agentleFS
tykisgodtykisgod/quick-question/skills/doc-tidy/SKILL.md

doc-tidy

Skill12 starsChanged 8 months agoMITView on GitHub

Scan the repo for scattered documentation files, analyze organization issues, and output cleanup recommendations. Analysis only — no changes made.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All files and directory structure under Docs/ (recursive)

    line 15
  2. Distinctive:

    Leave alone design docs synced from external sources (e.g., Notion exports.

    line 83

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).

Execution Steps

1. Full Scan

Dispatch 3 parallel Explore subagents (model: haiku) to collect a documentation inventory:

Subagent A — Root + Docs/

  • All .md files in root directory (except CLAUDE.md, AGENTS.md)
  • All files and directory structure under Docs/ (recursive)
  • For each file: path, first line content, line count

Subagent B — In-code documentation under Assets/

  • All .md files under Assets/ (recursive)
  • Including README, ARCHITECTURE, API_REFERENCE, CHANGELOG, AGENTS.md, etc.
  • For each file: path, first line content, line count

Subagent C — Config & tool documentation

  • .claude/ directory structure
  • Documentation under scripts/
  • Templates under .github/
  • Root config files (.mcp.json, opencode.json, etc.)

2. Classify

Categorize all documents by:

CategoryDescription
Long-term designSystem architecture, module design, data config (should be centrally managed)
In-code docsREADME, API reference, dev guides (should live with the code)
Branch artifactsReview outputs, spec files, timelines (should be archived after merge)
Temporary filestmp-*, one-off bug reports, old prompts (should be cleaned or archived)
Project entry pointsCLAUDE.md, AGENTS.md, PR templates (should stay in root)
Tool configSkills, hooks, script docs (each has its place, don't move)

3. Find Issues

Check and report:

  • Root pollution: files in root that shouldn't be there
  • Unorganized accumulation: directories with >10 files and no subdirectory structure
  • Temporal mixing: long-term docs and temporary artifacts in the same directory
  • Duplicate docs: files with highly similar names or content across directories
  • Orphaned docs: documents referencing deleted modules or outdated code
  • Missing docs: Service modules with code but no documentation at all

4. Output Cleanup Plan

Format:

## Current State Summary
- X documentation files across Y locations
- Main issues: 1, 2, 3 (one sentence each)

## Issue List
For each issue: location, description, number of files affected

## Recommended Plan
### Target Directory Structure
(tree diagram)

### Specific Actions
Priority ordered:
1. Delete (temporary files, confirmed unused)
2. Move (archive, categorize)
3. Merge (eliminate duplicates)
4. Fill gaps (important modules missing docs — flag but don't rush)

### Leave Alone
Explicitly list locations that are well-organized and need no changes

Notes

  • Analysis only — do not execute: output the plan and wait for user confirmation
  • Leave alone design docs synced from external sources (e.g., Notion exports; their structure is managed externally), skill files, and in-code READMEs (unless duplicated)
  • For docs where staleness is uncertain, mark as "needs confirmation" rather than suggesting deletion

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.