菜单
当在当前会话中执行包含独立任务的实现计划时使用；主 Agent 负责写入与确认，子代理仅做隔离的只读调查、审查或方案建议。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | subagent-driven-development |
| description | 当在当前会话中执行包含独立任务的实现计划时使用；主 Agent 负责写入与确认，子代理仅做隔离的只读调查、审查或方案建议。 |
| allowed-tools | task subagent_task execute_command read_file list_directory |
Use subagents to keep complex implementation work focused without polluting the main context. In MoviePilot Agent, subagents are investigators and reviewers by default; the main Agent owns all writes, confirmations, and final user-facing conclusions.
This skill complements executing-plans and dispatching-parallel-agents:
executing-plans: execute a written plan step by step.dispatching-parallel-agents: run independent read-only investigations in parallel.subagent-driven-development: coordinate a plan with subagent research/review checkpoints while the main Agent performs changes.Use when:
Do not use when:
Each subagent task should include:
For review checkpoints, ask subagents to grade issues by impact and evidence, not by authority. Main Agent resolves conflicts with fresh tools or file reads.
Before completion, verify with fresh evidence:
Final response should include: