菜单
Generate a structured handoff summary for the next session. Triggered when user says "handoff", "交接", or "写个交接".
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
Deep critical analysis of one specific paper — dissect experimental setup, extract numbers, evaluate claims against a hypothesis. Triggers: 'analyze this paper', 'deep dive into', '分析这篇论文', '论文深度分析', 'what does this paper really show', '这篇论文说明了什么', arXiv ID with analysis intent. Not for paper discovery (use scholar-agent), quick summaries, or literature surveys.
Check whether documentation needs updating after code changes. Triggered when user says "sync docs", "文档同步", or "检查文档".
Manage ML experiment lifecycle via structured YAML registry — register, record results, compare runs, track status. Triggers: 'register experiment', 'compare experiments', 'experiment results', 'exp init', 'exp list', '注册实验', '对比实验', '查实验', '哪个实验最好', '记录结果'. Not for training monitoring, checkpoints, or launching jobs.
初始化新项目的 Claude Code 配置。用户说"初始化项目"、"init project"、"配置 Claude Code"时触发。
Pick the next executable task from project-root TODO.md by priority + dependency, mark it in-progress, then start executing. Explicit invocation only — never auto-run. Triggers: 'work on todo', 'next task', 'pick a todo', '领 todo', 'todo worker', '接下来做什么', '领下一个任务'. NOT for: listing TODO contents (just read it), brainstorming what to do, interrupting active coding.
Self-review for paper paragraphs — diagnose v1 issues and give a revision direction (intro, abstract, method, related work). Triggers: 'review this intro', 'check this paragraph', 'paper paragraph self-review', 'help me look at intro / abstract', 'polish this intro', 'paper self-review', '帮我看 intro', 'paper 段落自检', 'review 这段 paper'. Not for: generating a draft from scratch — write v1 yourself first, then iterate.
| name | handoff |
| description | Generate a structured handoff summary for the next session. Triggered when user says "handoff", "交接", or "写个交接". |
Print the handoff summary directly in the conversation (do NOT create files). The user copies it into the first message of the next session to resume context.
Infer content from the current conversation context + git diff + task list. Ask the user to fill gaps if information is insufficient.
Format:
## Current Status
(One sentence summarizing progress)
## Completed
- ...
## Not Yet Done
- ...
## Key Decisions
- ...
## Pitfalls to Avoid
- ...
## Next Steps
(What to do first in the next session)
## Key Files
- ...