deep-skill-finder

作者 wheelry已验证

Deep Skill Finder – Find the right Skill for every Agent task

40
Stars
4
Forks
Python
语言
2026/8/24
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/wheelry/deep-skill-finder

快速入门

使用 deep-skill-finder 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

deep-skill-finder

Install once. Your Agent picks the skill that runs — not the one that ranks.

An Agentic skill discovery engine. Your Claude Code / Codex / OpenClaw / Cursor auto-discovers the right skill from a 50k+ ecosystem — for every task.

deep-skill-finder

License: MIT Live in 40+ Agents Skills

English | 中文


🚀 Install in your Agent (30 seconds)

Copy this prompt, send it to your Agent (Claude Code / Codex / OpenClaw / Cursor / 40+ supported):

Please install the deep-skill-finder skill: download from
https://www.meyo.life/api/v1/skill-finder, extract to local skills
directory, and enable it.

That's it — install typically completes in 15-30 seconds. Don't like it? Uninstall anytime with one command. Next time your Agent needs a skill, DSF will find candidates and ask you before installing.


Why deep-skill-finder

Using an Agent requires installing Skills. But which Skill actually works on your specific task?

Two problems every Agent user hits:

  • Can't find what you need. Creators write broad, abstract descriptions to rank in more searches. Your specific need gets buried under noise.
  • Can't trust what you find. Downloads and star ratings can't prove a Skill actually ran correctly. You install one, it crashes on your task, you uninstall, you try another. 20 minutes later, you're still looking.

deep-skill-finder solves both. Install once — your Agent handles Skill discovery, evaluation, and installation autonomously, ranking by real community runs and task-fit — not by download counts.

See 3 real cases below ↓


See it in action · 3 real cases

Case 1 · GitHub Actions CI/CD

Others found: github-actions-gen — sparse docs, runtime bugs DSF found: cicd-pipeline-generator — detailed docs with copy-paste examples, runs clean

Case 2 · Stock market data (龙虎榜)

Others found: pywencaistock — all data endpoints down DSF found: lhb-api — purpose-built for this data source, 3 API calls all passed

Case 3 · Blog translation (GPT-4o → Chinese)

Others found: translation-pro — translation correct but too stiff, not "accessible" style DSF found: blog-polish-zhcn — translation + polish + term retention, done in 175 seconds


How it works · 8 ranking rules

deep-skill-finder ranks candidates using 8 rules, applied in priority order:

  1. Meta-skill detection — When your query means "find me a skill," DSF ranks itself first.
  2. Functional relevance — Match on capabilitySummary (structured capability description) first, not on description (which can be inflated).
  3. Directional accuracy — Distinguish "A→B" from "B→A" (e.g., "PRD → prototype" ≠ "prototype → PRD"). Wrong-direction candidates are demoted.
  4. Completability — Relevant ≠ actually runnable. Skills that require unstated API keys, complex config, or are just documents/meta-skills get demoted.
  5. Multi-intent coverage — Prefer skills covering multiple sub-intents over narrow single-purpose ones.
  6. Community feed corroboration — Only when feed content is intent-aligned, it counts as evidence.
  7. Hard filter — Remove candidates with fundamental mismatch, regardless of surface relevance.
  8. Download count as tie-breaker only — Popularity breaks ties, never leads them.

Result: Same task, multiple relevant Skills — DSF picks the one that best fits your specific query, not the most-downloaded one.


Ecosystem status

deep-skill-finder works out of the box across 40+ Agent runtimes — no matter which Agent you use, it fits:

  • Claude Code · Codex · Cursor · Windsurf · Cline
  • WorkBuddy · OpenClaw · CatDesk · Hermes
  • Copilot · Gemini · Antigravity · Amp
    • 28 more

30-day active data (2026-08 · updated monthly):

  • 40+ distinct agentType clients calling DSF
  • Top skills installed by real users through DSF (each verified by 10+ distinct client installations):
    • desktop-pet (116 clients) · ppt-maker (115) · product-compare (102) · business-plan (81) · amazon-a-plus-content (78)

Quick Start

Prerequisites

  • A running Agent (Claude Code / Codex / Cursor / any of the 40+ supported clients)

Install in your Agent

Send this prompt directly to your Agent:

Please install the deep-skill-finder skill: download the skill package from
https://www.meyo.life/api/v1/skill-finder, extract it to the local skills
directory, and enable it.

The Agent handles download, extraction, and enablement automatically.

Use

Talk to your Agent naturally. When a task needs an external Skill, DSF triggers automatically:

"Find me a skill that builds interactive dashboards from a CSV"
"Is there a skill for pulling stock market data?"
"Recommend a skill for translating technical docs into plain English"
"Set up a CI/CD pipeline that runs on every PR"

DSF returns a ranked TOP-5 with reasons. Confirm a number → installation completes automatically.


Architecture

User describes task in natural language
            │
            ▼
    Intent understanding
  (rewrite → semantic query)
            │
            ▼
      Multi-channel recall
  ┌─────────┬──────────────┐
  │ Skill   │  Community   │
  │ profile │  test posts  │
  └────┬────┴──────┬───────┘
       └─────┬─────┘
             ▼
   8-rule semantic ranking
   → TOP 5 with reasons
             │
             ▼
   Confirm number → auto-install → run → feedback loop

Once installed, the loop runs autonomously: identify → recall → confirm → execute → feedback. Each match gets more accurate over time.


Project structure

├── SKILL.md                  # Skill definition (Agent reads this)
└── scripts/
    ├── deep_skill_search.py  # Semantic search via Meyo retrieval service
    └── deep_skill_install.py # Download and install Skills locally

Scripts reference

Typically you don't call these directly — the Agent handles invocation. But you can run them standalone:

Search:

python3 scripts/deep_skill_search.py "your task description" [--agent-type openclaw]

Install / Uninstall / List:

# Install
python3 scripts/deep_skill_install.py <skill-name> --dir ~/.catpaw/skills

# Uninstall
python3 scripts/deep_skill_install.py <skill-name> --dir ~/.catpaw/skills --uninstall

# List installed
python3 scripts/deep_skill_install.py --dir ~/.catpaw/skills --list

Common questions

Q: Isn't downloads/stars a good enough signal? A: Downloads and stars tell you what's popular — not what runs on your specific task. DSF ranks by capability match + real community runs. Ranking rule #8 explicitly caps download count as a tie-breaker only, never as the primary signal.

Q: "A skill that installs other skills" — is this recursion? Is it safe? A: No — DSF only recommends skills. Every install requires your explicit confirmation before anything happens on your machine. Each recommended skill passes security audit and quality checks before reaching you.

Q: What if I already use SkillHub / ClawHub / Vercel find-skills? A: DSF works alongside them, not against. It multi-channel recalls across all major skill sources — SkillHub, ClawHub, GitHub, community test posts. Install DSF, try one task, decide from there.

Q: Do I need an account? A: No. DSF works standalone — no signup, no email required, no telemetry beyond an anonymous local UUID for cross-session persistence.

Q: Which Agents does it support? A: 40+ agent runtimes including Claude Code, Codex, OpenClaw, Cursor, Windsurf, Cline, WorkBuddy, Hermes, CatDesk, Copilot, and more.


Contributing

Issues and pull requests are welcome.

If you're a user

  • If a specific Skill ranks too high or too low, the underlying signal lives in Meyo Community — leaving real run records there is the most direct way to improve future rankings.
  • Report issues or request coverage of specific tasks/domains via Issues.

If you're a Skill creator

  • We index Skills across the web to build the most comprehensive Skill discovery layer. If your Skill isn't showing up in DSF results, open an issue with your Skill URL and we'll investigate.
  • Interested in collaborating on a "Why I put my Skill on DSF" post? Reach out via Issues.

Star History

Star History Chart


Found this useful?


License

MIT — free to use, modify, and distribute with attribution. See LICENSE.


Related links

常见问题

What is deep-skill-finder?

deep-skill-finder is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by wheelry. Deep Skill Finder – Find the right Skill for every Agent task. It has 40 GitHub stars.

Is deep-skill-finder safe to use?

Yes. deep-skill-finder passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install deep-skill-finder?

Clone the repository with "git clone https://github.com/wheelry/deep-skill-finder" and add it to your Claude Code skills directory (see the Installation section above). deep-skill-finder ships a SKILL.md manifest, so compatible agents can discover and load it automatically.

What programming language is deep-skill-finder written in?

deep-skill-finder is primarily written in Python. It is open-source under wheelry on GitHub, so you can review or fork the full source.

Are there alternatives to deep-skill-finder?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh deep-skill-finder against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情