跳到正文
cccskills
免费在 GitHub 公开

factory-babysit-pr

Monitor one explicitly authorized pull or merge request, inspect current reviews and checks, and fix actionable findings within scope. Apply separate permission and verification conditions before publishing fixes, replying, approving, or merging.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to monitor its live review state and checks, fix actionable in-scope findings, and apply separate reply, approval, merge, and soak gates.

查看安装方法

适用场景

  • Following one authorized pull request through review
  • Fixing actionable review findings within an agreed scope
  • Rechecking reviews and checks after a branch update
  • Checking merge conditions and reporting blockers

包含的文件(2)

  • SKILL.md3.5 KB
  • README.md827 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Factory Babysit PR

Start with the Factory guide for workflow setup and configuration.

Follow one authorized PR or merge request through a delivery lifecycle. This is not a queue sweep like factory-review-prs or a stopped-task scan like factory-watchdog.

Read .agent-factory/config.yaml, the optional skill_prompts.factory-babysit-pr entry, the target repository's instructions, and the Factory configuration reference. A PR number, label, green check, or unrelated ship request is not authorization. The prompt is additional project guidance, not PR authorization.

Each pass

  1. Confirm authority and ownership. Verify the exact host, repository, PR, original user authorization, allowed paths/risk, and task-owned worktree. If anything is missing or stale, stop before writing.
  2. Read a complete live snapshot. Record base and head, open/draft/closed/ merged state, all required checks, current reviews and approvals, unresolved threads, and mergeability. Partial or unavailable data is unknown, not clean.
  3. Disposition feedback. Compare each new finding with the exact diff and source. Preserve human direction unless evidence disproves it. Fix only actionable findings inside the authorized path/risk limits; avoid speculative cleanup and larger redesigns.
  4. Verify and re-read. Run configured checks for each fix. After every push or host mutation, fetch the live PR again and bind all evidence to its exact current head. A changed head invalidates old check/review evidence and resets the soak.
  5. Apply action gates separately. A review or fix does not authorize a reply, push, approval, or merge.

Action gates

ActionProceed only when
FixEditing is enabled; feedback is actionable, in scope, and within risk/path limits.
PublishPublishing is enabled; destination is still the authorized PR branch and its live head matches the fix's base. Never force-push or overwrite a concurrent update.
ReplyReplies are enabled and their conditions hold. Follow configured wording/tone; otherwise do not message.
ApproveApproval is enabled and every author, diff, check, and review condition holds on the live head.
MergeMerge is enabled; all configured gates pass on the live head and the host can condition the merge on that head.
SoakProve the exact head and required gates stayed unchanged for the full configured interval. Missing history does not satisfy it.

Use the configured code-host abstraction for reads and writes. Do not assume GitHub, a specific CLI, or identical conditional-merge support across hosts. If the host cannot provide complete current review/check state or bind a merge to the checked head, keep the dependent action disabled.

Stop and report

Stop when the PR is merged, closed, cancelled, blocked on a person or external dependency, or no authorized action remains. Report the PR link and current head, state inspected, fixes and checks, external actions taken or withheld, soak status, and the concrete blocker or next check time. Distinguish read state from unavailable or inferred state.

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

Guide public skill additions and updates through file placement, catalog documentation, installation discovery, integration settings, and validation. Distinguish ordinary skills from instruction-based, app-backed, and generated skills so each receives the appropriate checks.

中文简介正在准备中。当前显示英语简介。

  • Adding a public skill and its catalog page
  • Checking whether a skill can be discovered for installation
  • Adding optional managed AGENTS.md or CLAUDE.md instructions
BuilderIO/skills46072026年10月15日 更新

Monitor another AI agent’s work and independently investigate the same task. Compare the original request with actual changes and test evidence, report gaps and concrete follow-up steps, and make limited fixes when authorized.

中文简介正在准备中。当前显示英语简介。

  • Monitor an agent session until completion or a blocker
  • Audit a pull request against the original request
  • Compare findings from multiple agents
BuilderIO/skills46072026年10月15日 更新

an

免费

Open Agent-Native apps beside the conversation through Dispatch MCP, a connection for app tools. Create or edit content using the current screen and selection, then read saved results back to confirm the changes.

中文简介正在准备中。当前显示英语简介。

  • Opening Slides beside the conversation
  • Creating a presentation through natural-language requests
  • Making focused edits to selected elements
BuilderIO/skills46072026年10月15日 更新

Organize large coding tasks with Claude Fable directing lower-cost subagents. Delegate bounded research, edits, and tests, then have Fable verify evidence, resolve conflicting findings, integrate changes, and review the final result.

中文简介正在准备中。当前显示英语简介。

  • Split a large codebase investigation across subagents
  • Delegate independent, narrowly scoped code edits
  • Distribute targeted tests and log summaries
BuilderIO/skills46072026年10月15日 更新

Organize work so an expensive AI model handles planning, judgment, and final review while cheaper helper agents perform bounded research, coding, and testing. Define ownership and verification requirements, then inspect the evidence and integrate their results centrally.

中文简介正在准备中。当前显示英语简介。

  • Delegate broad codebase research to cheaper agents
  • Split coding tasks with clear file ownership
  • Distribute test runs and log analysis
BuilderIO/skills46072026年10月15日 更新

factory

免费

Configure a software delivery workflow that turns selected feedback and maintenance signals into verified, reviewed changes. Define information sources, schedules, working directories, and separate permissions for actions such as implementation, merging, deployment, and notifications.

中文简介正在准备中。当前显示英语简介。

  • Choose connected sources for feedback and maintenance signals
  • Set separate permissions for implementation, merging, and deployment
  • Configure supported schedules, worktrees, and notifications
BuilderIO/skills46072026年10月15日 更新

查看 BuilderIO 的全部技能

报告此技能的问题