Doc tidy
Scan the repo for scattered documentation files, analyze organization issues, and output cleanup recommendations. Analysis only — no changes made.From its SKILL.md
npx -y skills add tykisgod/quick-question --skill doc-tidyAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 10 stars10 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.
SKILL.md
3.4 KB, 749 tokens by cl100k_base, as published. Nobody here has run it
Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).
Scan the repo for scattered documentation files, analyze organization issues, and output cleanup recommendations. Analysis only — no changes made.
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:
| Category | Description |
|---|---|
| Long-term design | System architecture, module design, data config (should be centrally managed) |
| In-code docs | README, API reference, dev guides (should live with the code) |
| Branch artifacts | Review outputs, spec files, timelines (should be archived after merge) |
| Temporary files | tmp-*, one-off bug reports, old prompts (should be cleaned or archived) |
| Project entry points | CLAUDE.md, AGENTS.md, PR templates (should stay in root) |
| Tool config | Skills, 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
Important Notes
- Analysis only — do not execute — output the plan and wait for user confirmation
- Do not touch design docs synced from external sources (e.g., Notion exports) — their structure is managed externally
- Do not touch skill files — they are not ordinary documentation
- Do not touch in-code READMEs — unless duplicates are found, keep them in place
- For docs where staleness is uncertain, mark as "needs confirmation" rather than suggesting deletion
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most research analysis skills give in 749 tokens
Counted across 1,213 of the 2,113 authors here whose files we hold, read 2026-09-06
- Cite sources for every important claimin 47 of 1213, across 38 files
- Separate facts from inferences and recommendationsin 21 of 1213, across 12 files
- Write findings to a markdown filein 19 of 1213
- Label every insight with a confidence levelin 18 of 1213, across 8 files
- Read product marketing context before asking questionsin 18 of 1213, across 8 files
- Rank themes by frequency and intensityin 16 of 1213, across 6 files
- Establish research mode before proceedingin 16 of 1213, across 6 files
- Segment survey responses by customer tier or tenurein 16 of 1213, across 6 files
- Categorize support tickets before analyzingin 16 of 1213, across 6 files
- Weight research sources from the last twelve monthsin 16 of 1213, across 6 files
- Use at least five data points per segmentin 15 of 1213, across 5 files
- Extract verbatim quotes for all research findingsin 15 of 1213, across 5 files
Said here and by no other author read
- Scan repository for all documentation files
- Categorize documents by type and purpose
- Identify root pollution and unorganized directories
- Detect duplicate or orphaned documentation files
- Create a structured cleanup recommendation plan
- Prioritize deletion of temporary files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.