ChineseResearchLaTeX is a collection of LaTeX templates and an AI-assisted workflow for preparing Chinese research documents such as grant proposals, papers, theses, and academic CVs. Researchers use it to plan, format, review, compile, and revise these documents with human oversight. The catalogue skills and instructions support its agent-based research-writing workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huangwb8/ChineseResearchLaTeX --skill paper-write-scigit clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huangwb8/chineseresearchlatex/paper-write-sci)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/paper-write-sci"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/paper-write-sci.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.03630 |
| Opus 5 | $0.00052 | $0.01815 |
| Sonnet 5 | $0.00021 | $0.00726 |
| Haiku 4.5 | $0.00010 | $0.00363 |
Grade A, and why
paper-write-sci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Write SCI
BenszAPI 任务工作区
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。
与 bensz-collect-bugs 的协作约定
- 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
目标
- 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 |
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}/
模式规则
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
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 12 KB
- config.yaml 6.3 KB
- README.md 14 KB
- references/collaborative-plan-template.md 1.2 KB
- references/execution-guards.md 11 KB
- references/styles/bensz-01.md 13 KB
- references/styles/general-01.md 7.3 KB
- references/styles/style-template.md 3.2 KB
- references/templates/discussion-role-check-template.md 1.5 KB
- references/templates/logic-check-template.md 1.8 KB
- references/templates/logic-tree-template.md 1.3 KB
- references/templates/number-check-template.md 1.9 KB
- references/templates/section-role-check-template.md 1.7 KB
- references/writing-style-guide.md 5.6 KB
- scripts/prepare_workspace.py 7.9 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 253 lines · 104 tokens per session scan A 449841bc6542
paper-write-sci is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,707 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 3,630 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
nature-data
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data…
nature-response
Draft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review…
paper-self-review
This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", "audit claims", "check overclaiming", "verify whether results support claims", or mentions systematic paper quality checking. Provides comprehensive quality…
post-acceptance
This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter thread", or mentions post-acceptance conference preparation. Provides comprehensive workflow for presentation, poster, and…
results-report
A workflow for turning completed experiment analyses into a structured research report with findings, limitations, failures, and next steps.