Back to Details

skill-finder

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill Finder

Skill Finder

Discover and install agent skills from the skills.sh open ecosystem into Skill Compose.
从skills.sh开放生态系统中发现Agent技能并将其安装到Skill Compose中。

When to Use This Skill

何时使用本技能

Activate when users:
  • Ask "how do I do X?" where an existing skill might help
  • Request "find a skill for X" or "is there a skill for X?"
  • Ask "can you do X?" for specialized tasks (poster design, data analysis, etc.)
  • Want to search for tools, templates, or workflows
  • Mention needing help with a specific domain that might have a community skill
在以下场景激活本功能：
  • 用户询问“我该如何做X？”，而现有技能可能提供帮助时
  • 用户请求“寻找适用于X的技能”或“有没有适用于X的技能？”时
  • 用户询问“你能做X吗？”以完成特定任务（如海报设计、数据分析等）时
  • 用户想要搜索工具、模板或工作流时
  • 用户提到需要特定领域的帮助，而该领域可能存在社区技能时

Available Scripts

可用脚本

1. Search Skills — 
find_skills.py

1. 搜索技能 — 
find_skills.py

Search the skills.sh ecosystem for skills matching a query.
bash
python scripts/find_skills.py <query> [--limit N]
Example:
bash
python scripts/find_skills.py "react performance"
python scripts/find_skills.py "docker" --limit 5
Output: JSON array of matching skills with 
name
, 
source
(owner/repo), 
installs
count, and 
url
(skills.sh link).
在skills.sh生态系统中搜索与查询词匹配的技能。
bash
python scripts/find_skills.py <query> [--limit N]
示例：
bash
python scripts/find_skills.py "react performance"
python scripts/find_skills.py "docker" --limit 5
输出： 匹配到的技能的JSON数组，包含
name
、
source
（所有者/仓库）、
installs
计数和
url
（skills.sh链接）。

2. Install Skill — 
add_skill.py

2. 安装技能 — 
add_skill.py

Download a skill from GitHub and register it in Skill Compose.
bash
python scripts/add_skill.py <owner/repo@skill-name>
Example:
bash
python scripts/add_skill.py "vercel-labs/agent-skills@vercel-react-best-practices"
What it does:
  1. Parses the 
    owner/repo@skill-name
    identifier
  2. Tries multiple GitHub paths to locate the skill (
    skills/<name>/
    , 
    <name>/
    , root)
  3. Downloads all skill files (SKILL.md, scripts/, references/, assets/)
  4. Saves to the local 
    skills/
    directory
  5. Registers the skill in Skill Compose via the import-local API
  6. The skill is immediately available for use in Agent Presets
从GitHub下载技能并在Skill Compose中注册。
bash
python scripts/add_skill.py <owner/repo@skill-name>
示例：
bash
python scripts/add_skill.py "vercel-labs/agent-skills@vercel-react-best-practices"
功能说明：
  1. 解析
    owner/repo@skill-name
    标识符
  2. 尝试多个GitHub路径以定位技能（
    skills/<name>/
    、
    <name>/
    、根目录）
  3. 下载所有技能文件（SKILL.md、scripts/、references/、assets/）
  4. 保存到本地
    skills/
    目录
  5. 通过import-local API在Skill Compose中注册技能
  6. 该技能将立即在Agent Presets中可用

CRITICAL: Never Combine Questions with Tool Calls

重要提示：切勿将问题与工具调用合并

When you ask the user a question or present results for them to review, your response MUST end with text only. Do NOT include any tool call (execute_code, bash, etc.) in the same response. The user needs a chance to read and reply. If you combine a question with a tool call, the tool executes immediately without waiting — this breaks the conversation flow.
WRONG (never do this):
"Should I install X?" + [execute_code: install X]
CORRECT (always do this):
Turn 1: "Should I install X?" (text only, no tool calls) Turn 2: User says "yes" Turn 3: [execute_code: install X]
当你向用户提问或展示结果供他们查看时，你的回复必须仅以文本结尾。请勿在同一回复中包含任何工具调用（如execute_code、bash等）。用户需要时间阅读并回复。如果将问题与工具调用合并，工具会立即执行而无需等待——这会破坏对话流程。
错误示例（切勿这样做）：
"我应该安装X吗？" + [execute_code: 安装X]
正确示例（始终这样做）：
轮次1："我应该安装X吗？"（仅文本，无工具调用） 轮次2：用户回复"是" 轮次3：[execute_code: 安装X]

How to Help Users Find and Install Skills

如何帮助用户查找和安装技能

Each step below MUST be a separate conversation turn. Never combine steps.
以下每个步骤必须作为独立的对话轮次进行。切勿合并步骤。

Step 1: Understand the Need

步骤1：理解需求

Identify what domain and specific task the user needs help with.
确定用户需要帮助的领域和具体任务。

Step 2: Search

步骤2：搜索

Run 
find_skills.py
with relevant keywords. Try multiple queries if the first doesn't yield good results. Even if the user names an exact skill, always search first to find the correct source/owner and verify it exists.
使用相关关键词运行
find_skills.py
。如果第一次搜索结果不理想，尝试多个查询词。即使用户指定了确切的技能名称，也务必先进行搜索，以找到正确的来源/所有者并验证其是否存在。

Step 3: Present Results and Ask

步骤3：展示结果并询问

Show the user the found skills with:
  • Skill name
  • Source repository
  • Install count (popularity indicator)
  • skills.sh link for more details
Ask which skill(s) they want to install. End your response here — no tool calls.
向用户展示找到的技能，包含：
  • 技能名称
  • 源仓库
  • 安装次数（受欢迎程度指标）
  • 查看更多详情的skills.sh链接
询问用户想要安装哪些技能。在此结束回复——不要包含工具调用。

Step 4: Confirm

步骤4：确认

When the user picks a skill, repeat back what you will install and ask for confirmation. This must be a text-only response with no tool calls. Wait for the user to reply.
当用户选定技能后，重复你将安装的内容并请求确认。**此回复必须仅为文本，无工具调用。**等待用户回复。

Step 5: Install

步骤5：安装

Only after the user confirms in a separate message, run 
add_skill.py
. Report the result.
仅在用户通过单独消息确认后，运行
add_skill.py
。报告结果。

Common Skill Categories

常见技能分类

CategoryExample Queries
Web Developmentreact, nextjs, vue, css, tailwind, html
Testingtesting, jest, playwright, cypress
DevOpsdocker, kubernetes, ci-cd, terraform
Documentationdocs, readme, markdown, api-docs
Code Qualitylint, refactor, code-review, typescript
Designui, design, figma, accessibility
Data & MLpandas, data-analysis, machine-learning
Productivitygit, automation, workflow
分类示例查询词
网页开发react, nextjs, vue, css, tailwind, html
测试testing, jest, playwright, cypress
DevOpsdocker, kubernetes, ci-cd, terraform
文档docs, readme, markdown, api-docs
代码质量lint, refactor, code-review, typescript
设计ui, design, figma, accessibility
数据与机器学习pandas, data-analysis, machine-learning
生产力git, automation, workflow

Tips for Effective Searches

高效搜索技巧

  • Use specific domain keywords: "react performance" instead of just "fast"
  • Try alternative terms if first search yields few results: "testing" → "jest" → "playwright"
  • Popular skill sources include: 
    vercel-labs/agent-skills
    , 
    google-labs-code/stitch-skills
  • Check install counts — higher counts generally indicate more mature skills
  • 使用特定领域关键词：例如用“react performance”而非仅“fast”
  • 如果第一次搜索结果较少，尝试替代术语：“testing” → “jest” → “playwright”
  • 热门技能来源包括：
    vercel-labs/agent-skills
    、
    google-labs-code/stitch-skills
  • 查看安装次数——次数越高通常表示技能越成熟

When No Skills Are Found

未找到匹配技能时

  1. Acknowledge that no matching skill exists yet
  2. Offer to help the user directly with their task
  3. Suggest the user could create a custom skill for their use case using 
    skill-creator
  1. 告知用户目前没有匹配的技能
  2. 主动提出直接帮助用户完成其任务
  3. 建议用户可以使用
    skill-creator
    为其使用场景创建自定义技能