Skills 系统完全拆解：用自定义命令驱动无人值守自动化

从 Commands 到 Skills：不只是改名

• 目录结构：Skill 可以是一个目录，SKILL.md 是入口，支持配套文件（模板、示例、脚本）
• 调用控制：disable-model-invocation 和 user-invocable 两个字段精确控制谁能触发这个 Skill
• 子代理隔离：context: fork 让 Skill 在独立沙盒里运行，不污染主对话上下文
• 预注入 shell 命令：!`command` 语法在 Claude 看到 Skill 内容之前先执行，把实时数据注入 prompt

调用控制：谁来触发这个命令

$ARGUMENTS：让命令接受参数

$ARGUMENTS       # 命令名后的所有内容（整体字符串）
$ARGUMENTS[0]    # 第一个参数
$ARGUMENTS[1]    # 第二个参数
$0, $1, $2       # $ARGUMENTS[N] 的简写

---
name: fix-issue

disable-model-invocation: true
---
Fix GitHub issue $ARGUMENTS following our coding standards.

1. Read the issue description
2. Understand the requirements
3. Implement the fix
4. Write tests
5. Create a commit

---
name: migrate-component

---
Migrate the $0 component from $1 to $2.
Preserve all existing behavior and tests.

Shell 预注入：让 Skill 基于实时数据工作

---
name: pr-summary

context: fork
agent: Explore
allowed-tools: Bash(gh *)
---
## Pull request context {#pull-request-context}
- PR diff: !`gh pr diff`
- PR comments: !`gh pr view --comments`
- Changed files: !`gh pr diff --name-only`

## Your task {#your-task}
Summarize this pull request...

• !`command` 必须在行首或紧跟空白字符后出现；如果 ! 紧跟其他字符（如 KEY=!`cmd`），不会被识别
• 替换只做一次，命令输出不会再被当作模板扫描
• 多行命令用 ```! 代码块：

## Environment {#environment}
```!
node --version
npm --version
git status --short

可以通过 settings 里的 `disableSkillShellExecution: true` 关闭这个特性（企业场景的安全控制）。

## `context: fork`：子代理隔离执行 {#context-fork子代理隔离执行}

<LinkPreview href="https://docs.anthropic.com/en/docs/claude-code/sub-agents" />

`context: fork` 是 Skills 系统里另一个高价值能力：让 Skill 在独立的子代理上下文中运行，Skill 内容成为子代理的 prompt，子代理完成任务后把结果返回到主对话——主对话的历史和上下文完全不受影响 <cite index="1" title="官方文档" url="https://docs.anthropic.com/en/docs/claude-code/slash-commands" />。

何时用 `context: fork`：

- **长时间研究任务**：在主对话里做大量文件扫描和分析，会迅速消耗上下文。用 fork 隔离，主对话保持干净。
- **探索性操作**：需要大量 Grep、Glob、Read 但不做写入的探索，`agent: Explore` 提供只读工具集，同时跳过 CLAUDE.md 加载以保持上下文小。
- **有副作用的并行任务**：配合 `agent` 字段选择合适的执行环境。

一个实际案例——深度代码研究：

```yaml
---
name: deep-research

context: fork
agent: Explore
---
Research $ARGUMENTS thoroughly:
1. Find relevant files using Glob and Grep
2. Read and analyze the code
3. Summarize findings with specific file references

allowed-tools：精细授权而非全局放开

---
name: commit

disable-model-invocation: true
allowed-tools: Bash(git add *) Bash(git commit *) Bash(git status *)
---
Stage and commit all current changes with a descriptive message.

四种典型组合

---
name: deploy

disable-model-invocation: true
allowed-tools: Bash(npm run deploy:*) Bash(git status *) Bash(gh *)
---
Deploy $ARGUMENTS to production:

1. Check git status and confirm we're on the right branch
2. Run the test suite
3. Build the application
4. Deploy using: npm run deploy:$ARGUMENTS
5. Verify the deployment succeeded via health check

---
name: review-pr

context: fork
agent: Explore
allowed-tools: Bash(gh pr *)
---
## Current PR {#current-pr}
- Diff: !`gh pr diff`
- Files changed: !`gh pr diff --name-only`
- CI status: !`gh pr checks`

Review this PR for:
1. Logic errors and edge cases
2. Security issues (injections, auth bypasses, data exposure)
3. Performance problems
4. Missing test coverage

Report findings only, don't make changes.

---
name: api-conventions

user-invocable: false
---
When writing or reviewing API endpoints in this codebase:
- Use RESTful naming: /users/:id, not /getUser?id=...
- Return errors in format: { error: { code, message } }
- All endpoints require authentication unless marked public
- Rate limiting: 100 req/min per token, return 429 with Retry-After header

---
name: fix

disable-model-invocation: true
argument-hint: "[issue-number]"
---
Fix GitHub issue #$ARGUMENTS.

First read the issue:
!`gh issue view $ARGUMENTS`

Then:
1. Understand the requirements from the issue body
2. Find relevant code files
3. Implement the fix following project conventions
4. Write or update tests
5. Run tests with: !`npm test -- --testPathPattern=`
6. Create a commit with message: fix(#$ARGUMENTS): [description]

上下文生命周期与 Skill 大小

版本控制与团队协作

• PR 里可以审查 Skill 变更，和普通代码改动一样
• 新团队成员 clone 仓库就拿到了所有工作流
• Skill 逻辑的 bug 可以通过 git blame 溯源