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 complete-examplegit 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/complete-example)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/complete-example"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/complete-example.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 | $0.00094 | $0.01532 |
| Opus 5 | $0.00047 | $0.00766 |
| Sonnet 5 | $0.00019 | $0.00306 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
complete-example 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 today.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
complete-example Skill
- 用于给现有 LaTeX 项目补“示例内容”，不是写真实科研结论。
- AI 负责语义理解、资源关联和叙事生成；硬编码负责文件扫描、结构保护、格式验证和备份。
- 重点是“生成得像一个完整示例”，同时不破坏模板骨架和系统文件。
输入
必需：
project：项目名称或路径。
常用可选参数：
content_density：minimal/moderate/comprehensiveoutput_mode：preview/apply/reporttarget_files：默认自动检测extraTex/*.texnarrative_hint：指导示例叙事方向，但仍属于“示例场景”
默认值与细节统一读取 config.yaml。
适用与不适用
- 适用：需要为 NSFC / thesis / paper 等项目补示例章节、示例表格、示例图文叙事。
- 不适用：真实科研写作、模板修复、结构性重构、修改系统配置文件。
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。
- 扫描项目中的 figures、code、references 等资源。
- AI 分析章节主题、关键概念、语气和上下文。
- AI 推理资源与章节的相关性，并决定内容类型组合。
- 生成连贯的示例叙述，可参考
narrative_hint。 - 用硬编码模板包装成合法 LaTeX。
- 自检并优化生成内容。
- 执行格式与结构验证，需要时生成质量报告。
- AI：语义分析、资源选择、文本生成、自我优化。
- 硬编码：文件扫描、Top-K 选择、LaTeX 包装、格式保护、备份、日志、结构校验。
重点关注 config.yaml 中的：
parameters.*run_management.*scan.*generation.*generation.section_hierarchy.*generation.templates.*
输出
- 所有运行产物写入
{project_path}/.complete_example/<run_id>/ - 典型结构：
backups/logs/analysis/output/metadata.json
output_mode=apply时才写回项目；其它模式只给预览或报告。
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。
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
- 禁止修改系统文件：
main.tex、extraTex/@config.tex、@config.tex - 黑名单文件要做访问控制与哈希校验；若检测到非法修改尝试，必须拒绝。
main.tex只允许\section/\subsection；输入类extraTex/*.tex只允许\subsubsection/\subsubsubsection- 生成内容必须保持“示例”属性，不伪装成真实实验或真实数据来源。
What ships with it
20 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.
- config.yaml 17 KB
- references/README.md 962 B
- scripts/__init__.py 503 B runs code
- scripts/advanced_usage.py 5.4 KB runs code
- scripts/ai_content_generator.py 20 KB runs code
- scripts/basic_usage.py 1.3 KB runs code
- scripts/bibtex_parser.py 5.6 KB runs code
- scripts/file_utils.py 4.8 KB runs code
- scripts/format_guard.py 16 KB runs code
- scripts/formula_generator.py 2.1 KB runs code
- scripts/latex_parser.py 6.2 KB runs code
- scripts/llm_client.py 6.3 KB runs code
- scripts/placeholder_parser.py 3.1 KB runs code
- scripts/resource_allocator.py 10 KB runs code
- scripts/resource_scanner.py 6.5 KB runs code
- scripts/security_manager.py 17 KB runs code
- scripts/semantic_analyzer.py 8.3 KB runs code
- scripts/skill_controller.py 23 KB runs code
- scripts/table_generator.py 5.8 KB runs code
- scripts/template_renderer.py 994 B 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.
- today Changed · +4 lines 8b2dbb9b7c20
- 8d ago First seen · 105 lines · 94 tokens per session scan A d35a67c0430e
complete-example is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,711 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,532 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
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
flue
Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.