agentleFS
Sign inStart free
paulo-yamagishipaulo-yamagishi/claude-code-setup/.claude/skills/add-core-guide/SKILL.md

add-core-guide

Skill2 starsChanged 9 months agoMITView on GitHub

Create a new core/ reference guide following repo conventions

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Create a new core/{topic}-guide.md file for the topic specified in $ARGUMENTS.

    line 15
  2. Very specific:

    Fetch official docs: Use WebFetch to read https://docs.anthropic.com/en/docs/claude-code pages relevant to the topic for authoritative …

    line 21
  3. Very specific:

    Study existing guides: Read 2-3 files in core/ to extract the consistent structure:

    line 23
  4. Distinctive:

    Follow the extracted structure exactly

    line 30
  5. Distinctive:

    Use only verified information from official docs

    line 31
  6. Distinctive:

    All JSON must be valid — no comments, no trailing commas

    line 33
  7. Distinctive:

    All settings keys and hook events must match official documentation

    line 34
  8. Distinctive:

    Keep language-agnostic — no framework-specific advice

    line 35
  9. Distinctive:

    No duplicate of existing content in other guides

    line 44

≈ “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

Add Core Guide

Create a new core/{topic}-guide.md file for the topic specified in $ARGUMENTS.

Steps

  1. Validate topic: Confirm core/$ARGUMENTS-guide.md does not already exist. If it does, report and stop.
  2. Fetch official docs: Use WebFetch to read https://docs.anthropic.com/en/docs/claude-code pages relevant to the topic for authoritative content.
  3. Study existing guides: Read 2-3 files in core/ to extract the consistent structure:
    • Title format: # Topic Guide
    • Section pattern: overview → key concepts → configuration → examples → troubleshooting → cross-references
    • Style: imperative, concrete examples, valid JSON in code blocks, language-agnostic
    • Length: under 300 lines
  4. Generate the guide:
    • Follow the extracted structure exactly
    • Use only verified information from official docs
    • Include at least 2 concrete JSON or bash code block examples
    • All JSON must be valid — no comments, no trailing commas
    • All settings keys and hook events must match official documentation
    • Keep language-agnostic — no framework-specific advice
  5. Add cross-references:
    • Link to related core guides using relative paths: ../core/{related}-guide.md
    • Grep other guides for mentions of the new topic and note where a backlink would help
  6. Verify: Re-read the generated file and confirm:
    • Valid JSON in all code blocks
    • Under 300 lines
    • No duplicate of existing content in other guides

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