菜单
Build and maintain a clean separation between public artifact packages and internal writing/advisor packages. Use when the user says "artifact package", "paper package", "writing package", "public artifact vs internal package", "生成投稿包", or "生成写作用包".
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。
Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review → research-refine plus experiment-plan to go from a broad research direction to validated, pilot-tested ideas. Also handles robotics / embodied AI directions through simulation-first robotics mode. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", "robotics idea discovery", "embodied AI idea", or wants the complete idea exploration workflow.
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
Turn one core reference paper and up to three comparable papers into evidence-grounded topic candidates. Use when the user asks to 拆解对标论文, 从论文找选题, analyze reference papers for research ideas, map conflicting findings, or wants a reference-led idea start before novelty checking.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Generate a structured paper outline from audited formal experiment results and review conclusions. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants a paper plan after formal runs and evidence audit. If only smoke, pilot, toy, or validation results exist, produce a gap report or next actions instead of routing to manuscript drafting.
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
| name | artifact-package-splitter |
| description | Build and maintain a clean separation between public artifact packages and internal writing/advisor packages. Use when the user says "artifact package", "paper package", "writing package", "public artifact vs internal package", "生成投稿包", or "生成写作用包". |
Use this skill when final results exist and the project needs separate public artifact content and internal paper-writing/advisor content.
Keep these layers distinct:
experiments/runs/.experiments/results/ or a project-specific promoted directory.The public package must be English only and must not include internal writing language such as:
Include only final tables, figures, LaTeX snippets, trace CSVs, and scripts or metadata needed for reproduction. Exclude obsolete datasets, old exploratory traces, local paths, and abandoned package versions.
The internal package may include Chinese explanatory README files, claim boundaries, what-can/cannot-be-written notes, narrative ordering, and trace provenance.
It must copy current final artifact data, not old package data. Do not restore old numeric values or legacy filenames unless the user explicitly requests a historical comparison.
When a one-off builder is useful, recommend an ignored script under root
temp/, for example temp/build_internal_writing_package.py, and keep it out
of Git unless the user wants a reusable maintained tool.
Run or prepare checks like:
rg -n "we should write|claim boundary|advisor|draft|thinking|old experiment|TODO|C:\\Users|/root/autodl" <public-package>
find <public-package> -type f | sort
find <internal-package> -type f | sort
du -sh <public-package> <internal-package>
Also verify: