agentsclimarketplace

Docs audit

Skill Statusnone420/Skills/adapters/plugin/skills/docs-audit

Bounded repository memory and evidence-backed documentation skill for Codex/Claude Code

Install
npx -y skills add Statusnone420/Skills --skill docs-audit

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

3 things to look at

  • 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 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

Audit documentation and return prioritized evidence-backed findings.

SKILL.md

1.3 KB, 240 tokens by cl100k_base, as published. Nobody here has run it

Docs Audit

This is the explicit thin route for the fixed command audit. Treat all trailing text as that command's raw trailing text; never reinterpret it as another command.

Load and follow the sibling Diátaxis Docs skill, including its shared safety, evidence, health, and result contracts. The selected command contract below is the complete canonical commands.md contract for audit; do not load commands.md, and load no additional playbook beyond those linked here. If a required shared resource is unavailable, stop and report that the command could not be executed; do not invent a fallback.

Selected command contract (canonical)

  • audit [scope] Audit a scope.

audit [scope]: make no edits. Its first repository-evidence action is the same installed checker invocation Map uses, with --scope <repository-relative-directory> only when the user explicitly requested one component. Consume the engine's boundary and manifest identity before opening evidence. Then return numbered, prioritized semantic findings with file/line evidence from at most four directly relevant nonignored files. Do not rebuild the repository inventory or substitute a model-selected boundary.

What ships with it: 3 files

10.1 KB alongside SKILL.md

agents/

assets/

Keep looking

Skills are one crate of 328,083. 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.