القائمة
收到代码审查反馈后、实施建议之前使用，尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证，而非敷衍附和或盲目执行。
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | 2 |
| name | receiving-code-review |
| description | 收到代码审查反馈后、实施建议之前使用，尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证，而非敷衍附和或盲目执行。 |
| allowed-tools | read_file list_directory execute_command edit_file write_file ask_user_choice |
Use this skill when the user gives code review feedback, asks to apply review suggestions, or provides external review comments that need technical evaluation before implementation.
The goal is not to agree politely. The goal is to understand, verify, decide, implement safely, and prove the result.
Review feedback is a technical input, not an automatic command.
Default flow:
Ask before implementing when:
Use buttons when the user needs to choose between a few concrete options.
Classify incoming review comments before acting:
For each accepted item, define the smallest verification before writing. For rejected/deferred items, record the technical reason rather than arguing from taste.
Before applying a review suggestion, check:
For YAGNI checks, inspect actual usage with code search before adding abstractions or unused features.
For multi-item feedback:
Do not batch unrelated changes if separate verification would be clearer.
When feedback is correct:
When feedback is wrong or risky:
When verification is impossible with current access:
Avoid performative agreement, defensive arguing, long apologies, or implementing before validation.
/config/agent and /config local plugin assets, user-authorized low-risk review fixes can be applied directly and verified.writing-skills / skill-architecture-governance checks as needed.After changes, run the smallest fresh verification that proves the reviewed issue is addressed:
Never claim that review feedback is resolved without fresh evidence.
Report:
/config/agent assets changed.