find-skill

Search for Agent Skills in local folders and on GitHub. Use when you need a capability you don't have—search before building.

16 stars

Best use case

find-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Search for Agent Skills in local folders and on GitHub. Use when you need a capability you don't have—search before building.

Teams using find-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/find-skill/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/tools/find-skill/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/find-skill/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How find-skill Compares

Feature / Agentfind-skillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Search for Agent Skills in local folders and on GitHub. Use when you need a capability you don't have—search before building.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Find Skill

Search for Agent Skills across local folders and GitHub.

## When to Use

You need a capability. Before building it, search. Someone may have already made it.

## Usage

```bash
# Search for a skill
python scripts/find.py "detect silence in audio"

# Local only (offline)
python scripts/find.py "resize images" --local-only

# JSON output for programmatic use
python scripts/find.py "send email" --json

# Fetch and display full SKILL.md content
python scripts/find.py "python" --fetch --limit 2
```

## Output

```
Found 2 skill(s) for "silence detection":

1. silence-detect
   Location: https://github.com/user/audio-tools
   Description: Detects silence gaps in audio files using ffmpeg...

2. audio-silence
   Location: ~/skills/audio-silence
   Description: Find silent regions in recordings...
```

## Configuration

Edit `scripts/config.json`:

```json
{
  "local_paths": ["~/skills/", "./skills/"],
  "github": {
    "enabled": true,
    "topic": "agentskills",
    "repos": [
      "your-username/your-skills-monorepo"
    ]
  }
}
```

### Config Options

| Field | Description |
|-------|-------------|
| `local_paths` | Local folders to search for skills |
| `github.enabled` | Enable/disable GitHub search |
| `github.topic` | Topic to search for (default: `agentskills`) |
| `github.repos` | Your personal skill repos (always searched first) |

### GitHub Token (Recommended)

A GitHub token provides higher rate limits (5000/hour vs 60/hour) and is required for searching private repos.

Create a `.env` file in the project root:

```
GITHUB_TOKEN=ghp_xxxxxxxxxxxx
```

Or set environment variables: `GITHUB_TOKEN` or `GH_TOKEN`

To create a token:
1. Go to GitHub → Settings → Developer settings → Personal access tokens
2. Generate new token with `repo` scope (for private repos) or `public_repo` (for public only)

## What It Searches

1. **Local folders** — Scans configured paths for directories containing SKILL.md
2. **Your repos** — Searches repos listed in `github.repos` config (fast, reliable)
3. **Topic search** — Searches public repos with topic `agentskills`
4. **Code search** — Finds SKILL.md files containing your search terms

## After Finding

1. Read the description—is this what you need?
2. Clone or fetch the skill
3. Read the full SKILL.md before executing
4. Run in your environment

## Options

| Flag | Effect |
|------|--------|
| `--local-only` | Skip GitHub, search only local folders |
| `--json` | Output as JSON for parsing |
| `--fetch` | Fetch and display full SKILL.md content |
| `--limit N` | Maximum results (default: 10) |

## Notes

- This skill searches only; it does not execute found skills
- GitHub search requires network access
- With token: 5000 requests/hour. Without: 60 requests/hour
- Local search works offline

Related Skills

affinda-automation

16
from diegosouzapw/awesome-omni-skill

Automate Affinda tasks via Rube MCP (Composio). Always search tools first for current schemas.

find-bugs

16
from diegosouzapw/awesome-omni-skill

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

apply-all-findings

16
from diegosouzapw/awesome-omni-skill

Use after code review - implement ALL findings; any finding not fixed MUST have tracking issue created; no finding disappears without trace

unified-find-skills

16
from diegosouzapw/awesome-omni-skill

Helps users discover and install agent skills from skills.sh, clawhub.com, and tessl.io. Use when the user asks to find a skill for a task, extend agent capabilities, or search for tools/workflows.

find-skills

16
from diegosouzapw/awesome-omni-skill

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.

ast-grep-find

16
from diegosouzapw/awesome-omni-skill

AST-based code search and refactoring via ast-grep MCP

skill-finder

16
from diegosouzapw/awesome-omni-skill

Find and install the best skill for your current task. Use when the user wants to discover skills, asks "is there a skill for...", "find a skill for...", or "/skill-finder". Searches skills.sh in real-time and uses LLM reasoning to match skills to the user's context.

ops-automation-opportunity-finder

16
from diegosouzapw/awesome-omni-skill

Identify and evaluate automation opportunities in banking operations using structured assessment frameworks. Use when analyzing processes for RPA, intelligent automation, AI/ML, or straight-through processing potential across payments, lending, account servicing, compliance, and back-office functions.

llm-icon-finder

16
from diegosouzapw/awesome-omni-skill

Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.

findymail-automation

16
from diegosouzapw/awesome-omni-skill

Automate Findymail tasks via Rube MCP (Composio). Always search tools first for current schemas.

clawdhub-find-skills

16
from diegosouzapw/awesome-omni-skill

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. Uses reskill as the package manager.

utils:find-claude-plugin-root

16
from diegosouzapw/awesome-omni-skill

This skill should be used when the user needs to locate a plugin's installation path, when ${CLAUDE_PLUGIN_ROOT} doesn't expand in markdown files, or when invoked via /utils:find-claude-plugin-root. Generates a CPR resolver script at /tmp/cpr.py.