agentleFS
chrislacey89chrislacey89/content-to-skill/CLAUDE.md

content-to-skill

CLAUDE.md1 starsChanged 9 months agoMITView on GitHub

Claude Code plugin that transforms PDFs and EPUBs into Agent Skills. When bumping the version, update ALL of these files to keep them in sync: The site version is auto-derived from plugin.json at build time (no manual update needed). The site version is auto-derived from plugin.json at build time (no manual update needed). This project uses Biome for formatting and linting. Run npm run check before committing.

  • Installs packages
  • In this repository2 other files it gives its agents.

The file

We split this CLAUDE.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use ${CLAUDE_PLUGIN_ROOT} for all plugin-relative paths (never ${PLUGIN_ROOT})

    line 9
  2. Very specific:

    All side-effect commands must have disable-model-invocation: true

    line 11
  3. Distinctive:

    When bumping the version, update ALL of these files to keep them in sync:

    line 29
  4. Very specific:

    Run npm run check before committing.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

Content-to-Skill Plugin

Overview

Claude Code plugin that transforms PDFs and EPUBs into Agent Skills.

Conventions

  • Use ${CLAUDE_PLUGIN_ROOT} for all plugin-relative paths (never ${PLUGIN_ROOT})
  • allowed-tools uses comma-separated colon syntax: Bash(npx:*)
  • All side-effect commands must have disable-model-invocation: true
  • Reference files are declarative methodology docs, not conversational prompts
  • Generated skills follow the Agent Skills spec (agentskills.io)

Directory Structure

.claude-plugin/plugin.json    # Plugin manifest
commands/content-to-skill.md  # Main slash command
commands/library.md           # Library browse/load command
references/                   # Prompt methodology files
scripts/chunk_document.ts     # Document chunker
scripts/library_index.ts      # Library index builder
scripts/library_migrate.ts    # Skills-to-library migrator

Versioning

When bumping the version, update ALL of these files to keep them in sync:

  • .claude-plugin/plugin.json
  • .claude-plugin/marketplace.json
  • package.json (then run npm install --package-lock-only to sync package-lock.json)

The site version is auto-derived from plugin.json at build time (no manual update needed).

The site version is auto-derived from plugin.json at build time (no manual update needed).

Formatting

This project uses Biome for formatting and linting.

npm run check    # Format + lint + fix
npm run format   # Format only
npm run lint     # Lint only (no fixes)

Run npm run check before committing.

Testing

# Test chunking
npx tsx scripts/chunk_document.ts <input.pdf> -p 5 -o /tmp/test-chunks

# Test library index
npx tsx scripts/library_index.ts

# Test migration
npx tsx scripts/library_migrate.ts

# Install plugin locally for testing
# /plugin install /Users/christopherlacey/Documents/content-to-skill

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.