agentleFS
Sign inStart free
npownpow/claude-skills/find-skill/SKILL.md

find-skill

Skill4 starsChanged 6 months agoApache-2.0View on GitHub

Search across all installed skills (user + plugin) by keyword to discover relevant skills whose descriptions may have been truncated from the main listing. Use when the user references a skill by partial/fuzzy name, asks "is there a skill for X?", or when the main skill listing seems incomplete. Trigger phrases include "find a skill", "is there a skill for", "search skills", "what skill does X", "find skill", "skill search", "look for a skill", "any skill that handles".

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the ID has spaces or special characters that don't match a Skill tool entry, the listing in your conversation's system reminder is …

    line 60

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “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

find-skill

Searches ~/.cache/claude-skill-index.json (built by the inject-skill-hints hook) across all SKILL.md files in ~/.claude/skills/ and ~/.claude/plugins/. Returns matches with full descriptions, scores, and paths.

When to use

  • User asks "is there a skill for X?" or names a skill fuzzily ("the kafka skill")
  • Main skill listing has truncated descriptions and you suspect a relevant skill exists but you can't see its trigger phrases
  • You want to discover skills before committing to a manual approach

How to use

Run the CLI:

python3 ~/.claude/skills/find-skill/find_skill.py <query terms>

Flags:

  • --limit N — max results (default 10)
  • --full — show full descriptions (default truncates to 200 chars)
  • --rebuild — force index rebuild (otherwise cached for 24h)

Output: ranked list with score, namespaced ID (e.g. ods-datastores:wal-observability), description, and path.

Examples

# Find anything related to GPU queues
python3 ~/.claude/skills/find-skill/find_skill.py gpu queue capacity

# Search for kafka-related skills with full descriptions
python3 ~/.claude/skills/find-skill/find_skill.py --full kafka

# Force a fresh index rebuild after installing new skills
python3 ~/.claude/skills/find-skill/find_skill.py --rebuild metaflow

Scoring

  • +1 per query keyword that appears in the skill's description tokens
  • +3 per query keyword that appears in the skill name
  • +1 per query keyword that appears as a substring of the description

Skills with the same leaf name (after :) are deduped; cache/ entries (authoritative plugin IDs) are preferred over marketplaces/ entries.

Once you find a relevant skill

Invoke it via the Skill tool:

Skill(skill="<namespaced-id>")

If the ID has spaces or special characters that don't match a Skill tool entry, the listing in your conversation's system reminder is authoritative — cross-reference there.

Related

  • ~/.claude/hooks/inject-skill-hints.py — UserPromptSubmit hook that auto-surfaces top matches on every prompt; this skill is the manual companion for explicit search.

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