agentleFS
PUNCKePUNCKe/manuscript-context-integrity/.agents/skills/paper-write/SKILL.md

paper-write

Skill2 starsChanged 56 days agoMITView on GitHub

Paper writing stage: enforce the hard writing rules before drafting, one file per section, and run style_lint plus similarity_check immediately after. (指导内容为中文 / guidance is in Chinese) 论文写作环节:写作前核对 04 号禁则、按节独立成文件、写完立刻跑 style_lint 与 similarity_check 体检

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use auto-paper-improvement-loop, paper-illustration and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Yusong-EnceladusSkill

    auto-paper-improvement-loop

    Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper.

    Also in 5 projects that use this

  • raja21068Skill

    paper-illustration

    Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says \"生成图表\", \"画架构图\", \"AI绘图\", \"paper illustration\", \"generate diagram\", or needs visual figures for papers.

    Also in 6 projects that use this

  • raja21068Skill

    deepxiv

    Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.

    Also in 4 projects that use this

  • Yusong-EnceladusSkill

    dse-loop

    Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.

    Also in 4 projects that use this

  • +8 more from raja21068

The file

Files
SKILL.md

论文写作

分工原则(不要搞错)

**写作在主对话做,不要交给子代理。**写作需要你来我往的反馈, 子代理没有对话上下文,语感与理论辨析会丢。

子代理只用于:批量文献、联网验证、格式转换、跨文件汇总。

写作前:核对禁则

如果项目里有 04 号文档的副本或目标刊风格卡,先读。硬性禁则:

  1. 正文禁用破折号(——)。解释性插入改用逗号、冒号或括号重构;补充说明独立成句。
  2. 访谈直接引文用楷体,md 中写 *"引文内容"*。非引文的分析性文字保持正体。 教师课堂话语等非受访者引语不转换。
  3. 括号内不得自我解释或举例((如指令、反馈、提问))。 括号只用于术语缩写定义、文献引用、必要的人物化名标注。
  4. 不写绝对性研究空白表述:不用"研究空白""明显不足""尚无研究""填补空白"。 改用"有待深入""有待推进""相对薄弱""尚属少见""关注不足"。CSSCI 审稿人对"填补空白"类表述敏感。
  5. 学科常识不引注:质性研究范式、三角互证、目的性抽样、主题分析法等属学科通用词汇。 只有直接使用某位学者的特定概念、命题或理论框架时才引。
  6. 政策文件全名在正文写完整后不加括号引用——全名已含发布主体、年份和文件名称。

写作中

  • 按章节独立成文件,放 _输出文件/5_论文草稿/
  • 要引用某个概念时不要 Read 知识库全文,用 kb_search.py 取片段
  • 功能相近的章节合并,避免相邻章节重复同一论证功能 (例如引言和文献综述都有文献批判环节则合并)
  • 从个案提炼一般机制,不要把全文反复用单一经验场域(如"课堂")作为最高层级分析对象, 把它处理为经验入口

写完立刻体检

# 快查(只查 04 禁则,逐行定位)
python "tools/style_lint.py" --draft <这一节> --rules-only

# 完整(含与目标刊风格卡的偏离比对)
python "tools/style_lint.py" --draft <稿> --card "_输出文件/2_文献管理/风格卡_<期刊>.md"

硬性违规逐行列出,改到退出码为 0。

如果这一节用过范文模仿:

python "tools/similarity_check.py" --draft <稿> --corpus corpus/<期刊>

命中 ≥15 字连续重合时必须改写:保留句子的论证功能,更换全部措辞与语序, 不要只做同义词替换。

改稿后

改了正文就可能破坏引用编号,必须接着跑引注重验(见 refs-verify 技能)。

迭代闭环

用户反馈原话优先,逐条落实。用户反馈的原话要记进 _synthesis/—— compaction 会改写或删除用户原话。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.