菜单
Launch, define, and track autonomous headless Claude agents with tool whitelists. USE WHEN automate, launch agent, run autonomous, headless claude, background task, check agents, agent status, define automation, automation profile.
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
Personal AI Infrastructure core. The authoritative reference for how PAI works.
Kaizen AI core. The authoritative reference for how PAI works. USE WHEN KAI system, how PAI works, PAI documentation, PAI reference, system architecture, core functionality.
Spec-driven development accelerator for turning ideas into specs, plans, task lists, implementations, and validation loops. USE WHEN speckit, spec kit, specification kit, write a spec, create a plan from a spec, derive tasks, implement from tasks, spec-driven development, clarify requirements, validate a plan against a spec.
Session wrap-up checklist — saves memory, updates knowledge, checks commit/push status, updates PRD phase. USE WHEN end, wrap up, done for now, closing out, finish session.
Extract system improvements from content AND monitor external sources (Anthropic ecosystem, YouTube). USE WHEN upgrade, improve system, system upgrade, analyze for improvements, check Anthropic, Anthropic changes, new Claude features, check YouTube, new videos. SkillSearch('upgrade') for docs.
Query the YourCompany Engineering Wiki for firmware, build system, Jenkins, GitHub, and repository knowledge. USE WHEN wiki, wiki query, check wiki, what do we know about, yourcompany knowledge, firmware knowledge, build knowledge, jenkins knowledge, look up in wiki, wiki search.
| name | Automate |
| description | Launch, define, and track autonomous headless Claude agents with tool whitelists. USE WHEN automate, launch agent, run autonomous, headless claude, background task, check agents, agent status, define automation, automation profile. |
Launch autonomous Claude agents with pre-defined tool access. No babysitting.
| Trigger | Workflow |
|---|---|
| "launch", "run", "start", profile name | Workflows/Launch.md |
| "define", "create profile", "new automation" | Workflows/Define.md |
| "status", "check agents", "what's running" | Workflows/Status.md |
| "stop", "kill", "cancel" | Workflows/Stop.md |
| "list profiles", "show automations" | Workflows/List.md |
Profiles live at: ~/.claude/automations/
Each profile is a JSON file:
{
"name": "jenkins-monitor",
"description": "Check Jenkins builds, summarize failures",
"prompt": "Check recent Jenkins builds. Summarize any failures with root cause analysis.",
"allowedTools": ["mcp__jenkins__*"],
"cwd": "~/Projects/Automation",
"permissionMode": "auto",
"model": "sonnet"
}
Launch inline: /automate run jenkins-monitor
Launch ad-hoc: /automate run "check device health" --tools mcp__router__*