agentleFS
Sign inStart free
crgarcia12crgarcia12/Liliput/.github/skills/skill-discovery/SKILL.md

skill-discovery

Skill4 starsChanged 4 months agoISCView on GitHub

Search the skills.sh open ecosystem for community skills relevant to the current task. Install discovered skills into the project. Use before starting any new task, when resolving technology decisions, or when the user asks to find a skill for a specific capability.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-review.

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.
  • 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

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Search skills.sh for community skills before building from scratch.

    line 12
  2. Very specific:

    Before starting any task in the Ralph loop (after checking local .github/skills/)

    line 16
  3. Distinctive:

    When the user asks "is there a skill for X?" or "find a skill for X"

    line 18
  4. Distinctive:

    When you encounter a domain where a community best-practice skill likely exists

    line 19
  5. Distinctive:

    When you find relevant skills:

    line 49
  6. Distinctive:

    Ask the user if they want to install it

    line 54
  7. Very specific:

    If a reusable pattern emerges, suggest creating a project skill via the skill-creator skill

    line 78

“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

Skill Discovery

Search skills.sh for community skills before building from scratch.

When to Search

  • Before starting any task in the Ralph loop (after checking local .github/skills/)
  • During Phase 1d (Tech Stack Resolution) — search for technology-specific skills
  • When the user asks "is there a skill for X?" or "find a skill for X"
  • When you encounter a domain where a community best-practice skill likely exists

How to Search

npx skills find [query]

Examples:

  • npx skills find react performance — React optimization patterns
  • npx skills find playwright testing — E2E testing best practices
  • npx skills find azure deployment — Azure deployment patterns
  • npx skills find nextjs — Next.js development patterns

How to Install

Install a skill for the project (stored in .github/skills/):

npx skills add <owner/repo@skill-name> -y

Install a skill globally (shared across projects):

npx skills add <owner/repo@skill-name> -g -y

Presenting Results

When you find relevant skills:

  1. Present the skill name and what it does
  2. Show the install command
  3. Link to the skills.sh page: https://skills.sh/<owner>/<repo>/<skill-name>
  4. Ask the user if they want to install it

Example:

Found: "vercel-react-best-practices" — React and Next.js optimization guidelines from Vercel Engineering.

Install: npx skills add vercel-labs/agent-skills@vercel-react-best-practices -y
Details: https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices

Would you like to install this skill?

Common Skill Sources

SourceSkills
vercel-labs/agent-skillsReact best practices, web design guidelines
anthropics/skillsFrontend design, code review
microsoft/github-copilot-for-azureAzure services (AI, storage, deployment, etc.)

When No Skills Are Found

  1. Acknowledge that no existing skill was found
  2. Offer to help with the task directly
  3. If a reusable pattern emerges, suggest creating a project skill via the skill-creator skill

Check for Updates

Periodically check for skill updates:

npx skills check
npx skills update

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