search-skill

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Search Skill

技能搜索

Search and recommend Claude Code Skills from trusted marketplaces based on user requirements.

根据用户需求，从可信市场中搜索并推荐Claude Code技能。

When to Use

适用场景

When users describe a need and want to find an existing Skill to solve it.

Examples:

"Is there a skill that can auto-generate changelogs?"
"Find me a skill for frontend design"
"I need a skill that can automate browser actions"

当用户描述需求并希望找到现有Skill来解决时。

示例：

"有没有可以自动生成更新日志的技能？"
"帮我找一个前端设计相关的技能"
"我需要一个能自动化浏览器操作的技能"

Data Sources (by trust level)

数据来源（按可信度分级）

Tier 1 - Official / High Trust (show first)

一级 - 官方/高可信度（优先展示）

Source	URL	Notes
anthropics/skills	github.com/anthropics/skills	Official examples, most reliable
ComposioHQ/awesome-claude-skills	github.com/ComposioHQ/awesome-claude-skills	Hand-picked, 12k+ stars

来源	链接	说明
anthropics/skills	github.com/anthropics/skills	官方示例，最可靠
ComposioHQ/awesome-claude-skills	github.com/ComposioHQ/awesome-claude-skills	人工精选，超1.2k星

Tier 2 - Community Curated (secondary)

二级 - 社区精选（次要）

Source	URL	Notes
travisvn/awesome-claude-skills	github.com/travisvn/awesome-claude-skills	Community curated, 21k+ stars
skills.sh	skills.sh	Vercel's official directory

来源	链接	说明
travisvn/awesome-claude-skills	github.com/travisvn/awesome-claude-skills	社区整理，超2.1k星
skills.sh	skills.sh	Vercel官方目录

Tier 3 - Aggregators (use with caution)

三级 - 聚合平台（谨慎使用）

Source	URL	Notes
skillsmp.com	skillsmp.com	Auto-scraped, requires extra filtering

来源	链接	说明
skillsmp.com	skillsmp.com	自动抓取，需额外过滤

Search Process

搜索流程

Step 1: Parse User Intent

步骤1：解析用户意图

Extract from user description:

Core functionality keywords (e.g., changelog, browser, frontend)
Use case (e.g., development, testing, design)
Special requirements (e.g., language support, specific framework)

从用户描述中提取：

核心功能关键词（如：更新日志、浏览器、前端）
使用场景（如：开发、测试、设计）
特殊要求（如：语言支持、特定框架）

Step 2: Multi-Source Search

步骤2：多源搜索

IMPORTANT: Only search these 5 sources. Do NOT search the entire internet.

Search by priority:

1. Search Tier 1 (official/high trust) first
2. If fewer than 5 results, continue to Tier 2
3. If still insufficient, search Tier 3 with strict filtering
4. If still nothing found, tell user honestly - do NOT expand to other sources

Allowed search queries (use

site:

to restrict):

site:github.com/anthropics/skills {keywords}
site:github.com/ComposioHQ/awesome-claude-skills {keywords}
site:github.com/travisvn/awesome-claude-skills {keywords}
site:skills.sh {keywords}
site:skillsmp.com {keywords}

Search methods:

GitHub repos: Use
```
site:github.com/{repo}
```
to restrict search scope
skills.sh: WebFetch to scrape search results from skills.sh only
skillsmp.com: WebFetch with additional verification

Do NOT:

Search the entire web
Use broad queries without
```
site:
```
restriction
Include results from unknown sources

重要提示：仅搜索以下5个来源，不得搜索整个互联网。

按优先级搜索：

1. 优先搜索一级来源（官方/高可信度）
2. 若结果少于5个，继续搜索二级来源
3. 若仍不足，严格过滤后搜索三级来源
4. 若仍未找到，如实告知用户 - 不得扩展至其他来源

允许的搜索查询（使用

site:

限制范围）：

site:github.com/anthropics/skills {keywords}
site:github.com/ComposioHQ/awesome-claude-skills {keywords}
site:github.com/travisvn/awesome-claude-skills {keywords}
site:skills.sh {keywords}
site:skillsmp.com {keywords}

搜索方式：

GitHub仓库：使用
```
site:github.com/{repo}
```
限制搜索范围
skills.sh：仅抓取skills.sh的搜索结果
skillsmp.com：抓取后需额外验证

禁止：

搜索整个互联网
使用无
```
site:
```
限制的宽泛查询
包含未知来源的结果

Step 3: Quality Filtering (Critical)

步骤3：质量筛选（关键）

Must filter out the following:

Filter Condition	Reason
GitHub stars < 10	Not community verified
Last update > 6 months ago	Possibly abandoned
No SKILL.md file	Non-standard format
README too sparse	Quality concerns
Contains suspicious code patterns	Security risk

Security checks:

Requests sensitive permissions (e.g., ~/.ssh, env variables)
External network requests to unknown domains
Contains eval() or dynamic code execution
Modifies system files

必须过滤以下内容：

过滤条件	原因
GitHub星数 < 10	未经过社区验证
最后更新 > 6个月前	可能已被弃用
无SKILL.md文件	非标准格式
README内容过于简略	质量存疑
包含可疑代码模式	存在安全风险

安全检查：

请求敏感权限（如：~/.ssh、环境变量）
向未知域名发起外部网络请求
包含eval()或动态代码执行
修改系统文件

Step 4: Rank Results

步骤4：结果排序

Scoring formula:

Score = Source Weight × 0.4 + Stars Weight × 0.3 + Recency Weight × 0.2 + Relevance × 0.1

Source weights:
- Tier 1: 1.0
- Tier 2: 0.7
- Tier 3: 0.4

评分公式：

评分 = 来源权重 × 0.4 + 星数权重 × 0.3 + 更新时间权重 × 0.2 + 相关性 × 0.1

来源权重：
- 一级：1.0
- 二级：0.7
- 三级：0.4

Step 5: Format Output

步骤5：格式化输出

Return Top 5-10 results:

markdown

undefined

返回Top 5-10结果：

markdown

undefined

Found X relevant Skills

找到X个相关技能

Worth considering

值得考虑

skill-name - Source: ComposioHQ ...

技能名称 - 来源：ComposioHQ ...

Not recommended (for reference only)

不推荐（仅作参考）

skill-name - Reason: low stars / not maintained

undefined

技能名称 - 原因：星数过低/未维护

undefined

Example

示例

User: Is there a skill that helps write commit messages?

Search process:

Extract keywords: commit, message, git
Search Tier 1: Found git-commit-assistant in anthropics/skills
Search Tier 2: Found semantic-commit in ComposioHQ
Filter: Exclude results with stars < 10
Rank: Official sources first

Output:

undefined

用户：有没有能帮助编写提交信息的技能？

搜索流程：

提取关键词：commit, message, git
搜索一级来源：在anthropics/skills中找到git-commit-assistant
搜索二级来源：在ComposioHQ中找到semantic-commit
筛选：排除星数<10的结果
排序：官方来源优先

输出：

undefined

Found 3 relevant Skills

找到3个相关技能

Important Notes

重要提示

Never recommend unverified Skills - Better to recommend fewer than to recommend risky ones
Stay cautious with Tier 3 sources - Results from skillsmp.com must be double-checked
If nothing suitable is found - Tell the user honestly, suggest using skill-from-masters to create their own
Security concerns - Clearly inform users of risks, let them decide

绝不推荐未验证的技能 - 宁少勿滥，避免推荐有风险的技能
谨慎使用三级来源 - skillsmp.com的结果必须二次核查
如果未找到合适技能 - 如实告知用户，建议使用skill-from-masters创建自定义技能
安全顾虑 - 明确告知用户风险，由用户自行决定