Skill profile · Inspected
agent-compatibility
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.
What it actually does
- Pairs a deterministic, published
agent-compatibilityCLI 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.
When to use it — and when not to
Use it when
- You want a repeatable score for how easily an agent can bootstrap, verify changes in, and trust the docs of a given repository.
Not for
- You want a general code review — this specifically audits agent-workflow ergonomics, not code quality or correctness.
Agent compatibility
- Cursor
Cursor-native plugin — the CLI itself is a separate published npm package the plugin runs.
Confirmed means the skill’s own source or vendor states it works with that agent. Portable means it only reaches that agent through the shared SKILL.md format and a directory convention — real, but a weaker claim. An agent with no entry here isn’t known to be unsupported; it simply isn’t documented either way, so nothing is claimed. Full model on Agent Skills Compatibility.
Requirements and operational surface
Depends on
- The published
agent-compatibilitynpm CLI, run vianpx
What it actually does at runtime
- Runs
npx agent-compatibilityagainst the repo - Reads repository files, the startup path, and documentation
- No writes documented
More from cursor/plugins
Other skills from the same source.
- orchestrateFans 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.
- continual-learningAutomatically 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.
- cli-for-agentDesign 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.
- create-pluginMeta-workflow for scaffolding a marketplace-ready Cursor plugin — manifest, skills, rules, agents, and commands together — plus a pre-submission quality check.
- cursor-sdkIntegration guidance for building on the Cursor TypeScript SDK (@cursor/sdk) — invocation patterns, runtime choice, auth, streaming, MCP, and error handling.
Evidence and provenance
Maintained by Cursor (official). Primary source: cursor/plugins, last checked against this page’s claims on . This page summarizes and analyzes that source — it isn’t a copy of its SKILL.md or README, and installation happens at the source, not here.
Topic: Testing & QA.