菜单
Write documentation — user-facing, technical, runbooks, onboarding, changelogs. Less is more: only document what code can't tell you.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Gotchas for the agents-cli headless release. The macOS home base signs, notarizes, and npm-publishes over SSH with no GUI and no Touch ID — three things must be primed or the release stalls. Triggers on: release stuck at sign/publish, errSecInternalComponent, "no npmjs.com bundle", "Missing embedded.provisionprofile", making the release autonomous.
Search, browse, and read agent conversation transcripts across Claude, Codex, Gemini, and OpenCode. Use this skill to find previous sessions, recover context, or inspect what agents have done.
Organize AI coding agents into teams that collaborate on a shared task. Create teams, add teammates, start them, monitor progress, and collect results. Use this skill when you need parallel agent execution. For single-agent dispatch, use `agents run` instead.
Use FIRST for any question about THIS codebase's structure, symbols, or relationships — where a function/class/file is defined, what calls or imports it, what breaks if you change it, how two parts connect, or to load focused source context before editing or reviewing. Routes to the cgraph MCP tools (graph_query / graph_explain / graph_impact / graph_path / graph_context), which serve ranked file:line results, node neighborhoods, transitive blast radius, and token-budgeted source bundles from a resident per-project graph daemon in ~10ms — far cheaper than grepping and reading files. Prefer over blind grep/read for code navigation, dependency tracing, and impact analysis.
Register and connect to your machines over Tailscale SSH with agents-cli. Use this skill to sync devices from the tailnet, list them, open a shell on another machine, or see agent sessions running across your whole fleet.
Schedule agents to run on a cron schedule or one-shot at a specific time. The scheduler auto-starts on first add. Triggers on: 'schedule an agent', 'recurring job', 'cron', 'daily', 'every weekday', 'run at 2pm'.
| name | docs |
| description | Write documentation — user-facing, technical, runbooks, onboarding, changelogs. Less is more: only document what code can't tell you. |
| user-invocable | true |
Less is more. Agents and humans can gather context on the fly. Only document what's hard to see from code:
| Task | Subskill | When to Use |
|---|---|---|
| User-facing (CLI, API, tools) | write-user.md | Public interfaces, README, guides |
| Internal technical | write-technical.md | Architecture docs, system design |
| Runbooks | write-runbook.md | Operational procedures, troubleshooting |
| Onboarding | write-onboarding.md | New contributor guide |
| Changelogs | write-changelog.md | Release notes |
1. Don't document what code tells you. If someone can read the function and understand it, don't write docs. Comments rot. Code is truth.
2. Architecture over implementation. Document component boundaries, data flow, integration points. Not how functions work internally.
3. High-level, like a principal engineer. Write for someone who understands systems but doesn't know THIS system. Skip basics.
4. Diagrams over prose. One ASCII diagram or mermaid chart replaces paragraphs. Show structure visually.
5. Reference the code, don't duplicate it.
See harness/agent/execution.go:306-500 beats copying code into docs.
Need documentation?
├── Public interface (CLI, API)? → write-user.md
├── System architecture? → write-technical.md
├── Operational procedure? → write-runbook.md
├── New contributor setup? → write-onboarding.md
├── Release notes? → write-changelog.md
└── Implementation details? → DON'T DOCUMENT. Code is the doc.