agentleFS
Sign inStart free
alanbenalanben/ClaudeSkills/reindex-docs/SKILL.md

reindex-docs

Skill0 starsChanged 10 months agoMITView on GitHub

Re-index all PDF and HTML documents, update index.html, and commit/push changes to the repository

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. hishamkaram/markdown-memory★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. About 0 are common, 11 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Use Glob to find all PDF files: /*.pdf

    line 17
  2. Very specific:

    Use Glob to find all HTML files: /*.html

    line 18
  3. Distinctive:

    Run these searches in parallel for efficiency

    line 19
  4. Very specific:

    Read the existing index.html to understand the structure

    line 22
  5. Very specific:

    Update the last-updated date to today's date (format: YYYY-MM-DD)

    line 26
  6. Very specific:

    Update the documentTree object to include:

    line 27
  7. Distinctive:

    All newly found documents

    line 28
  8. Distinctive:

    Remove any empty folders that have no documents

    line 41
  9. Distinctive:

    Add all untracked files (new documents)

    line 44
  10. Very specific:

    Commit index.html changes with descriptive message

    line 45
  11. Distinctive:

    Commit new document files with descriptive message

    line 46
  12. Distinctive:

    Use proper commit message format with Claude Code attribution

    line 48
  13. Distinctive:

    Use this format for commits:

    line 52
  14. Distinctive:

    Keep sections collapsed by default for clean navigation

    line 90
  15. Distinctive:

    Use relative paths for all document links

    line 91
  16. Distinctive:

    Follow the existing naming conventions for document titles

    line 92
  17. Distinctive:

    After completion, provide a summary of:

    line 96

≈ “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

Reindex Documents Skill

You are a specialized agent for maintaining the document index in this static document repository.

Your Task

Re-index all PDF and HTML documents in the repository and update index.html, then commit and push the changes.

Process Steps

  1. Scan for all documents
    • Use Glob to find all PDF files: **/*.pdf
    • Use Glob to find all HTML files: **/*.html
    • Run these searches in parallel for efficiency
  2. Read current index.html
    • Read the existing index.html to understand the structure
    • Note the current documentTree JavaScript object structure
  3. Update index.html with new documents
    • Update the last-updated date to today's date (format: YYYY-MM-DD)
    • Update the documentTree object to include:
      • All newly found documents
      • Proper Client → Project → Section → Folder hierarchy
      • Documents sorted in reverse chronological order (newest first)
      • Clean, readable document titles
      • Relative paths from root
  4. Organizational Rules
    • Clients (top level): Turnbuckle, Nextgen, Loeries, MachinaXX, etc.
    • Projects (under clients): RentaStore, Adstream, LifeGauge, etc.
    • Sections (under projects): Meeting notes, Technical, Projects, Programs, etc.
    • Folders (under sections): Webstream, Phase 4, Modernization Program, etc.
    • Documents: Individual PDF and HTML files
    • Sort documents by date in reverse chronological order (most recent first)
    • Remove any empty folders that have no documents
  5. Commit and Push
    • Add all untracked files (new documents)
    • Commit index.html changes with descriptive message
    • Commit new document files with descriptive message
    • Push all commits to remote repository
    • Use proper commit message format with Claude Code attribution

Commit Message Format

Use this format for commits:

Update index with new documents - [Month Year]

Added/Updated documents:
- Client/Project: Document description
- Client/Project: Document description

Updated last modified date to YYYY-MM-DD

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

For new document files:

Add new client documents - [Month Year]

New documents added:
- Client/Project: Document description
- Client/Project: Document description

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

Important Notes

  • Exclude these HTML files from the document index (they are system files):
    • index.html (the index itself)
    • repos.html (repository index)
    • access-denied.html (security page)
  • Maintain the existing JavaScript structure and styling
  • Preserve the auth.js script reference in the head section
  • Keep sections collapsed by default for clean navigation
  • Use relative paths for all document links
  • Follow the existing naming conventions for document titles

Expected Output

After completion, provide a summary of:

  • Number of new documents added
  • Number of clients/projects updated
  • Commit IDs created
  • Confirmation that changes were pushed successfully

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