agentleFS
wangsy0247wangsy0247/multiagent-studio/skills/builtin/find-skill/SKILL.md

find-skill

Skill2 starsChanged 4 months agoMITView on GitHub

Discover and load the right skill for the task at hand. Use this skill when you're unsure which skills are available, need to find a skill by capability or keyword, or want to check if a specialized workflow exists before building one from scratch.

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 0

    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. Very specific:

    Use file_read or Glob to list available skills:

    line 25

“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

Purpose

Discover available skills that match the current task. This skill prevents reinventing the wheel — before manually executing a complex workflow, check if a skill already provides optimized instructions for it.

When to Use

  • User asks for something that sounds like a repeatable workflow (code review, research, deployment, architecture review, etc.)
  • You're about to spend significant effort on a multi-step task
  • User mentions a skill name but you're not sure it exists
  • You want to see all skills across a certain domain

Workflow

Step 1: Scan available skills

Use file_read or Glob to list available skills:

Glob: /mnt/skills/builtin/*/SKILL.md
Glob: /mnt/skills/my/*/SKILL.md

Each directory name is the skill name; each SKILL.md contains the skill's description and workflow.

Step 2: Match by description

For skills whose name doesn't obviously match the task, read their SKILL.md frontmatter to get the description. The YAML frontmatter is between --- fences at the top:

---
name: skill-name
description: What this skill does
license: MIT
---

Key matching signals:

  1. Skill name — exact or fuzzy keyword match against the user's request
  2. Description — semantic fit with the task requirements
  3. Domain overlap — the skill's category matches the task's domain

Step 3: Load the best match

Once a skill is identified, call file_read on its SKILL.md location to load the full workflow instructions. Follow the skill's progressive loading pattern — read referenced resources (references/, templates/, scripts/) only when needed.

Step 4: Report or execute

  • Single clear match: Load the skill and follow its workflow without further confirmation
  • Multiple candidates: Present a brief summary to the user: "I found skills for A, B, and C — which should I use?"
  • No match: Tell the user "No built-in skill matches this task. I'll proceed manually. To create a skill for this, use skill_manage."

Skill Categories

Built-in skills are located at /mnt/skills/builtin/. User-created skills are at /mnt/skills/my/. Built-in skills are read-only; user skills can be edited.

Quick Reference

User says...Look for...
"review this code"code-reviewer
"research X" / "write a report"deep-research
"review the architecture"system-architecture-review
"check before deploying"deployment-checklist
"what skills are available"List all */SKILL.md files

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.