agentleFS
Sign inStart free
paulo-yamagishipaulo-yamagishi/claude-code-setup/.claude/skills/verify-docs/SKILL.md

verify-docs

Skill2 starsChanged 9 months agoMITView on GitHub

Validate JSON, file paths, and settings keys across all docs

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use Bash(node -e 'JSON.parse(require("fs").readFileSync("/dev/stdin","utf8"))' < tmpfile) or inline the JSON string

    line 26
  2. Distinctive:

    Verify each referenced file or directory actually exists using Glob

    line 32
  3. Distinctive:

    If no issues found, report: "All docs passed verification."

    line 47

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Verify Docs

Validate all documentation files in the repo for correctness.

Steps

  1. Collect files: Glob all .md files in these directories:
    • core/
    • projects/
    • templates/
    • skill/
    • .claude/skills/
    • .claude/rules/
  2. Validate JSON code blocks: For each file, extract all ```json fenced code blocks and validate each one:
    • Use Bash(node -e 'JSON.parse(require("fs").readFileSync("/dev/stdin","utf8"))' < tmpfile) or inline the JSON string
    • Flag: trailing commas, comments (// or /* */), single quotes, unquoted keys
    • Record file path and line number of each invalid block
  3. Validate file paths: Extract all relative file paths referenced in the docs (patterns like core/, .claude/, projects/, templates/, skill/):
    • Grep for path-like references
    • Verify each referenced file or directory actually exists using Glob
    • Flag broken references with file and line number
  4. Validate settings keys: Extract settings keys used in JSON examples (e.g., permissions, allow, deny, hooks, mcpServers):
    • Cross-check against skill/SKILL.md Section 4 (Config Reference) as the source of truth
    • Flag any key not present in the reference
  5. Validate hook events: Extract hook event names (e.g., PreToolUse, PostToolUse, Stop, SubagentStop):
    • Cross-check against known valid events in core/hooks-guide.md
    • Flag unrecognized events
  6. Report: Group all issues by file. For each issue, show:
    • File path and line number
    • Issue type: INVALID_JSON, BROKEN_PATH, UNKNOWN_KEY, UNKNOWN_EVENT
    • Description of the problem
    • If no issues found, report: "All docs passed verification."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free