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 nsfc-research-content-writergit 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/nsfc-research-content-writer)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-research-content-writer"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-research-content-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-research-content-writer"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-research-content-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00082 | $0.03007 |
| Opus 5 | $0.00041 | $0.01503 |
| Sonnet 5 | $0.00016 | $0.00601 |
| Haiku 4.5 | $0.00008 | $0.00301 |
Grade A, and why
nsfc-research-content-writer 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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSFC(二)研究内容编排写作器
目标输出(契约)
- 写入落点(3 个文件):
extraTex/2.1.研究内容.texextraTex/2.2.特色与创新.texextraTex/2.3.年度研究计划.tex
- 禁止改动:
main.tex、extraTex/@config.tex、任何.cls/.sty - 编排原则:先把
2.1写成“可验证闭环”,再从2.1抽取创新点生成2.2,最后把2.1的任务拆分成三年里程碑生成2.3。
参数与输出模式(建议显式提供)
project_root:标书项目根目录(如projects/NSFC_Young)output_mode(默认apply):preview:不直接写入文件;输出三段可复制粘贴的 LaTeX 正文草稿,并标注应写入的目标文件路径apply:仅写入三份目标文件(见“目标输出”),不触碰其他文件
必需输入(最小信息表)
- 若用户未提供,请先收集/补全:references/info_form.md
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
- 当用户环境中出现因本 skill 设计缺陷导致的 bug 时,优先使用
bensz-collect-bugs按规范记录到~/.bensz-skills/bugs/,严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。 - 若 AI 仍可通过 workaround 继续完成用户任务,应先记录 bug,再继续完成当前任务。
- 当用户明确要求“report bensz skills bugs”等公开上报动作时,调用本地
gh与bensz-collect-bugs,仅上传新增 bug 到huangwb8/bensz-bugs;不要 pull / clone 整个 bug 仓库。
- 定位项目与目标文件:确认
project_root,读取并仅编辑三份extraTex/2.*.tex文件;如目标文件不存在,提示用户先初始化/拷贝模板项目。 - 固定”子目标三件套”:把目标拆成 3–4 个子目标(内部规划时可用
S1–S4编号便于自检回溯,此编号仅用于 AI 内部规划,禁止出现在最终 LaTeX 正文中),并对每个子目标强制写清:- 指标(可判定/可验收)
- 对照/基线(与谁比、怎么比)
- 数据来源/验证方案(样本/实验体系/评估方法)
- 生成
2.1 研究内容(以”问题→目标→内容→路线→验证”为主线):- 篇幅控制原则(推荐值,非强制):
- 推荐页数:12–15 页(含图表),约占标书总页数(≤28 页)的 50%
- 推荐字数:12000–15000 字(纯文字部分)
- 图表策略:插入 10–20 张图通常不会显著压缩文字篇幅;图片是“提质”的重要手段
- 核心原则:评审标准已从“字数控制”转向“页数控制”,不要以字数为导向规划篇幅
- 组织逻辑框架(按研究类型选择):新版不再预设提纲,可按研究的内在逻辑自主组织:
- 基础研究推荐框架:
科学问题提出 → 研究假说 → 验证思路 → 预期结果 - 应用研究推荐框架:
技术瓶颈 → 解决方案 → 实验设计 → 效果验证 - 通用主线(兜底):
问题 → 目标 → 内容 → 路线 → 验证
- 基础研究推荐框架:
- 研究问题与总体目标(不超过 2 段,用连贯段落而非条目)
- 研究内容与任务展开(以科学叙事驱动,把验证逻辑自然编织进行文,而非逐条填写三件套)
- 技术路线与验证口径(对照/消融/外部验证/泄漏防控/统计方法,融入叙述而非单独罗列)
- 篇幅控制原则(推荐值,非强制):
- 从
2.1抽取2.2 特色与创新:- 1–3 条即可,少而精(调研报告强调:创新点数量不在多,在于说服力);每条从”为什么这个选择是必然的”出发,说清楚现有路线的局限、本项目的不同之处、以及这个差异预期带来什么——让评审感受到研究者真的想清楚了,而不是在填写创新点模板。
- 避免绝对化措辞(如”首次””领先”);如确需使用,必须给出可核验证据或改写为可审稿的相对表述。
- 从
2.1推导2.3 年度研究计划(三年不跨年):- 每年:年度目标 → 关键任务 → 里程碑(可验收)→ 可交付成果(论文/数据/原型/规范/软件等)
- 里程碑必须与子目标挂钩(否则评审会认为“计划与研究内容脱节”)
- 推进逻辑:让评审看到研究的依赖关系和递进节奏——第一年为什么先做这个、第二年为什么能做那个(避免“第一年做基础研究;第二年做深入研究;第三年做总结”的流水账)
- 一致性校验:
- 检查
2.2创新点是否能回溯到2.1的具体任务与验证; - 检查
2.3里程碑是否覆盖全部子目标,且每年都有可交付物。 - 术语口径对齐:研究对象/缩写/指标命名尽量与
(一)立项依据、(三)研究基础保持一致(如项目中已存在) - 输出净化:最终写入
.tex文件前,确认正文中不含任何S1/S2/Sx/Ty/Vz等内部规划编号;如需表达对应关系,改用自然语言(如"针对第一个研究目标")
- 检查
- 任务完成后的用户提醒:
- 技术路线图建议放在研究内容开头。
What ships with it
22 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 268 B
- config.yaml 2.1 KB
- README.md 3.3 KB
- references/anti_patterns.md 1.4 KB
- references/dod_checklist.md 2.5 KB
- references/info_form.md 1.7 KB
- references/output_skeletons.md 2.5 KB
- references/page_budget.md 1.0 KB
- references/relative_coordinate_examples.md 1.6 KB
- references/subgoal_triplet_examples.md 1.7 KB
- references/terminology_sheet.md 1.4 KB
- references/validation_menu.md 2.5 KB
- references/yearly_plan_template.md 2.3 KB
- scripts/_yaml_utils.py 2.3 KB runs code
- scripts/check_project_outputs.py 6.8 KB runs code
- scripts/create_test_session.py 7.6 KB runs code
- scripts/run_checks.py 2.0 KB runs code
- scripts/validate_skill.py 7.7 KB runs code
- templates/B_ROUND_CHECK_TEMPLATE.md 1.3 KB
- templates/OPTIMIZATION_PLAN_TEMPLATE.md 1.2 KB
- templates/TEST_PLAN_TEMPLATE.md 1007 B
- templates/TEST_REPORT_TEMPLATE.md 830 B
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.
- 4d ago Changed · -2 lines d34c79f2fb68
- 13d ago First seen · 137 lines · 82 tokens per session scan A fff759783179
nsfc-research-content-writer is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,726 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 3,007 once invoked, about $0.0004 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.