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 zuoliangyu/LaTeX-Thesis-Writing --skill bishe-guidergit clone --depth 1 https://github.com/zuoliangyu/LaTeX-Thesis-WritingWrote 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/zuoliangyu/latex-thesis-writing/bishe-guider)<a href="https://agentmods.dev/skills/zuoliangyu/latex-thesis-writing/bishe-guider"><img src="https://agentmods.dev/badge/skills/zuoliangyu/latex-thesis-writing/bishe-guider/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/zuoliangyu/latex-thesis-writing/bishe-guider"><img src="https://agentmods.dev/badge/skills/zuoliangyu/latex-thesis-writing/bishe-guider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00193 | $0.03220 |
| Opus 5 | $0.00097 | $0.01610 |
| Sonnet 5 | $0.00039 | $0.00644 |
| Haiku 4.5 | $0.00019 | $0.00322 |
Grade A, and why
bishe-guider 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 13d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bishe Guider: 毕业论文写作指导
概述
本 Skill 提供中文学术毕业论文从撰写到定稿的全流程指导，包含 4 大规则模块。每个规则对应一个独立文件夹，内含详细的参考文档和工具脚本。
适用对象： 本科、硕士、博士学位论文（以中文学术论文为主）
核心目标：
- 消除 AI 写作痕迹，使论文行文自然严谨
- 确保论文符合学校评审标准与盲审要求
- 规范实验描述、图表排版、引用格式
- 在定稿前执行系统性复盘检查
规则模块
| 规则编号 | 规则名称 | 路径 | 核心功能 |
|---|---|---|---|
| 规则 0 | 项目初始化 | rule-05-project-init/reference.md |
构建标准化的毕业论文项目目录结构 |
| 规则 1 | 像个人类一样写作 | rule-01-humanizer/reference.md |
检测并去除 AI 写作痕迹，注入学术语体的人味 |
| 规则 2 | 查阅参考文献 | rule-02-reference-search/reference.md |
Google Scholar 检索、筛选、引用、管理文献 |
| 规则 3 | 毕业论文写作要点 | rule-03-thesis-writing/reference.md |
论文结构、实验规范、排版语法、用词规范 |
| 规则 4 | 复盘检查 | rule-04-review-check/reference.md |
结构、逻辑、盲审、图表一致性等终稿检查 |
使用方式
根据当前任务阶段，加载对应的规则参考文档：
- 项目未初始化 → 优先加载规则 0，构建标准项目结构
- 撰写/润色阶段 → 加载规则 1 + 规则 3
- 文献调研阶段 → 加载规则 2
- 修改/审查阶段 → 加载规则 1 + 规则 3 + 规则 4
- 定稿前 → 加载全部 4 个规则，按规则 4 的复盘流程执行
核心工作流
工作流 A：项目启动（如未初始化）
1. 检测当前目录是否已存在标准项目结构（检查 src/、references/ 等核心目录）
2. 如未初始化，加载规则 0（项目初始化）
3. 询问用户项目名称和论文题目
4. 执行 init_project.sh 生成完整目录结构
5. 在 src/ 中生成 LaTeX 模板骨架
6. 以表格形式输出初始化结果
工作流 B：章节撰写
1. 用户提交待撰写的章节主题和大纲
2. 加载规则 3（毕业论文写作要点），确认该章节的结构规范
3. 协助用户撰写内容
4. 加载规则 1（像人类一样写作），润色文本去除 AI 痕迹
5. 以表格形式输出审查结果
工作流 C：文献检索与引用
1. 用户提出文献检索需求（主题、时间范围等）
2. 加载规则 2（查阅参考文献）
3. 使用 gs-search / gs-advanced-search 检索文献
4. 按筛选标准评估结果
5. 导出到 Zotero 或生成 BibTeX，存入 references/from-scholar/
6. 以表格形式输出检索与评估结果
工作流 D：全面复盘检查
1. 用户提交论文全文或指定章节
2. 加载规则 4（复盘检查）
3. 按检查清单逐项执行：
- 结构检查（四级标题、章节逻辑一致性）
- 用词检查（夸张词汇、人称、缩写）
- 盲审合规性（匿名性、无个人信息）
- 图表检查（编号、caption、颜色一致性）
- 排版检查（公式标点、表格对齐、首行缩进）
- 逻辑检查（创新点一致性、引用完整性）
4. 运行 check_figure_colors.py 检查图片颜色分布
5. 以表格形式输出全部检查结果
输出格式要求（强制）
所有形式的错误、有效或警告汇报，最终都必须以表格形式返回。
审查结果表格模板
| 检查项 | 位置/上下文 | 严重级别 | 问题描述 | 修改建议 | 状态 |
|---|---|---|---|---|---|
| 夸张词汇 | 第 1 章第 3 段 | 错误 | 出现"首次提出" | 改为"提出了一种" | 待修改 |
| 人称使用 | 第 2 章第 5 段 | 错误 | 出现"我们认为" | 改为"本文认为" | 待修改 |
| 图表大小 | 图 4-1 | 警告 | 图中文字偏小 | 调整字号至 ≥8pt | 待修改 |
| 公式标点 | 式 (3.2) | 错误 | 公式后缺少标点 | 添加逗号 | 待修改 |
| 颜色一致性 | 图 5-2 | 警告 | 与整体画风差异较大 | 调整配色方案 | 待修改 |
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.
- rule-01-humanizer/reference.md 8.4 KB
- rule-02-reference-search/reference.md 4.8 KB
- rule-03-thesis-writing/reference.md 9.4 KB
- rule-04-review-check/reference.md 6.4 KB
- rule-04-review-check/scripts/check_figure_colors.py 13 KB runs code
- rule-05-project-init/reference.md 8.5 KB
- rule-05-project-init/scripts/compile_tikz_to_png.sh 2.1 KB runs code
- rule-05-project-init/scripts/extract_figures_from_pdf.py 2.9 KB runs code
- rule-05-project-init/scripts/init_project.sh 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.
- 13d ago First seen · 299 lines · 193 tokens per session scan A 3fb52ed94d82
bishe-guider is a skill published in the GitHub repository zuoliangyu/LaTeX-Thesis-Writing (55 stars, last pushed 3mo ago), licensed MIT. It adds 193 tokens to every session and 3,220 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…