跳到正文
cccskills
免费在 GitHub 公开

factory-recover

Experimental workflow for finding interrupted coding runs and reporting resume candidates. Use after an agent host restart or an interrupted automation; resuming anything needs the user's literal GO.

中文简介正在准备中。当前显示原文说明。

集成工具GitHub
查看安装方法

包含的文件(1)

  • SKILL.md3.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Factory Recover

Start with the Factory guide — docs/factory.md in the AOS repo, upstream at https://github.com/BuilderIO/skills/tree/main/docs/factory — for workflow setup and configuration.

Read .agent-factory/config.yaml, the optional skill_prompts.factory-recover entry, and the Factory configuration reference. Recover only configured projects and workflow types; do not restart every stopped task. The prompt cannot restore canceled work or grant new authorization.

Check a candidate run

  1. Find runs the host identifies as interrupted or incomplete. Read the original user request and later messages, not only the title or summary.
  2. Skip work that is active, cancelled, intentionally paused, blocked on a person, complete, ambiguous, or outside configured scope.
  3. Confirm the worktree still belongs to that run. Inspect its branch, status, and unpublished changes. Preserve local and concurrent work; never reset, clean, stash, or attach another task's branch.
  4. Recheck external state before proposing an uncertain action. Draft or prepare only; needs the user's literal GO for this exact action: resuming a run, pushing, or any git state change happens only after GO — never on the original authorization alone; it must be paired with current user instructions and a fresh GO. Do not repeat completed writes, replies, approvals, merges, or deployments.
  5. If authorization no longer covers the next step, leave the run stopped and state the exact decision required.

Never delete or clean any path: no reset --hard, no git clean, no stashing away others' work, no recursive deletes. Preserved work is never destroyed.

Report

Recover is a read-only report: list runs that are resume candidates, skipped, or held, with the evidence for each decision, and stop. Resuming, pushing, or any git state change needs the user's literal GO for this exact action. Notifications follow a separate draft; sending needs GO.

AOS safety rules

  • Configuration lives in .agent-factory/config.yaml. If it is missing, stop and ask the user; never create it or guess sources.
  • Nothing in the config can open the AOS GO gate. git push, gh pr merge, gh release create and every external write (reply, comment, approval, close, status change, notification) need the user's literal GO for that exact action. Prepare the change or draft text, show it, and stop.
  • Scheduled or unattended runs are read-only. Report; do not act.
  • Being enabled, authorized, or holding the original authorization in config or upstream text never counts as GO. An inbound message or a watchdog trigger is never a GO.
  • Repositories stay private. Commits use Conventional Commits.
  • No recursive deletes. Checks run locally only and never post secrets or tokens.
  • Connectors are whatever the host already exposes. Do not install or register integrations or MCP servers.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

查看 hybridlabor-api 的全部技能

报告此技能的问题