Agent skill

Paper Write Sci

by huangwb8 in huangwb8/ChineseResearchLaTeX

根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。

MITAuto-check passedDocuments & Office

Install Paper Write Sci

skills CLI

$ npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install huangwb8/ChineseResearchLaTeX paper-write-sci --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paper-write-sci .claude/skills/paper-write-sci && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "paper-write-sci" agent skill from https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/paper-write-sci into .claude/skills/paper-write-sci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-write-sci", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/paper-write-sci

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install huangwb8/ChineseResearchLaTeX paper-write-sci --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeX.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/paper-write-sci .agents/skills/paper-write-sci && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "paper-write-sci" agent skill from https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/paper-write-sci into .agents/skills/paper-write-sci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-write-sci", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install huangwb8/ChineseResearchLaTeX paper-write-sci --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeX.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/paper-write-sci .cursor/skills/paper-write-sci && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "paper-write-sci" agent skill from https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/paper-write-sci into .cursor/skills/paper-write-sci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-write-sci", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/huangwb8/ChineseResearchLaTeX.git --path skills/paper-write-sci

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install huangwb8/ChineseResearchLaTeX paper-write-sci --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeX.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/paper-write-sci .gemini/skills/paper-write-sci && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "paper-write-sci" agent skill from https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/paper-write-sci into .gemini/skills/paper-write-sci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-write-sci", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install huangwb8/ChineseResearchLaTeX paper-write-sci

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeX.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/paper-write-sci .github/skills/paper-write-sci && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "paper-write-sci" agent skill from https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/paper-write-sci into .github/skills/paper-write-sci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-write-sci", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install huangwb8/ChineseResearchLaTeX paper-write-sci --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeX.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/paper-write-sci .opencode/skills/paper-write-sci && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "paper-write-sci" agent skill from https://github.com/huangwb8/ChineseResearchLaTeX/tree/main/skills/paper-write-sci into .opencode/skills/paper-write-sci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-write-sci", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: paper-write-sci
GitHub stars: 2.9k
Token cost: ~2k tokens
SKILL.md length: 461 words
Files: 16 (incl. scripts, references)
Skills in repo: 27
Repo updated: Oct 4, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 6 steps: 优先使用用户显式指定的风格 → 若用户提供了参考论文或作者材料，可在所选风格基础上提炼额外信号，保存到当前运行目录… → 若用户未指定，则使用 config.yaml:style.default → …
Tasks that involve LaTeX
SKILL.md covers 流程 and 约束
Runs Python scripts from its folder; calls python3

What it does

Paper Write Sci is an agent skill from huangwb8/ChineseResearchLaTeX. 根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including scripts and reference files (for example `CHANGELOG.md`, `README.md` and `config.yaml`).

It sits in Documents & Office, covering LaTeX. It works with LaTeX. The licence is MIT.

When your agent uses it

Tasks that involve LaTeX

Example prompts

“/paper-write-sci”

Requirements

Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

优先使用用户显式指定的风格
若用户提供了参考论文或作者材料，可在所选风格基础上提炼额外信号，保存到当前运行目录的 analysis/reference-style.md
若用户未指定，则使用 config.yaml:style.default
风格服务于“更像人”，不是为了堆砌花哨句子
风格只能改变表达方式，不能改变事实、数字和逻辑
当任务是“全面润色”“重写 Discussion”或任何明显涉及 Discussion 去结果化的请求时，先用 general-01 守住章节分工底线，再叠加 bensz-01 的作者感；不要让作者风格压过章节职责

What it can do on your machine

Read from SKILL.md and the folder at commit b8b4142. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Paper Write Sci loads about 2k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 461 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~38
When it runs · the whole SKILL.md, loaded when a task matches: ~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~15k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from huangwb8/ChineseResearchLaTeX at commit b8b4142, republished under its MIT licence (© huangwb8). 461 words, ~1,994 tokens.

Download SKILL.mdSave it as .claude/skills/paper-write-sci/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.

name: paper-write-sci
description: 根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。
metadata.author: Bensz Conan

Paper Write SCI

写出更像作者本人、而不是通用 AI 模板的论文
控制 SCI 论文语气，少用带冒号的口语化解释句，优先写成自然递进的完整句
在 Introduction 中协调核心观点、核心痛点和核心问题的出现频率，避免反复重提同一主张导致冗余
在写作与修订过程中严格保护数字、逻辑和术语一致性
默认直接推进修改；当用户需要人机协作时，只输出计划，不直接改论文
除明确约定的对外交付物外，把所有中间文件收敛到 <paper_dir>/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-write-sci/{yyyy-mm-dd-hh-mm}/

输入

输入项	是否必须	说明
论文源代码目录	必须	LaTeX 论文项目根目录
Figure/Table 注释	必须	解释每张图表支撑什么论点、有哪些关键数字
用户要求	可选	例如“只改 Results”“偏保守润色”“补强 Discussion”
参考论文/参考作者材料	可选	用于提炼额外风格信号，只学风格，不抄句子
运行模式	可选	默认值与别名以 `config.yaml:mode` 为准
风格	可选	默认值与可用列表以 `config.yaml:style` 为准

流程

输入

按用户请求和配置文件提供必要输入；缺失信息应明确列出并停止依赖该输入的步骤。

执行步骤

因本 skill 设计缺陷导致的 bug，先用 bensz-collect-bugs 规范记录到 ~/.bensz-skills/bugs/，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务
只有用户明确要求“report bensz skills bugs”等公开上报时，才用本地 gh 上传新增 bug 到 huangwb8/bensz-bugs；不要 pull 或 clone 整个仓库

用于根据 LaTeX 论文项目、Figure/Table 注释和用户补充要求，撰写或优化 SCI 期刊论文正文。

执行时优先把确定性步骤交给脚本，把启发式判断留给 AI：

初始化工作区、模式归一化、风格选择、计划文件命名：使用 config.yaml:scripts.prepare_workspace
长规则块按需从 references/ 读取；不要把所有参考文档一次性塞进上下文

`autonomous`（默认）

发现问题就直接修复
采用最小必要改动原则
在写入任何新数字前，必须先过数字审查
在结束前，必须通过章节职责终审、全文一致性终审和逻辑树终审

`collaborative`

先完整读论文，再归纳缺陷和修改路径
计划仅作为人类审查材料，不对正文落笔
计划文件名、主题 slug、run_id 和输出目录都以 config.yaml:runtime_outputs 为准
计划内容至少包含：问题、证据、建议动作、影响章节、关联图表、风格锚点、章节分工风险、风险说明
风格目录：references/styles/
风格模板：references/styles/style-template.md
默认风格以 config.yaml:style.default 为准

当前风格：

风格	领域	作用
`bensz-01`	生物医学	以作者风格为中心，强调问题导向、方法命名、强数字对比、详尽且对非领域读者友好的 figure legend，以及诚实局限
`general-01`	通用 SCI	综合官方 SCI 写作建议，提供未指定领域时的稳健默认风格

风格使用原则：

优先使用用户显式指定的风格
若用户提供了参考论文或作者材料，可在所选风格基础上提炼额外信号，保存到当前运行目录的 analysis/reference-style.md
若用户未指定，则使用 config.yaml:style.default
风格服务于“更像人”，不是为了堆砌花哨句子
风格只能改变表达方式，不能改变事实、数字和逻辑
当任务是“全面润色”“重写 Discussion”或任何明显涉及 Discussion 去结果化的请求时，先用 general-01 守住章节分工底线，再叠加 bensz-01 的作者感；不要让作者风格压过章节职责

优先只读取当前任务所需的参考文件：

风格与章节写法：references/writing-style-guide.md、references/styles/bensz-01.md、references/styles/general-01.md
执行护栏与通过标准：references/execution-guards.md
协作计划模板：references/collaborative-plan-template.md
数字审查模板：references/templates/number-check-template.md
章节职责审查模板：references/templates/section-role-check-template.md
Discussion audit 模板：references/templates/discussion-role-check-template.md
逻辑树模板：references/templates/logic-tree-template.md
逻辑审查模板：references/templates/logic-check-template.md

读取建议：

涉及章节串位、Discussion 重写或全文终审时，读取 references/execution-guards.md
只做风格化润色或图注润色时，优先读取 writing-style-guide.md 和目标风格文件
新增风格时，再读取 references/styles/style-template.md

阶段 0：初始化

确认论文目录、Figure/Table 注释存在且可读
定位主入口 tex，优先检查 main.tex
扫描 \input{} 和 \include{}，建立章节路径映射
识别构建方式与受保护格式文件
运行 python3 scripts/prepare_workspace.py --paper-dir <paper_dir> [--mode ...] [--style ...] [--topic ...] [--reference-material ...]
根据脚本输出确认本轮 {yyyy-mm-dd-hh-mm} 目录、协作计划路径和隐藏工作区根目录
若有参考论文或参考作者材料，提炼补充风格信号
若任务涉及章节职责、数字、缩写或逻辑高风险问题，读取 references/execution-guards.md

阶段 1：理解当前论文

读取全文正文与关键 front/back matter
对照 Figure/Table 注释，提取每张图表支撑的论点
识别已有优质段落、薄弱段落、事实风险、风格不一致位置
标记章节职责风险，特别是 Introduction 泄露结果、Results 过度解释、Discussion 复述结果的段落
标记 Introduction 中核心观点、核心痛点、核心问题被重复表达的位置，判断哪些句子应合并、前移、后置或删除
初步构建逻辑树并写入当前运行目录的 analysis/logic-tree.md
若任务涉及全文缩写治理，按 references/execution-guards.md 建立 analysis/abbreviation-inventory.md

阶段 2：决定执行路径

`collaborative`

按 config.yaml:runtime_outputs.collaborative_plan_pattern 生成计划文件
计划应聚焦“缺陷与修复建议”，而不是直接给改后全文
计划必须显式写出 section-role risk
到此停止，不修改正文

`autonomous`

制定内部修订顺序
优先修正事实错误、数字风险和逻辑断裂
再做结构优化、语言润色和风格统一

阶段 3：逐节写作或修订

默认顺序：

text

Introduction -> Methods -> Results -> Discussion -> Conclusion ->
Additional Information -> Figure Legends -> Supplementary Materials -> Abstract

每节处理时：

先读现有文本和对应图表证据
先判断该节的章节职责，再用所选风格判断“应该怎么写更像作者”
写句子时少用 X: Y、This means: ...、The reason is: ... 这类冒号解释句；除方法标签、列表、图注必要标记外，优先改成自然从句、分号或独立句
写 Introduction 时，把核心问题、核心痛点和核心贡献分别安排在最合适的一处展开；后文只做推进或收束，不反复用近义句重说同一主张
若涉及长规则判断，回到 references/execution-guards.md
若涉及新数字，先过数字审查
若命中 Discussion audit 触发条件，先完成专项审查，再动笔
若涉及新增、删除或改写缩写，先回查 analysis/abbreviation-inventory.md
在 autonomous 模式下对目标 tex 做最小必要修改，并遵守 config.yaml:tex_readability
更新逻辑树与必要的全文一致性记录，确保局部改动没有破坏全局

处理 Figure Legends 或 Supplementary Materials 时：

对每个 panel 解释读图所需的最小视觉语法
对首次出现且不够直观的术语或缩写，补全称并给一句短定义
只保留帮助读图的必要方法细节，避免把整段 Methods 重复进 legend

Show full SKILL.md (165 more words)Show less

阶段 4：终审

发起 section-role-check
完成全文一致性复核，包括数字、缩写、Figure/Table 引用与图注一致性
复查全文冒号解释句是否过密，特别是段首、段尾和 Introduction 贡献句
复查 Introduction 是否反复提及同一个核心问题、痛点或贡献；若重复没有推进逻辑，应合并或删除
对最新文本重建逻辑树并发起逻辑审查
若有阻塞性问题，修复后再复审

阶段 5：渲染与交付

按以下优先级检测构建链：

项目内置一键构建或导出脚本
scripts/manuscript_tool.py
Makefile
latexmk
直接 xelatex

若存在 Word 导出链，也应尝试执行。构建日志放入当前运行目录的 render/。

运行准备脚本：scripts/prepare_workspace.py
执行护栏：references/execution-guards.md
风格模板：references/styles/style-template.md
bensz-01：references/styles/bensz-01.md
general-01：references/styles/general-01.md
协作计划模板：references/collaborative-plan-template.md
章节写作指南：references/writing-style-guide.md
数字审查模板：references/templates/number-check-template.md
章节职责审查模板：references/templates/section-role-check-template.md
Discussion audit 模板：references/templates/discussion-role-check-template.md
逻辑树模板：references/templates/logic-tree-template.md
逻辑审查模板：references/templates/logic-check-template.md

输出

`autonomous`

直接修改目标正文文件
将分析、审查、渲染日志写入当前运行目录 <paper_dir>/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-write-sci/{yyyy-mm-dd-hh-mm}/
若检测到可用构建链，尝试重新渲染 PDF 和 Word

`collaborative`

只输出计划文件，文件名模式以 config.yaml:runtime_outputs.collaborative_plan_pattern 为准，默认带上本轮 run_id
计划中总结论文缺陷、证据、建议修复方案、影响文件和风险
不直接修改论文内容
计划以外的中间文件仍写入当前运行目录 <paper_dir>/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-write-sci/{yyyy-mm-dd-hh-mm}/

输出管理

本 Skill 的新任务中间文件统一写入 ./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/{skill名}/input|output|log/。同一任务复用一个任务根目录；多 Skill 协作才创建 shared/。正式交付物不写入该目录，历史隐藏目录只允许显式兼容读取、迁移或清理。

除下列“明确约定的对外交付物”外，其余中间文件都必须放在 <paper_dir>/.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-write-sci/{yyyy-mm-dd-hh-mm}/：

plans/{collaborative_plan_pattern}
论文最终构建产物，例如项目已有的 PDF 和 Word 输出

禁止再使用旧目录 .write-paper-sci/ 与更早的 .write-paper/。

校验

完成后执行 Skill 已有的静态检查、脚本验证或人工复核，并记录通过标准。

失败与恢复

保留错误证据和已完成产物；仅在输入、环境或外部依赖恢复后从最近的失败步骤重试。

约束

不修改 artifacts/、*.sty、*.cls、*.bst、*.bbx、*.cbx、latexmkrc
不改 main.tex 的结构，除非用户明确要求
不编造数字
不把缩写检查降级成“当前文件自洽”
不允许同一概念在不同 tex 中使用冲突缩写、冲突全称或忽有忽无的定义
不要为了局部简洁随意新造缩写；若新缩写不会在全文稳定复用，优先不用
不为“排版整齐”而重排无关段落或整节 .tex
不把 SCI 正文写成冒号驱动的口语化说明；冒号只用于确有必要的标签、列表、图注结构或期刊格式要求
不在 Introduction 中反复重提同一个核心观点、痛点或问题；每次出现都必须承担新的逻辑推进功能
用户要求“只改某节”时，严格限制改动范围
用户要求协作模式时，严格禁止直接修改论文

公共硬约束

任务需要落盘时，使用唯一的 ./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/ 根目录；共享材料放入 shared/，Skill 专属材料放入该 Skill 的 input/、output/、log/。
正式交付物、源代码和正式计划按项目约定保存，不写入任务工作区；未经授权不覆盖、删除、迁移或远程写入。
项目维护变更检查 BAC 可用性并记录需求、AI 产出、工具结果、文件改动和验证摘要；BAC 只做过程审计，不替代署名、责任或合规判断。
不记录 API Key、访问令牌、密码、Cookie、环境/凭据文件、私有 Prompt、身份信息、本地用户名、主机名或不必要的大体积原始数据。
文件路径必须规范化并限制在授权项目范围内；外部 URL、子进程和网络访问遵循最小权限，防止路径遍历、SSRF 和命令注入。
Skill 版本唯一记录在自身 config.yaml:skill_info.version；公开 API、协议、目录或配置变更同步文档与 CHANGELOG.md。
仅将 Skill 或 Bensz 基础设施本身的设计缺陷交给 bensz-collect-bugs；先脱敏写入 ~/.bensz-skills/bugs/，当前任务不中断，只有用户明确要求才公开上报，禁止直接修改用户已安装的 Skill 源码。

<!-- End of canonical common constraints. -->

Skill 专属约束

不得超出本 Skill description 和上方流程所声明的范围；不将未验证的信息伪装成确定结论。

Files

SKILL.md and 15 other files (scripts, references) in skills/paper-write-sci of huangwb8/ChineseResearchLaTeX.

SKILL.md
CHANGELOG.md
README.md
config.yaml
references/collaborative-plan-template.md
references/execution-guards.md
references/styles/bensz-01.md
references/styles/general-01.md
references/styles/style-template.md
references/templates/discussion-role-check-template.md
references/templates/logic-check-template.md
references/templates/logic-tree-template.md
references/templates/number-check-template.md
references/templates/section-role-check-template.md
references/writing-style-guide.md
scripts/prepare_workspace.py

Open the folder on GitHubat commit b8b4142

Compare with similar skills

Paper Write Sci next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Paper Write Sci compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Paper Write Sci this skillhuangwb8/ChineseResearchLaTeX	2.9k	—	~2k	Automated safety check: Pass	MIT	3 days ago
Research Writingalfonso0512/research-writing-skill	486	1 repos	~818	Automated safety check: Pass	MIT	2 mo ago
Paper WritingMLNLP-World/Paper-Writing-Tips	4.7k	—	~630	Automated safety check: Pass	None	11 days ago
Evomath TaoEvoScientist/EvoSkills	474	2 repos	~3.8k	Automated safety check: Pass	Apache-2.0	7 days ago
PaperjurySpark-To-Paper-Skills/paperjury	1.2k	—	~5.3k	Automated safety check: Pass	MIT	1 mo ago
Thesis Defense PPTX Builderzouchenzhen/thesis-defense-pptx-skill	266	—	~2.4k	Automated safety check: Pass	Apache-2.0	4 mo ago

Similar skills

Research Writing
alfonso0512/research-writing-skill
科研论文写作助手，提供 30 个 Prompt 模板覆盖论文写作全流程. An agent skill from alfonso0512/research-writing-skill.
486 GitHub starsUsed in 1 repo~818 tokens
Documents & OfficeAuto-check passed
Paper Writing
MLNLP-World/Paper-Writing-Tips
学术论文写作检查与优化助手。基于 MLNLP-World 社区整理的论文写作技巧，帮助检查和优化学术论文。Use when: (1) 检查论文 LaTeX 格式和排版, (2) 优化公式符号使用, (3) 改进图表设计, (4) 润色英文学术表达, (5) 检查参考文献格式, (6) 投稿前终稿检查, (7) 用户询问论文写作技巧或规范。
4.7k GitHub stars~630 tokensUpdated 11 days ago
Documents & OfficeAuto-check passed
Evomath Tao
EvoScientist/EvoSkills
A skill your agent uses whenever the user submits a non-trivial mathematical claim that needs a rigorous proof or audit.
474 GitHub starsUsed in 2 repos~3.8k tokens
Documents & OfficeAuto-check passed
Paperjury
Spark-To-Paper-Skills/paperjury
Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML).
1.2k GitHub stars~5.3k tokensUpdated 1 mo ago
Documents & OfficeAuto-check passed
Thesis Defense PPTX Builder
zouchenzhen/thesis-defense-pptx-skill
Builds an editable thesis defense PowerPoint from a thesis PDF or LaTeX project while preserving a supplied university or lab template, then runs a visual quality check.
266 GitHub stars~2.4k tokensUpdated 4 mo ago
Documents & OfficeAuto-check passed
Mathmodel Skill
handsomeZR-netizen/mathmodel-skill
CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling…
292 GitHub stars~2.5k tokensUpdated 11 days ago
Documents & OfficeAuto-check passed

Questions about Paper Write Sci

What does Paper Write Sci do?

根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。. Paper Write Sci is an agent skill from huangwb8/ChineseResearchLaTeX.

When should I use Paper Write Sci?

Paper Write Sci fits situations like: tasks that involve LaTeX.

How do I install Paper Write Sci in Claude Code?

Run `npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a claude-code`. Or copy the skill folder (skills/paper-write-sci in huangwb8/ChineseResearchLaTeX) into .claude/skills/paper-write-sci in your project. Claude Code loads it when a task matches its description.

How do I install Paper Write Sci in Codex?

Run `npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a codex`. Or copy the skill folder (skills/paper-write-sci in huangwb8/ChineseResearchLaTeX) into .agents/skills/paper-write-sci in your project. Codex loads it when a task matches its description.

Can I use Paper Write Sci in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-sci -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paper-write-sci, .gemini/skills/paper-write-sci, .github/skills/paper-write-sci and .opencode/skills/paper-write-sci in your project.

What does Paper Write Sci need to run?

Going by SKILL.md and its folder, Paper Write Sci needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Paper Write Sci access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Paper Write Sci safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Paper Write Sci use?

Paper Write Sci is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper Write Sci use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Paper Write Sci?

Skills that share tags, products or a category with Paper Write Sci: Research Writing (alfonso0512/research-writing-skill, 486 stars), Paper Writing (MLNLP-World/Paper-Writing-Tips, 4.7k stars), Evomath Tao (EvoScientist/EvoSkills, 474 stars) and Paperjury (Spark-To-Paper-Skills/paperjury, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Write Sci?

huangwb8 (a GitHub user) maintains it in huangwb8/ChineseResearchLaTeX, which has 2,865 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 4, 2026.

Source: huangwb8/ChineseResearchLaTeX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Paper Write Sci

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Paper Write SCI

输入

流程

输入

执行步骤

autonomous（默认）

collaborative

阶段 0：初始化

阶段 1：理解当前论文

阶段 2：决定执行路径

collaborative

autonomous

阶段 3：逐节写作或修订

阶段 4：终审

阶段 5：渲染与交付

输出

autonomous

collaborative

输出管理

校验

失败与恢复

约束

公共硬约束

Skill 专属约束

Files

Compare with similar skills

Similar skills

More from huangwb8/ChineseResearchLaTeX

Related

Questions about Paper Write Sci

`autonomous`（默认）

`collaborative`

`collaborative`

`autonomous`

`autonomous`

`collaborative`