菜单
Use when a task may be a user-approved design/plan document, an existing task CSV, a markdown execution or investigation document, a long-running task description, or a recovery request and needs routing to the right mission sub-skill.
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
Generate a minimal remote artifact pull manifest (results.json + train/logs + eval logs/metrics/vis) and place files under research_workspace/experiments/<ExpID>/remote_artifacts.
Generate a copy-paste remote (AutoDL/tmux) run snippet (git fetch/checkout/pull + scripts/train_eval_shutdown_autodl.sh). Use when you need a remote train→eval command block and must manually choose train/eval scripts from scripts/.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Analyze experiment results pulled by autodl-remote-pull-manifest (remote_artifacts) and generate a Hypothesis→Evidence→Next-Experiment (H→E→N) report. Use when you want evidence-first analysis from logs/metrics/vis and an actionable next-step plan to improve <主指标>.
Ingest pulled remote artifacts under research_workspace/experiments/<ExpID>/remote_artifacts, summarize latest eval (summary.json), and update research_workspace/00-实验记录.md (index row + detailed section). Use when you want to record <主指标>/<辅助指标> into 00-实验记录.md after pulling remote artifacts.
Use when the input is a user-approved design doc or implementation plan and the agent needs to turn it into an executable issues CSV before handing off to CSV execution.
| name | mission |
| description | Use when a task may be a user-approved design/plan document, an existing task CSV, a markdown execution or investigation document, a long-running task description, or a recovery request and needs routing to the right mission sub-skill. |
统一任务入口。判断输入类型，委托给对应的子 skill。
宣告： "使用 mission skill，路由到 <子 skill 名称> 模式。"
若当前会话里已经存在未终态的 mission 执行流，优先继续该执行流；不要因为用户发来解释性、进度性、原因性消息就重新路由。
按以下顺序检查，第一个匹配的规则胜出。
输入匹配: *.csv 或包含路径分隔符
且文件在磁盘上存在
且文件有合法 CSV 表头
→ 委托给 mission-csv-execute
输入匹配: *.md（不是 *.csv）
且文件在磁盘上存在
→ 委托给 mission-doc-route
输入为空，或用户说 "continue" / "resume" / "继续" / "接着做"
→ 委托给 mission-recovery
输入是自然语言描述
且预估工作量 > 1 小时或步骤 ≥ 3
→ 委托给 mission-long-task
预估工作量 < 1 小时且步骤 < 3
→ 不使用 mission。直接执行 + update_plan。
| 子 Skill | 职责 | 输入 |
|---|---|---|
mission-approved-doc | 已批准设计/计划文档 → CSV → 闭环执行 | doc-path.md |
mission-csv-execute | CSV 闭环执行器（强内核） | csv-path |
mission-long-task | 长任务拆分 → CSV → 闭环执行 | 任务描述 |
mission-recovery | 恢复中断的任务 | 无 |
mission-doc-route | 文档 → 路由到 approved-doc 或 long-task | doc-path.md |
mission-csv-executemission-csv-execute 或其他执行类子 skill，后续消息默认仍属于同一执行流；除非用户显式要求 stop / pause / cancel、明确变更任务边界，或满足正式停止条件，否则不得重新落回普通 Q&A / 分析路由