agentleFS
dannotedannote/dot-pi/skills/skill-discovery/SKILL.md

skill-discovery

Skill57 starsChanged 5 months agoMITView on GitHub

Find agent skills and skill repositories on GitHub.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use find-skills, code-review and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    find-skills

    Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search repos by topic to find skill collections

    line 12
  2. Distinctive:

    Search/filter based on user query

    line 16
  3. Very specific:

    Search GitHub code for actual SKILL.md files (finds repos not tagged with topics):

    line 32
  4. Distinctive:

    Search for different keywords

    line 99

“Common” is measured: kept by at least 6 in 10 of the 12 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

Skill Discovery

Find agent skills on GitHub using gh CLI. Skills work across multiple harnesses (Claude Code, Codex, Gemini CLI, Pi, etc.) as they follow the same SKILL.md format.

Workflow

  1. Search repos by topic to find skill collections
  2. For awesome lists: fetch README and extract skill links
  3. For skill repos: list directories containing SKILL.md
  4. Build searchable catalog at /tmp/skills-catalog.md
  5. Search/filter based on user query

Find skill repos

gh search repos --topic=claude-skills --sort=stars --limit=30 --json fullName,description
gh search repos --topic=codex-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=gemini-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=skill-md --sort=stars --limit=20 --json fullName,description
gh search repos --topic=agent-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=claude-code-skills --sort=stars --limit=20 --json fullName,description
gh search repos --topic=gemini-cli-skills --sort=stars --limit=20 --json fullName,description

Find repos with SKILL.md files

Search GitHub code for actual SKILL.md files (finds repos not tagged with topics):

# Find repos containing SKILL.md files, then fetch stars via GraphQL (single query)
repos=$(gh search code "filename:SKILL.md" --limit=50 --json repository | jq -r '.[].repository.nameWithOwner' | sort -u)

# Build GraphQL query to get stars for all repos at once
query="{ "
i=0
for repo in $repos; do
  owner="${repo%/*}"
  name="${repo#*/}"
  query+="r$i: repository(owner: \"$owner\", name: \"$name\") { nameWithOwner stargazerCount description } "
  ((i++))
done
query+="}"

gh api graphql -f query="$query" --jq '.data | to_entries[] | "\(.value.nameWithOwner) ★\(.value.stargazerCount) - \(.value.description // "no desc")"' | sort -t'★' -k2 -rn

Build catalog from awesome lists

For repos with "awesome" in name, fetch README:

gh api "repos/<owner>/<repo>/contents/README.md" --jq '.content' | base64 -d >> /tmp/skills-catalog.md

List skills in a collection repo

For repos with skills directories:

# Find skills directory (skills/, scientific-skills/, etc.)
gh api repos/<owner>/<repo>/contents --jq '.[].name'

# List individual skills
gh api repos/<owner>/<repo>/contents/<skills-dir> --jq '.[].name'

Search catalog

grep -i "<keyword>" /tmp/skills-catalog.md -B2 -A1

View skill contents

gh api repos/<owner>/<repo>/contents/<path>/SKILL.md --jq '.content' | base64 -d

Install skill

gh repo clone <owner>/<repo> /tmp/<repo>
cp -r /tmp/<repo>/skills/<skill-name> ~/.pi/agent/skills/

Output

Show matching skills as table: | Repository | Description |

After results, offer:

  1. View a specific skill's SKILL.md
  2. Install a skill to ~/.pi/agent/skills/
  3. Search for different keywords

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.