." ], "notFor": [ "You're not building against `@cursor/sdk` — it's a reference skill for that specific package." ], "related": [ { "skillId": "orchestrate", "note": "orchestrate is built directly on this SDK — this skill is the source of truth for its auth model." } ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/cursor-sdk/" }, { "id": "docs-canvas", "name": "docs-canvas", "description": "Renders architecture notes, API references, runbooks, or codebase walkthroughs as a navigable Cursor Canvas instead of a flat markdown file.", "capabilities": [ "documentation" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Requires Cursor Canvas specifically, not just Cursor generally." } ], "dependencies": [ "Cursor with Canvas enabled" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/docs-canvas", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Builds a Canvas presenting documentation with an overview card, a navigable table of contents, mixed prose/code/diagram body sections, and a references block." ], "whenToUse": [ "Turning a directory of markdown docs, a single large doc, or a codebase question into something scannable rather than a flat top-to-bottom read." ], "notFor": [ "You don't have Cursor Canvas enabled — this doesn't degrade to plain markdown, it needs the feature." ], "caveat": "The plugin's own README calls this an \"initial scaffold\" — the skill structure is complete, but the playbook itself is a starting outline rather than a fully-tuned one yet.", "related": [ { "skillId": "pr-review-canvas", "note": "Same Canvas pattern, different target — this is for documentation, that one is for PR diffs." } ], "topicIds": [ "development" ], "url": "https://agentskills.site/skills/docs-canvas/" }, { "id": "pr-review-canvas", "name": "pr-review-canvas", "description": "Renders a pull request diff as an interactive Cursor Canvas organized by reviewer value — core logic first, wiring condensed, boilerplate summarized.", "capabilities": [ "code-review" ], "agents": [ { "agent": "cursor", "tier": "confirmed", "note": "Requires Cursor Canvas specifically, not just Cursor generally." } ], "dependencies": [ "Cursor with Canvas enabled", "A diff source: local `git diff`, `gh pr diff`, or a Graphite stack (`gt`)" ], "sourceId": "cursor-plugins", "sourceFileUrl": "https://github.com/cursor/plugins/tree/main/pr-review-canvas", "lastVerified": "2026-08-16", "inspectionStatus": "inspected", "whatItDoes": [ "Groups a PR diff by reviewer value — core logic and behavior changes up top with full context, wiring/integration condensed, boilerplate summarized as a list — then layers in pseudocode, before/after traces, and inline callouts (`Subtle`, `Breaking`, `Race condition`, `Perf`) for the genuinely risky parts." ], "whenToUse": [ "Reviewing a PR and you want a walkthrough that surfaces real risk rather than a file-by-file diff, or summarizing a PR stack for a human reviewer." ], "notFor": [ "You don't have Cursor Canvas enabled.", "A plain diff view is enough — this is for PRs dense enough that reviewer guidance actually helps." ], "overlaps": [ { "skillId": "cursor-team-kit", "note": "This exact skill is also bundled inside cursor-team-kit — installing both gets you it twice." } ], "related": [ { "skillId": "docs-canvas", "note": "Same Canvas pattern, different target — this is for PR diffs, that one is for documentation." } ], "workflowFit": "Implementation → PR opened → canvas walkthrough → human review.", "topicIds": [ "development" ], "url": "https://agentskills.site/skills/pr-review-canvas/" }, { "id": "ab-testing", "name": "ab-testing", "description": "Plan, design, or implement an A/B test or experiment, or build a growth experimentation program.", "aliases": [ "A/B test", "split test", "experiment", "test this change", "variant copy", "multivariate test", "hypothesis", "should I test this" ], "capabilities": [ "paid-measurement" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/ab-testing", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "ad-creative", "name": "ad-creative", "description": "Generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform.", "aliases": [ "ad copy variations", "generate headlines", "RSA headlines", "bulk ad copy", "ad iterations", "creative testing", "ad performance optimization", "write me some ads" ], "capabilities": [ "paid-measurement" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/ad-creative", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "ads", "name": "ads", "description": "Work through paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms.", "aliases": [ "PPC", "paid media", "ROAS", "CPA", "ad campaign", "retargeting", "audience targeting", "Google Ads" ], "capabilities": [ "paid-measurement" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/ads", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "ai-seo", "name": "ai-seo", "description": "Optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers.", "aliases": [ "AEO", "GEO", "LLMO", "answer engine optimization", "generative engine optimization", "LLM optimization", "AI Overviews", "optimize for ChatGPT" ], "capabilities": [ "seo-content" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/ai-seo", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "analytics", "name": "analytics", "description": "Set up, improve, or audit analytics tracking and measurement.", "aliases": [ "set up tracking", "GA4", "Google Analytics", "conversion tracking", "event tracking", "UTM parameters", "tag manager", "GTM" ], "capabilities": [ "paid-measurement" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/analytics", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "aso", "name": "aso", "description": "Audit or optimize an App Store or Google Play listing.", "aliases": [ "ASO audit", "app store optimization", "optimize my app listing", "improve app visibility", "app store ranking", "audit my listing", "why aren", "improve my app conversion" ], "capabilities": [ "seo-content" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/aso", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "attribution", "name": "attribution", "description": "Figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools.", "aliases": [ "attribution model", "first-touch vs last-touch", "multi-touch", "which channel drives revenue", "what", "my dashboards disagree", "Google/Meta says X but GA says Y", "media mix model" ], "capabilities": [ "paid-measurement" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/attribution", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "churn-prevention", "name": "churn-prevention", "description": "Reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies.", "aliases": [ "churn", "cancel flow", "offboarding", "save offer", "dunning", "failed payment recovery", "win-back", "retention" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/churn-prevention", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "co-marketing", "name": "co-marketing", "description": "Find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities.", "aliases": [ "co-marketing", "partner marketing", "joint campaign", "who should we partner with", "integration marketing", "cross-promotion", "collaborate with another company", "partnership ideas" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/co-marketing", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "cold-email", "name": "cold-email", "description": "Write B2B cold emails and follow-up sequences that get replies.", "aliases": [ "cold outreach", "prospecting email", "outbound email", "email to leads", "reach out to prospects", "sales email", "follow-up email sequence", "nobody" ], "capabilities": [ "content-copy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/cold-email", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "community-marketing", "name": "community-marketing", "description": "Build and leverage online communities to drive product growth and brand loyalty.", "aliases": [ "build a community", "community strategy", "Discord community", "Slack community", "community-led growth", "brand advocates", "user community", "forum strategy" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/community-marketing", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "competitor-profiling", "name": "competitor-profiling", "description": "Research, profile, or analyze competitors from their URLs.", "aliases": [ "competitor profile", "competitor research", "competitor analysis", "profile this competitor", "analyze competitor", "competitive intelligence", "competitor deep dive", "who are my competitors" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/competitor-profiling", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "competitors", "name": "competitors", "description": "Create competitor comparison or alternative pages for SEO and sales enablement.", "aliases": [ "alternative page", "vs page", "competitor comparison", "comparison page", "[Product] vs [Product]", "[Product] alternative", "competitive landing pages", "how do we compare to X" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/competitors", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "content-strategy", "name": "content-strategy", "description": "Plan a content strategy, decide what content to create, or figure out what topics to cover.", "aliases": [ "what should I write about", "content ideas", "blog strategy", "topic clusters", "content planning", "editorial calendar", "content marketing", "content roadmap" ], "capabilities": [ "seo-content" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/content-strategy", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "copy-editing", "name": "copy-editing", "description": "Edit, review, or improve existing marketing copy, or refresh outdated content.", "aliases": [ "edit this copy", "review my copy", "copy feedback", "proofread", "polish this", "make this better", "copy sweep", "tighten this up" ], "capabilities": [ "content-copy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/copy-editing", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "cro", "name": "cro", "description": "Optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages, feature pages, lead capture forms, or contact forms.", "aliases": [ "conversion rate optimization", "this page isn", "improve conversions", "why isn", "my landing page sucks", "form abandonment", "nobody", "low conversion rate" ], "capabilities": [ "cro" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/cro", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "customer-research", "name": "customer-research", "description": "Conduct, analyze, or synthesize customer research.", "aliases": [ "ICP research", "talk to customers", "analyze transcripts", "customer interviews", "survey analysis", "support ticket analysis", "voice of customer", "VOC" ], "capabilities": [ "marketing-strategy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/customer-research", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "directory-submissions", "name": "directory-submissions", "description": "Submit a product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks and discovery.", "aliases": [ "submit to directories", "backlinks from directories", "list my product", "submit to Product Hunt", "BetaList", "TAAFT", "Futurepedia", "G2 listing" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/directory-submissions", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "emails", "name": "emails", "description": "Create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program.", "aliases": [ "email sequence", "drip campaign", "nurture sequence", "onboarding emails", "welcome sequence", "re-engagement emails", "email automation", "lifecycle emails" ], "capabilities": [ "content-copy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/emails", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "free-tools", "name": "free-tools", "description": "Plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness.", "aliases": [ "engineering as marketing", "free tool", "marketing tool", "calculator", "generator", "interactive tool", "lead gen tool", "build a tool for leads" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/free-tools", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "image", "name": "image", "description": "Create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets.", "aliases": [ "AI image generation", "generate an image", "create a graphic", "product mockup", "hero image", "social media graphic", "banner image", "cover photo" ], "capabilities": [ "content-copy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/image", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "influencer-marketing", "name": "influencer-marketing", "description": "Run influencer, creator, or ambassador partnerships to promote a product - vetting partners, structuring deals, briefing creators, and measuring ROI.", "aliases": [ "creator partnerships", "sponsorships", "YouTube sponsorships", "podcast sponsorships", "brand ambassador", "ambassador program", "creator program", "UGC creators" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/influencer-marketing", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "launch", "name": "launch", "description": "Plan a product launch, feature announcement, or release strategy.", "aliases": [ "Product Hunt", "feature release", "announcement", "go-to-market", "beta launch", "early access", "waitlist", "product update" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/launch", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "lead-magnets", "name": "lead-magnets", "description": "Create, plan, or optimize a lead magnet for email capture or lead generation.", "aliases": [ "lead magnet", "gated content", "content upgrade", "downloadable", "ebook", "cheat sheet", "checklist", "template download" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/lead-magnets", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "marketing-council", "name": "marketing-council", "description": "Get multiple expert marketing perspectives at once - a simulated board of advisors staffed by well-known marketers (Seth Godin, David Ogilvy, April Dunford, and others).", "aliases": [ "board of advisors", "advisory board", "what would Seth Godin say", "what would Ogilvy think", "channel Hormozi", "get multiple perspectives", "debate this", "have the council review" ], "capabilities": [ "marketing-strategy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/marketing-council", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "marketing-ideas", "name": "marketing-ideas", "description": "Generate marketing ideas, inspiration, or strategies for a SaaS or software product.", "aliases": [ "growth ideas", "how to market", "marketing strategies", "marketing tactics", "ways to promote", "ideas to grow", "what else can I try", "I don" ], "capabilities": [ "marketing-strategy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/marketing-ideas", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "marketing-loops", "name": "marketing-loops", "description": "Set up a recurring, self-running marketing workflow — a repeatable loop an AI agent runs on a cadence (weekly, daily, on a trigger) rather than a one-off task.", "aliases": [ "marketing loop", "recurring marketing workflow", "automate my marketing", "marketing on autopilot", "weekly marketing review", "ad fatigue check", "content refresh loop", "churn watch" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/marketing-loops", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "marketing-plan", "name": "marketing-plan", "description": "Build a comprehensive marketing plan for a client, an advisory engagement, or your own product.", "aliases": [ "growth plan", "GTM plan", "go-to-market plan", "AARRR plan", "90-day marketing plan", "12-month marketing roadmap", "fractional CMO plan", "fCMO plan." ], "capabilities": [ "marketing-strategy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/marketing-plan", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "marketing-psychology", "name": "marketing-psychology", "description": "Apply psychological principles, mental models, or behavioral science to marketing.", "aliases": [ "psychology", "mental models", "cognitive bias", "persuasion", "behavioral science", "why people buy", "decision-making", "consumer behavior" ], "capabilities": [ "marketing-strategy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/marketing-psychology", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "offers", "name": "offers", "description": "Design, construct, or improve an offer - the thing being sold - including value framing, bonuses, guarantees, and pricing structure.", "aliases": [ "offer", "offer design", "build an offer", "grand slam offer", "irresistible offer", "value stack", "bonus stack", "guarantee" ], "capabilities": [ "cro" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/offers", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "onboarding", "name": "onboarding", "description": "Optimize post-signup onboarding, user activation, first-run experience, or time-to-value.", "aliases": [ "onboarding flow", "activation rate", "user activation", "first-run experience", "empty states", "onboarding checklist", "aha moment", "new user experience" ], "capabilities": [ "cro" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/onboarding", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "paywalls", "name": "paywalls", "description": "Create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates.", "aliases": [ "paywall", "upgrade screen", "upgrade modal", "upsell", "feature gate", "convert free to paid", "freemium conversion", "trial expiration screen" ], "capabilities": [ "cro" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/paywalls", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "popups", "name": "popups", "description": "Create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes.", "aliases": [ "exit intent", "popup conversions", "modal optimization", "lead capture popup", "email popup", "announcement banner", "overlay", "collect emails with a popup" ], "capabilities": [ "cro" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/popups", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "pricing", "name": "pricing", "description": "Work through pricing decisions, packaging, or monetization strategy.", "aliases": [ "pricing tiers", "freemium", "free trial", "packaging", "price increase", "value metric", "Van Westendorp", "willingness to pay" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/pricing", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "product-marketing", "name": "product-marketing", "description": "Create or update the product marketing context document other skills read first.", "aliases": [ "product context", "marketing context", "set up context", "positioning", "who is my target audience", "describe my product", "ICP", "ideal customer profile" ], "capabilities": [ "marketing-strategy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/product-marketing", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "prospecting", "name": "prospecting", "description": "Find, qualify, and build a list of prospects to reach out to - B2B SaaS, general B2B, or local small business.", "aliases": [ "build a prospect list", "find prospects", "find leads", "lead gen list", "find SaaS companies that", "find B2B companies", "find local businesses", "ICP-fit accounts" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/prospecting", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "public-relations", "name": "public-relations", "description": "Work on public relations, earned media, press coverage, journalist outreach, or media strategy.", "aliases": [ "PR", "press", "press release", "press coverage", "media outreach", "pitch a journalist", "get featured", "media list" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/public-relations", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "referrals", "name": "referrals", "description": "Create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy.", "aliases": [ "referral", "affiliate", "ambassador", "word of mouth", "viral loop", "refer a friend", "partner program", "referral incentive" ], "capabilities": [ "growth-retention" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/referrals", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "revops", "name": "revops", "description": "Work through revenue operations, lead lifecycle management, or marketing-to-sales handoff processes.", "aliases": [ "revenue operations", "lead scoring", "lead routing", "MQL", "SQL", "pipeline stages", "deal desk", "CRM automation" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/revops", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "sales-enablement", "name": "sales-enablement", "description": "Create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts.", "aliases": [ "sales deck", "pitch deck", "one-pager", "leave-behind", "objection handling", "deal-specific ROI analysis", "demo script", "talk track" ], "capabilities": [ "sales-gtm" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/sales-enablement", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "schema", "name": "schema", "description": "Add, fix, or optimize schema markup and structured data on their site.", "aliases": [ "schema markup", "structured data", "JSON-LD", "rich snippets", "schema.org", "FAQ schema", "product schema", "review schema" ], "capabilities": [ "seo-content" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/schema", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "seo-audit", "name": "seo-audit", "description": "Audit, review, or diagnose SEO issues on their site.", "aliases": [ "technical SEO", "why am I not ranking", "SEO issues", "on-page SEO", "meta tags review", "SEO health check", "my traffic dropped", "lost rankings" ], "capabilities": [ "seo-content" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/seo-audit", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "signup", "name": "signup", "description": "Optimize signup, registration, account creation, or trial activation flows.", "aliases": [ "signup conversions", "registration friction", "signup form optimization", "free trial signup", "reduce signup dropoff", "account creation flow", "people aren", "signup abandonment" ], "capabilities": [ "cro" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/signup", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "site-architecture", "name": "site-architecture", "description": "Plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking.", "aliases": [ "sitemap", "site map", "visual sitemap", "site structure", "page hierarchy", "information architecture", "IA", "navigation design" ], "capabilities": [ "seo-content" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/site-architecture", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "sms", "name": "sms", "description": "Plan, build, or optimize SMS or MMS marketing — including welcome flows, abandoned cart texts, post-purchase, win-back, promotional sends, or transactional/auth SMS.", "aliases": [ "SMS marketing", "text message campaigns", "SMS sequence", "SMS automation", "abandoned cart text", "post-purchase SMS", "Klaviyo SMS", "Postscript" ], "capabilities": [ "content-copy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/sms", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "social", "name": "social", "description": "Create, schedule, or optimize social media content for LinkedIn, X, Instagram, TikTok, and Facebook, or do social listening and engagement triage.", "aliases": [ "LinkedIn post", "Twitter thread", "social media", "content calendar", "social scheduling", "engagement", "viral content", "what should I post" ], "capabilities": [ "content-copy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/social", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "video", "name": "video", "description": "Create, generate, or produce video content using AI tools or programmatic frameworks.", "aliases": [ "video production", "AI video", "Remotion", "Hyperframes", "HeyGen", "Synthesia", "Veo", "Sora" ], "capabilities": [ "content-copy" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/video", "inspectionStatus": "catalogued", "lastVerified": "2026-08-16", "topicIds": [ "marketing" ], "url": null }, { "id": "programmatic-seo", "name": "programmatic-seo", "description": "Builds SEO-optimized pages at scale from templates and data — twelve playbooks (locations, comparisons, integrations, glossary, and more), chosen deliberately to avoid thin-content penalties.", "aliases": [ "pseo", "programmatic pages", "template pages", "pages at scale", "directory pages", "location pages" ], "capabilities": [ "seo-content", "programmatic-seo" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "operationalSurface": [ "Reads `.agents/product-marketing.md` (or the legacy `.claude/` path) if present, for shared product context — no writes or network access of its own" ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/programmatic-seo", "inspectionStatus": "inspected", "lastVerified": "2026-08-16", "whatItDoes": [ "Walks through business context, opportunity assessment, and competitive landscape, then picks from twelve documented playbooks — templates, curation, conversions, comparisons, locations, personas, integrations, glossary, translations, directories, profiles — based on what data you actually have.", "Centers the strategy on a data-defensibility hierarchy (proprietary beats product-derived beats user-generated beats licensed beats public) and a quality bar meant to avoid Google's thin-content and doorway-page penalties, not just generate volume.", "Outputs a strategy document plus a page template (URL structure, title/meta templates, content outline, schema) rather than the pages themselves." ], "whenToUse": [ "You want to target many similar keyword patterns — locations, integrations, comparisons, \"X vs Y,\" or directory-style pages — with a repeatable template rather than hand-writing each page.", "You have a real data source to drive the pages (proprietary, product-derived, or at minimum licensed/public) and want a framework for keeping each page genuinely unique rather than a template with swapped variables." ], "notFor": [ "You're auditing SEO problems on pages that already exist — that's `seo-audit`, which this skill explicitly defers to.", "You're planning general content strategy rather than templated pages at scale — see `content-strategy`.", "You don't have a data source that can support real per-page uniqueness — the skill's own principles flag swapped-variable pages as a common mistake and Google penalty risk, not a shortcut worth taking." ], "caveat": "It explicitly routes two adjacent jobs elsewhere in its own description: auditing existing pages to `seo-audit`, and content strategy planning to `content-strategy` — a real signal of a carefully scoped trigger, not a generic \"SEO skill.\"", "related": [ { "skillId": "seo-audit", "note": "The source's own Related Skills section: for auditing programmatic pages after launch." }, { "skillId": "schema", "note": "The source's own Related Skills section: for adding structured data to the pages this skill designs." }, { "skillId": "site-architecture", "note": "The source's own Related Skills section: for the page hierarchy, URL structure, and internal linking the pages need." }, { "skillId": "competitors", "note": "The source's own Related Skills section: for the comparison-page playbook specifically." } ], "workflowFit": "Opportunity assessment → template design → programmatic-seo build → schema markup → site-architecture linking → seo-audit after launch.", "topicIds": [ "marketing" ], "url": "https://agentskills.site/skills/programmatic-seo/" }, { "id": "copywriting", "name": "copywriting", "description": "Writes or rewrites persuasive marketing copy for any page — homepage, landing, pricing, feature — built around clarity, specificity, and customer language over company language.", "aliases": [ "landing page copy", "headline copy", "sales copy", "conversion copy", "marketing copy", "hero copy" ], "capabilities": [ "content-copy", "copywriting" ], "agents": [ { "agent": "claude-code", "tier": "confirmed", "note": "marketingskills' README states the collection \"works with Claude Code, OpenAI Codex, Cursor, Windsurf, and any agent that supports the Agent Skills spec\" as a collection-wide claim." }, { "agent": "codex", "tier": "confirmed", "note": "Same collection-wide compatibility statement." }, { "agent": "cursor", "tier": "confirmed", "note": "Same collection-wide compatibility statement." } ], "operationalSurface": [ "Reads `.agents/product-marketing.md` (or the legacy `.claude/` path) if present, for shared product context — no writes or network access of its own" ], "sourceId": "coreyhaines31-marketingskills", "sourceFileUrl": "https://github.com/coreyhaines31/marketingskills/tree/main/skills/copywriting", "inspectionStatus": "inspected", "lastVerified": "2026-08-16", "whatItDoes": [ "Gathers page purpose, audience, product/offer, and traffic context before writing, then applies a fixed set of principles: clarity over cleverness, benefits over features, specificity over vagueness, customer language over company language, one idea per section.", "Applies concrete style rules (simple over complex, active over passive, no exclamation points, no unearned adverbs) and explicitly flags fabricated statistics or testimonials as a trust and legal problem, not just a style issue.", "Outputs organized page copy (headline, subheadline, CTA, section-by-section body), annotations explaining the reasoning behind key choices, and 2-3 alternative options for headlines and CTAs." ], "whenToUse": [ "You need copy written or rewritten for a page meant to persuade — homepage, landing page, pricing, feature, or about page.", "Existing copy reads unnatural, vague, or unconvincing and you want it rebuilt around a stated set of principles rather than a generic rewrite." ], "notFor": [ "You're polishing a draft line-by-line rather than writing new copy — that's `copy-editing`, meant to run after this skill's draft.", "The page's structure or conversion strategy is the actual problem, not the words on it — see `cro`.", "You need email, popup, or SMS copy specifically — those have their own skills (`emails`, `popups`, `sms`) tuned to those formats." ], "caveat": "It draws a hard line on fabricated proof: \"Fabricated statistics or testimonials erode trust and create legal liability\" is stated as a principle, not a suggestion — worth knowing if you're hoping it will invent social proof for you.", "related": [ { "skillId": "copy-editing", "note": "The source's own Related Skills section: for polishing existing copy, meant to run after this skill's draft." }, { "skillId": "cro", "note": "The source's own Related Skills section: if page structure or strategy needs work, not just the copy." }, { "skillId": "emails", "note": "The source's own Related Skills section: for email-specific copywriting." }, { "skillId": "popups", "note": "The source's own Related Skills section: for popup and modal copy." }, { "skillId": "ab-testing", "note": "The source's own Related Skills section: to test copy variations once written." } ], "workflowFit": "product-marketing context → copywriting draft → copy-editing polish → ab-testing to validate.", "topicIds": [ "marketing" ], "url": "https://agentskills.site/skills/copywriting/" } ] }