skills-search

Search skills.sh registry from CLI. Find and discover agent skills from the skills.sh ecosystem.

33 stars

Best use case

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

Search skills.sh registry from CLI. Find and discover agent skills from the skills.sh ecosystem.

Teams using skills-search 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/skills-search/SKILL.md --create-dirs "https://raw.githubusercontent.com/aAAaqwq/AGI-Super-Team/main/skills/skills-search/SKILL.md"

Manual Installation

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

How skills-search Compares

Feature / Agentskills-searchStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Search skills.sh registry from CLI. Find and discover agent skills from the skills.sh ecosystem.

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

# Skills.sh Search CLI

Search skills from skills.sh registry directly from your terminal.

## Install (Clawdbot)

```bash
clawdhub install skills-search
```

## Usage

```bash
# Search for skills by name
skills-search "postgres"
skills-search "web design"
skills-search "twitter"

# Show most popular skills
skills-search --popular
skills-search --popular --limit 10

# Search with install command
skills-search "web design" --show-install
```

## Examples

```
❯ skills-search "web design"
🔍 Searching skills.sh for "web design"...

✅ web-design-guidelines (16,922 installs)
   Source: vercel-labs/agent-skills
   Install: npx skills add vercel-labs/agent-skills

✅ frontend-design (566 installs)
   Source: anthropics/skills
   Install: npx skills add anthropics/skills
```

### Popular Skills

```
❯ skills-search --popular --limit 5
📈 Top 5 most popular skills:

✅ vercel-react-best-practices (22,475 installs)
   Source: vercel-labs/agent-skills

✅ web-design-guidelines (17,135 installs)
   Source: vercel-labs/agent-skills

✅ upgrading-expo (1,192 installs)
   Source: expo/skills
...
```

## Automation (Clawdbot)

### Step 1: Search for a skill

```bash
npx @thesethrose/skills-search "react"
```

### Step 2: Install found skill via skills CLI

After finding a skill, install it using the `skills` CLI:

```bash
npx skills add vercel-labs/agent-skills
```

**TUI Navigation Guidance:**

The `skills` CLI uses an interactive menu. Watch for prompts and navigate accordingly:

1. **Select skills** → Toggle skills you want with `space`, confirm with `enter`
2. **Select agents** → Navigate with `up`/`down`, select `Clawdbot` with `space`, confirm with `enter`
3. **Installation scope** → Choose Project (recommended) with `enter`
4. **Confirm** → Press `enter` to proceed

**Important:** The TUI may change. Pay attention to the menu options and select `Clawdbot` when prompted for agents. If unsure about any selection, ask the user for guidance.

### Step 3: Verify installation

```bash
ls ~/.clawdbot/workspace/.agents/skills/
```

## Adding Your Own Skill

Skills.sh automatically indexes GitHub repos containing `SKILL.md` files. To add your skill:

1. **Create a skill folder** with `SKILL.md` in your GitHub repo
2. **Publish to ClawdHub** for Clawdbot-specific discovery:
   ```bash
   clawdhub publish ./your-skill/ --slug your-skill --name "Your Skill" --version 1.0.0
   ```
3. **Install in Clawdbot:**
   ```bash
   clawdhub install your-skill
   ```

## Notes

- Queries https://skills.sh/api/skills (official skills.sh API)
- Results sorted by install count (most popular first)
- **Clawdbot-only**: Install via `clawdhub install skills-search`
- Skills.sh leaderboard requires GitHub repo (not needed for ClawdHub-only skills)

Related Skills

writing-skills

33
from aAAaqwq/AGI-Super-Team

Use when creating new skills, editing existing skills, or verifying skills work before deployment

web-search

33
from aAAaqwq/AGI-Super-Team

网络搜索与网页内容获取。当用户需要搜索互联网信息、获取网页内容、查找实时数据、进行 websearch 时使用此技能。支持多种搜索工具:WebFetch、Firecrawl skill、Tavily skill。

trailofbits-skills

33
from aAAaqwq/AGI-Super-Team

> Trail of Bits 安全审计——基于 Trail of Bits 开源工具链的安全审计插件

tech-selection-research

33
from aAAaqwq/AGI-Super-Team

Use when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型", "compare Spring Boot vs NestJS", "写 ADR", "评估是否适合", "PoC 方案", or "technology radar".

suno-skills

33
from aAAaqwq/AGI-Super-Team

AI音乐生成工具Suno的浏览器自动化Skill。通过Playwright控制Suno网站(https://suno.com)进行:生成歌曲(含自定义歌词)、管理创作、下载音频。触发场景:"用suno生成歌曲"、"Suno创作"、"AI音乐生成"、"生成一首...风格的歌"、"上传歌词到Suno"

Getting Started with Skills

33
from aAAaqwq/AGI-Super-Team

Skills wiki intro - mandatory workflows, search tool, brainstorming triggers

skill-search-optimizer

33
from aAAaqwq/AGI-Super-Team

Optimize agent skills for discoverability on ClawdHub/MoltHub. Use when improving search ranking, writing descriptions for semantic search, understanding how the registry indexes skills, testing search visibility, or analyzing why a skill isn't being found.

search-specialist

33
from aAAaqwq/AGI-Super-Team

Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.

search-layer

33
from aAAaqwq/AGI-Super-Team

四源同级:Brave (`web_search`) + Exa + Tavily + Grok。按意图自动选策略、调权重、做合成。 DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.

search-first

33
from aAAaqwq/AGI-Super-Team

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.

research-engineer

33
from aAAaqwq/AGI-Super-Team

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal impl...

product-manager-skills

33
from aAAaqwq/AGI-Super-Team

> 产品经理技能集——PRD、用户故事、竞品分析、路线图等产品方法论工具