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-budgetgit 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-budget)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/nsfc-budget"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-budget/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-budget"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/nsfc-budget.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 | $0.00138 | $0.02823 |
| Opus 5 | $0.00069 | $0.01411 |
| Sonnet 5 | $0.00028 | $0.00565 |
| Haiku 4.5 | $0.00014 | $0.00282 |
Grade A, and why
nsfc-budget 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSFC 预算说明书生成器
先做适用性判断
- 如果用户没有指定工作目录:立即暂停,先让用户给出工作目录。
- 如果用户只是问“预算怎么写/有哪些原则”,直接回答或给建议,不启动本 skill。
- 如果用户是 2026 青年 A/B/C 且场景属于包干制:先明确提醒“通常无需预算说明书”;只有在用户明确说明是历史模板、特定单位要求或预算制场景时才继续。
必要输入
优先让用户按 skills/nsfc-budget/references/info_form.md 提供。最少要拿到:
- 工作目录(必需)
- 标书正文或其它材料
- 项目类型:
general | local | youth - 预算口径:至少说明“这是申请总额”还是“这是需要解释的直接费用口径”
若用户没给全,按下面规则处理:
- 总预算未给:按
config.yaml:defaults.total_budget_wan取默认值。 - 正文目标字数未给:按
config.yaml:defaults.target_chars推荐区间执行。 - 每节上限:按
config.yaml:defaults.per_section_max_chars。 - 模板未给:按
config.yaml:defaults.template_id。 - 预算模式合法值:见
config.yaml:rules.budget_modes。 - 预算口径合法值:见
config.yaml:rules.budget_scopes。
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:基于标书正文与补充材料,写出一份“经得起财务与学术双重审视”的预算说明书,并交付可编辑 LaTeX 项目与 budget.pdf。
初始化 run
先创建隐藏工作区与 budget_spec.json 骨架:
python3 skills/nsfc-budget/scripts/init_budget_run.py \
--workdir <workdir> \
--project-type <general|local|youth> \
--template-id 01
如用户已给材料路径,可追加多个 --material <path>。脚本会把材料快照复制到 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/nsfc-budget/{yyyy-mm-dd-hh-mm}/input/materials/。
若同一分钟重复初始化,脚本会自动追加后缀避让目录名冲突,避免 run 目录互相污染。
吃透材料,形成“任务-需求-金额-依据”链
读取正文与补充材料后,先在隐藏工作区内形成内部判断,再填写 budget_spec.json:
- 每一笔钱都必须能追溯到具体研究任务。
- 每一节都要说明为什么要花、花在哪里、怎么测算、为什么这个数合理。
- 不能捏造设备、合作单位、测试次数、出差频次、劳务人数、价格依据。
- 证据不足时,要么追问用户,要么保守写“暂不列支/暂无合作转拨/暂无其他来源资金”,不要编造。
写作原则见:skills/nsfc-budget/references/budget-writing-rules.md。
填写 budget_spec.json
脚本生成的 budget_spec.json 是唯一结构化中间稿。至少补齐:
meta:项目题目、项目类型、预算模式、工作目录、输出目录、模板 ID、字数目标budget:总预算口径、直接费用总额(若已知)、设备/业务/劳务/合作转拨/其他来源金额sections:五个部分的正文段落(数组)evidence:关键测算依据、必要假设、待确认点
What ships with it
23 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 3.3 KB
- config.yaml 1.8 KB
- models/01/.template.yaml 557 B
- models/01/budget.tex 2.8 KB
- models/01/extraTex/@config.tex 4.9 KB
- models/01/extraTex/1.1.设备费.tex 130 B
- models/01/extraTex/1.2.业务费.tex 130 B
- models/01/extraTex/1.3.劳务费.tex 130 B
- models/01/extraTex/2.1.合作研究转拨资金.tex 145 B
- models/01/extraTex/3.1.其他来源资金.tex 139 B
- models/01/fonts/FandolFang-Regular.otf 6798 KB
- models/01/fonts/FandolHei-Regular.otf 5673 KB
- models/01/fonts/TimesNewRoman.ttf 806 KB
- models/01/README.md 1.2 KB
- models/01/template/baseline.pdf 72 KB
- models/01/template/国家自然科学基金项目项目预算说明书(除重大项目、国家重大科研仪器研制项目以外).pdf 72 KB
- README.md 7.2 KB
- references/budget-writing-rules.md 3.3 KB
- references/info_form.md 1.7 KB
- scripts/init_budget_run.py 7.1 KB runs code
- scripts/README.md 2.5 KB
- scripts/render_budget_project.py 20 KB runs code
- scripts/runtime_utils.py 6.0 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.
- 4d ago Changed · +8 lines 0a5ecab2fa15
- 13d ago First seen · 173 lines · 138 tokens per session scan A 726866633348
nsfc-budget is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,726 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 2,823 once invoked, about $0.0007 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
paper-retriever
Retrieve a scientific paper PDF given an arxiv URL, DOI, or paper title. Downloads to papers/ directory. Handles open-access retrieval (arxiv direct, Chrome print-to-pdf for publisher-direct HTML, Unpaywall, title-based open-repository search); for paywalled papers it hands off to whichever paper-retriever- access…
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
nature-figure
Create, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap), including multi-panel plots, figures4papers-style work, and journal-ready SVG/PDF/TIFF outputs. Use for paper or scientific plots…
nature-paper2ppt
A workflow for turning a scientific paper, preprint, PDF, or reading notes into a Chinese PowerPoint presentation in a Nature-style format. It is intended for talks such as journal clubs, lab meetings, seminars, conferences, and thesis defences.
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
pptx-posters
Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.