القائمة
完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求；在 MoviePilot Agent 中优先使用只读子代理或本地验证命令，不依赖外部审查者。
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 | requesting-code-review |
| description | 完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求；在 MoviePilot Agent 中优先使用只读子代理或本地验证命令，不依赖外部审查者。 |
| allowed-tools | task subagent_task execute_command read_file list_directory |
Use this skill to get an independent check before claiming that an important implementation, skill change, plugin change, or repository sync is ready.
It is a verification aid, not a replacement for the main Agent's responsibility. The main Agent still owns final decisions, writes, confirmations, and user-facing conclusions.
Use before:
/config/agent capability changes;Skip when the change is a tiny text-only correction already covered by a direct structural check.
Use a security-focused review path when the change touches credentials, auth/session logic, API endpoints, file handling, command execution, external URLs, plugin settings, database access, or logs.
Check at least:
Report severity as CRITICAL / HIGH / MEDIUM / LOW with evidence and concrete fix guidance. This lane is advisory; it does not replace MoviePilot safety boundaries.
For important changes, choose the review lens explicitly:
A review finding must include severity, evidence, and a fix or deferral reason. Do not treat generic style opinions as blockers unless they affect safety, correctness, or maintainability.
Choose the smallest adequate path:
task or subagent_task.Give reviewers compact context:
Do not expose secrets. Do not ask subagents to perform writes.
After review:
For docs, skills, plans, and reports, review:
For MoviePilot plugin or Agent capability changes, add a docs/config-surface lane when relevant:
Final response should include: