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-abstractgit 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-abstract)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-abstract"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-abstract/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-abstract"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-abstract.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 | $0.00164 | $0.02945 |
| Opus 5 | $0.00082 | $0.01473 |
| Sonnet 5 | $0.00033 | $0.00589 |
| Haiku 4.5 | $0.00016 | $0.00295 |
Grade A, and why
nsfc-abstract 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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSFC 中英文摘要生成器
输入（先要信息，缺啥就问啥）
优先让用户按信息表提供（见 skills/nsfc-abstract/references/info_form.md）。若用户只给了零散信息，先用 3-6 个问题补齐最关键缺口：
- 你希望题目更偏“机制向 / 方法向 / 转化向 / 场景向”哪一类？（不确定可不选，默认给混合候选）
- 研究对象/场景是什么？（疾病/材料/系统/任务）
- 领域痛点与未解决的科学问题是什么？（一句话）
- 你们的关键前期发现/预实验/数据点是什么？（1-2 条，可定量）
- 拟验证的科学假说/核心判断是什么？（一句话）
- 研究内容 3-4 点分别要做什么、用什么方法、得到什么可验证结果？
- 预期科学意义/应用价值是什么？（避免空话）
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。
目标：写出“评审一眼读懂”的五句式摘要，做到重要性、科学问题、可行性证据、研究内容、科学意义五个要素齐全；并输出与之一致的英文翻译。
篇幅比例原则：资深评审希望尽快看到申请人”进入正题”，背景铺垫过多是专业度不足的信号。各句目标占比如下（超出即压缩）：
| 句子 | 功能 | 目标占比 |
|---|---|---|
| ① 背景 | 入场券 | ≤ 15% |
| ② 科学问题 | 定位缺口 | 15–20% |
| ③ 前期研究 | 建立可信度 | 20–25% |
| ④ 研究内容 | 主体 | 35–40% |
| ⑤ 意义 | 闭环 | 10–15% |
- 重要性/背景（≤ 15%）：严格 1 句，点明研究对象的重要性与核心瓶颈，不展开背景综述。
- 科学问题（15–20%）：指出关键未知与当前不足（具体到机制/指标/因果链的缺口）。
- 可行性证据（前期研究）（20–25%）：给出 1-2 条前期发现/预实验（尽量可定量），并顺势提出科学假说/核心判断。
- 研究内容（3-4 点）（35–40%）：用动词开头，写清”做什么→怎么做→要验证什么/得到什么判据”（点数默认以
config.yaml:limits.content_points_min/max为准）；此句是摘要主体，应获得最多篇幅。 - 意义/价值（10–15%）：总结预期贡献（科学机制 + 方法/策略/应用潜力），与第 2 句的问题形成闭环。
当用户明确要求“中文≤400字符/英文≤4000字符”等硬约束时，必须走闭环：先检测，再压缩，再检测，合格后再写入。
- 先生成一个“可读但可能超限”的初稿（五句式要素齐全）。
- 用确定性脚本检测（必须用
--json，让硬编码负责精确计数）：python3 skills/nsfc-abstract/scripts/validate_abstract.py - --json --diff --strict- 输入可通过 stdin（无需先写文件），或在写入
NSFC-ABSTRACTS.md后对文件校验。
- 若超限：按“压缩优先级”执行压缩，再回到步骤 2，最多 3 轮。
- 连续 3 轮仍超限：停止自动压缩，向用户说明当前超限数（ZH/EN exceeded），并请用户选择：
- 允许删减某些信息（哪些可删）
- 放宽字数上限（修改
config.yaml） - 人工给出更短的关键信息摘要（例如只保留最关键 1 条证据 + 3 点研究内容）
压缩优先级（从上到下）
- P0（必须保留）：研究对象/关键科学问题缺口/定量证据（若有）/核心方法名称/预期贡献闭环
- P1（优先精简）：程度副词、形容词修饰、”我们将/本研究”主语、过程性描述、”通过/采用”等介词短语、并列重复表达
- P2（优先删除）：背景超出 15% 的部分（首先压缩）、空洞评价（无定量支撑的”显著/重要/领先”等）、重复句、与科学问题无关的背景扩展
What ships with it
9 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.
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.
- 3d ago Changed · +10 lines 7a99a70a02a7
- 11d ago First seen · 137 lines · 164 tokens per session scan A c57a501b7b3a
nsfc-abstract is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,721 stars, last pushed 3d ago), licensed MIT. It adds 164 tokens to every session and 2,945 once invoked, about $0.0008 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.