agentleFS
ElasticKnown publisherelastic/elastic-docs-skills/CLAUDE.md

elastic-docs-skills

CLAUDE.md72 starsChanged 5 months agoApache-2.0View on GitHub

A catalog of Claude Code skills for Elastic documentation workflows. Skills are installed into ~/.claude/skills/ via install.sh and used as slash commands or auto-triggered behaviors in Claude Code. Every skills/**/SKILL.md must have YAML frontmatter: Agentic workflows use .md files compiled to .lock.yml via gh aw compile. The lock files are auto-generated — never edit them directly. The .gitattributes file marks them as linguist-generated=true merge=ours. Use /create-skill within this repo, or see CONTRIBUTING.md for manual instructions. The Elastic documentation site exposes…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Every skills//SKILL.md must have YAML frontmatter:

    line 20
  2. Very specific:

    Use context: fork for catalog skills so they run in an isolated subagent context

    line 47
  3. Very specific:

    All skills that accept $ARGUMENTS should have argument-hint

    line 49
  4. Very specific:

    Use /create-skill within this repo, or see CONTRIBUTING.md for manual instructions.

    line 58

≈ “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

Elastic Docs Skills — Project Guide

What this repo is

A catalog of Claude Code skills for Elastic documentation workflows. Skills are installed into ~/.claude/skills/ via install.sh and used as slash commands or auto-triggered behaviors in Claude Code.

Repository layout

skills/<category>/<skill-name>/
  SKILL.md          # The skill definition (frontmatter + instructions)
  evals/evals.json  # Test cases for the skill (optional but encouraged)
.claude/skills/     # Skills that work within this repo only (e.g., /create-skill)
.github/workflows/  # CI and gh-aw agentic workflows
.github/agents/     # Copilot agent definitions

Skill anatomy

Every skills/**/SKILL.md must have YAML frontmatter:

---
name: docs-my-skill              # Required — kebab-case skill invocation name
version: 1.0.0              # Required — SemVer
description: What it does    # Required — when to trigger this skill
argument-hint: <args>        # Shown in autocomplete if skill accepts input
disable-model-invocation: true  # Only via /my-skill, not auto-triggered
context: fork                # Run in isolated subagent
allowed-tools: Read, Grep    # Tools available without user approval
sources:                     # Upstream URLs this skill encodes (for freshness checks)
  - https://www.elastic.co/docs/some-page
---

Categories

  • authoring — Skills that help write or edit documentation content
  • changelogs — Skills for changelog YAML, release notes, and changelog tooling
  • review — Skills that validate, lint, or check existing content
  • project — Skills scoped to specific documentation areas (e.g., Kibana Lens charts)

Conventions

  • Skill names are kebab-case and must be unique across the catalog
  • Version follows SemVer: bump PATCH for fixes, MINOR for new features, MAJOR for breaking changes
  • Use context: fork for catalog skills so they run in an isolated subagent context
  • Skills that modify files should include Edit or Write in allowed-tools
  • All skills that accept $ARGUMENTS should have argument-hint
  • Skills derived from upstream docs should list URLs in sources: frontmatter

gh-aw workflows

Agentic workflows use .md files compiled to .lock.yml via gh aw compile. The lock files are auto-generated — never edit them directly. The .gitattributes file marks them as linguist-generated=true merge=ours.

Adding a skill

Use /create-skill within this repo, or see CONTRIBUTING.md for manual instructions.

Elastic Docs MCP server

The Elastic documentation site exposes a public MCP server at https://www.elastic.co/docs/_mcp/ (no auth required). Use it for searching docs, fetching pages, and checking content freshness.

Available tools:

ToolPurpose
search_docsSearch all published Elastic docs by meaning. Supports product/section filters.
find_related_docsDiscover pages related to a topic.
get_document_by_urlFetch a specific page by URL or path. Returns title, summaries, headings, and optionally the full body.
analyze_document_structureAnalyze heading count, link count, parent pages for a given URL.
check_docs_coherenceCheck how coherently a topic is covered across all docs.
find_docs_inconsistenciesFind potential inconsistencies across pages covering the same topic.

Test with: npx @modelcontextprotocol/inspector --url https://www.elastic.co/docs/_mcp/

Running CI locally

# Validate all skills
find skills -name "SKILL.md" -type f -exec echo "Checking {}" \;

# Validate eval JSON
find skills -name "evals.json" -exec python3 -m json.tool {} \;

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.