메뉴
当实现完成、所有测试通过、需要决定如何集成工作时使用——通过提供合并、PR 或清理等结构化选项来引导开发工作的收尾
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use this skill when the Agent needs to decide where a capability, rule, workflow, runtime anchor, script, job, document, persona change, plugin asset, or repository maintenance item should live. It provides a layered map of the Agent's durable assets so requests to “落实到 all”, “整理自身框架”, or “细化自身” do not bloat memory or scatter files.
Use this skill when the user asks to 自检自身、重新蒸馏、进化版 Agent、增强回去、避免死循环处理、能力增益评估，或在瘦身与增强之间取舍。它先盘点已处理对象、能力风险和真正增益点，再决定增强、修复、拆分、瘦身或停止，不把行数减少当成默认目标。
Use this skill when the Agent needs an executive-control layer before acting: classify user intent, decide direct execution vs read-only inspection vs button confirmation vs clarification, avoid over-asking, and keep work moving to the smallest safe completed state. Trigger especially when the user says 继续、落地、放开手脚、接管、自己判断、按方案推进，or complains about typing confirmations that should be buttons.
Use this skill when the Agent needs to read feedback signals before deciding whether to act, correct itself, distill a lesson, or ask for clarification. It treats user wording, repeated failures, tool errors, missing evidence, and activity context as sensory inputs, then routes to the right organ without overreacting.
Use this skill when the Agent needs to turn experience into a repeatable growth loop: observe signals, decide whether learning is needed, distill reusable lessons, place them into the right asset layer, verify the change, and keep future behavior lighter rather than heavier. Trigger when the user asks to 主动成长、持续进化、经验闭环、复盘后改进, or when repeated failures show a missing habit rather than a one-off bug.
Use this skill when the Agent needs to distinguish safe self-improvement from high-risk mutation. It guards credentials, destructive actions, MoviePilot core files, downloads, restarts, external service changes, and over-broad memory edits while still allowing authorized low-risk /config/agent and /config local plugin work to proceed.
| version | 3 |
| name | finishing-a-development-branch |
| description | 当实现完成、所有测试通过、需要决定如何集成工作时使用——通过提供合并、PR 或清理等结构化选项来引导开发工作的收尾 |
| allowed-tools | execute_command ask_user_choice |
当实现完成、测试通过，并且用户需要决定如何处理当前开发分支时使用：本地合并、推送 PR、保持现状或丢弃。
不要让本技能抢占 MoviePilot 媒体、站点、下载、订阅、转移、插件运维或普通 Git 同步路线。若只是同步 Agent 仓库，优先走 moviepilot-agent-git-maintenance。
验证测试 → 展示按钮选项 → 执行选择 → 必要清理。
不要在测试失败时继续集成；不要让用户手输例行选择；不要未确认就删除工作成果。
在展示选项前运行项目测试或用户指定的验证命令。
如果测试失败：报告失败数量和关键错误，停止，不继续合并或 PR。
优先自动识别 main / master：
git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null
如果无法确定，交给 tg-button-interaction 用按钮选择常见基础分支，不要求用户手输例行确认。
通过 ask_user_choice 展示 4 个选项并停止本轮：
本地合并 -> git:merge-local推送PR -> git:push-pr保持现状 -> git:keep丢弃工作 -> git:discard只在 本地合并 和 丢弃工作 后清理工作树。推送 PR 与 保持现状 默认保留。
详细命令模板、PR body 示例和 worktree 清理命令见同目录 REFERENCES.md。
| 选项 | 合并 | 推送 | 保留工作树 | 清理分支 |
|---|---|---|---|---|
| 本地合并 | 是 | 否 | 否 | 是 |
| 推送 PR | 否 | 是 | 是 | 否 |
| 保持现状 | 否 | 否 | 是 | 否 |
| 丢弃工作 | 否 | 否 | 否 | 是，需二次确认 |
绝不：
始终：
subagent-driven-development：所有任务完成后可调用。executing-plans：所有批次完成后可调用。using-git-worktrees：清理由该技能创建的工作树。本技能只是开发收尾支持，不是 MoviePilot 业务主路由。不得覆盖 direct routes、resource search、media operations、安全确认或完成验证。
/config/agent 能力资产变化，提醒走仓库同步路径。