技能开发者
- 作者仓库星标 487
- 作者仓库 vibecosystem
- 领域
- 通用
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @vibeeval · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- Python
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
第 1 步:使用模板
复制多工具管道模板:参考模板模式:
第 2 步:自定义脚本
编辑您的新脚本以链接您需要的 MCP 工具:
第 2 步:创造技能
创建`.claude/skills/my-pipeline/SKILL.md`:
第 3 步:添加触发器(可选)
添加到`.claude/skills/skill-rules.json`:
# Skill Developer
Meta-skill for creating new Claude Code skills, including skills that wrap MCP pipelines.
## When to Use
- "Create a skill for X"
- "Help me make a new skill"
- "Turn this script into a skill"
- "How do I create a skill?"
## Skill Structure
Skills live in `.claude/skills/<skill-name>/`:
```
.claude/skills/my-skill/
├── SKILL.md # Required: Main skill definition
├── scripts/ # Optional: Supporting scripts
└── templates/ # Optional: Templates, examples
```
### SKILL.md Format
```yaml
---
name: skill-name
description: Brief description (shown in skill list)
allowed-tools: [Bash, Read, Write] # Optional: restrict tools
---
# Skill Name
## When to Use
[When Claude should discover this skill]
## Instructions
[Step-by-step instructions for Claude to follow]
## Examples
[Usage examples]
```
## Creating an MCP Pipeline Skill
To create a new MCP chain script and wrap it as a skill:
### Step 1: Use the Template
Copy the multi-tool-pipeline template:
```bash
cp $CLAUDE_PROJECT_DIR/scripts/multi_tool_pipeline.py $CLAUDE_PROJECT_DIR/scripts/my_pipeline.py
```
Reference the template pattern:
```bash
cat $CLAUDE_PROJECT_DIR/.claude/skills/multi-tool-pipeline/SKILL.md
cat $CLAUDE_PROJECT_DIR/scripts/multi_tool_pipeline.py
```
### Step 2: Customize the Script
Edit your new script to chain the MCP tools you need:
```python
async def main():
from runtime.mcp_client import call_mcp_tool
args = parse_args()
# Chain your MCP tools (serverName__toolName)
result1 = await call_mcp_tool("server1__tool1", {"param": args.arg1})
result2 = await call_mcp_tool("server2__tool2", {"input": result1})
print(result2)
```
### Step 2: Create the Skill
Create `.claude/skills/my-pipeline/SKILL.md`:
```markdown
---
name: my-pipeline
description: What the pipeline does
allowed-tools: [Bash, Read]
---
# My Pipeline Skill
## When to Use
- [Trigger conditions]
## Instructions
Run the pipeline:
\`\`\`bash
uv run python -m runtime.harness scripts/my_pipeline.py --arg1 "value"
\`\`\`
### Parameters
- `--arg1`: Description
## MCP Servers Required
- server1: For tool1
- server2: For tool2
```
### Step 3: Add Triggers (Optional)
Add to `.claude/skills/skill-rules.json`:
```json
{
"skills": {
"my-pipeline": {
"type": "domain",
"enforcement": "suggest",
"priority": "medium",
"description": "What it does",
"promptTriggers": {
"keywords": ["keyword1", "keyword2"],
"intentPatterns": ["(pattern).*?(match)"]
}
}
}
}
```
## Reference Files
For full details, read:
```bash
cat $CLAUDE_PROJECT_DIR/.claude/rules/skill-development.md
cat $CLAUDE_PROJECT_DIR/.claude/rules/mcp-scripts.md
```
## Quick Checklist
- [ ] SKILL.md has frontmatter (name, description)
- [ ] "When to Use" section is clear
- [ ] Instructions are copy-paste ready
- [ ] MCP servers documented if needed
- [ ] Triggers added to skill-rules.json (optional)
## Examples in This Repo
Look at existing skills for patterns:
```bash
ls $CLAUDE_PROJECT_DIR/.claude/skills/
cat $CLAUDE_PROJECT_DIR/.claude/skills/commit/SKILL.md
cat $CLAUDE_PROJECT_DIR/.claude/skills/firecrawl-scrape/SKILL.md
```
章节与文件索引
按说明文件中的顺序排列。
何时使用
技能结构
创建 MCP 管道技能
第 1 步:使用模板
第 2 步:自定义脚本
文件/命令 -> .claude/skills/<skill-name>/ · .claude/skills/my-pipeline/SKILL.md · --arg1 · .claude/skills/skill-rules.json
内容校验值 -> 60ddbe96ddc2
当前原文的自动摘译,尚未人工审校。
何时使用
“为X创建一个技能”“帮我创建一个新技能”“把这个脚本变成一个技能”“我如何创建一个技能?”
技能结构
技能位于
.claude/skills/<skill-name>/:创建 MCP 管道技能
创建新的 MCP 链脚本并将其包装为技能: