agentsclimarketplace

Audit agent docs

Skill Mergemat/agent-readiness-skills/skills/audit-agent-docs

Harness-agnostic skills for agent-readable repos and task prep

Install
npx -y skills add Mergemat/agent-readiness-skills --skill audit-agent-docs

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Audits a repository's agent-readable docs for whether an agent can safely start work. Use when user asks if a repo is ready for coding agents, wants readiness gaps, or asks to review AGENTS.md, CONTEXT.md, docs/agents, build, test, owner, or tool policy docs.

SKILL.md

1.6 KB, 320 tokens by cl100k_base, as published. Nobody here has run it

Audit Agent Docs

Audit whether existing project docs give an agent enough facts to start work without guessing.

Do not edit by default. Report gaps first.

Inspect

Look for:

  • root agent instructions: AGENTS.md, CLAUDE.md, or equivalent
  • domain language: CONTEXT.md or CONTEXT-MAP.md
  • durable decisions: docs/adr/
  • agent docs: docs/agents/ or project equivalent
  • build, test, owner, security, and tool policy facts
  • package scripts, CI config, test config, and obvious entrypoints

If files are absent, inspect the repo directly before calling it a gap.

Audit Questions

The docs should let an agent answer:

  • Where should I start reading?
  • How do I install, build, run, lint, typecheck, and test?
  • Which modules are likely in scope?
  • Which paths or actions need approval?
  • Who owns decisions or review?
  • Which known risks should not be "fixed" accidentally?
  • Which tools, connectors, skills, hooks, and side effects are allowed?

For a deeper checklist, use readiness-questions.md.

Output

Return:

  • ready, ready_with_gaps, or not_ready
  • highest-risk gaps first
  • evidence: file path or command result
  • concrete fix for each gap
  • docs that are redundant or should become skills

Do not demand placeholder docs. If a fact is not needed for safe work, say so.

What ships with it: 1 file

954 B alongside SKILL.md

references/

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.