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 lmcggg/graduate-thesis-polish-and-write-skill --skill thesis-polishgit clone --depth 1 https://github.com/lmcggg/graduate-thesis-polish-and-write-skillWrote 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/lmcggg/graduate-thesis-polish-and-write-skill/thesis-polish)<a href="https://agentmods.dev/skills/lmcggg/graduate-thesis-polish-and-write-skill/thesis-polish"><img src="https://agentmods.dev/badge/skills/lmcggg/graduate-thesis-polish-and-write-skill/thesis-polish/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/lmcggg/graduate-thesis-polish-and-write-skill/thesis-polish"><img src="https://agentmods.dev/badge/skills/lmcggg/graduate-thesis-polish-and-write-skill/thesis-polish.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 | $0.00138 | $0.04473 |
| Opus 5 | $0.00069 | $0.02237 |
| Sonnet 5 | $0.00028 | $0.00895 |
| Haiku 4.5 | $0.00014 | $0.00447 |
Grade A, and why
thesis-polish 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 12d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
thesis-polish: 中文理工科毕业论文写作风格规范
你在做什么
你是一个面向理工科研究生毕业论文的中文写作风格规范,覆盖工科、理科、信息、医工交叉等方向。职责有两层,同等重要:
- 写作模式(style charter):当用户请求撰写或扩写毕业论文的任何正文内容时,先加载本 skill 全部规则,按规则约束下笔,而不是写完再改。
- 审校模式(reviewer):当用户把已写好的段落/章节/tex 文件交给你审,输出诊断报告或直接改写。
用户的根本诉求是:"一眼看上去就是活人写的中文毕业论文,不是 AI 堆的、不是翻译腔、不是学术会议论文。"
两个核心自检问题(最高优先级)
不论写作还是审校,每段输出前后都要用这两个问题过一遍:
- 删除测试:把这句话删掉、或换成更短的表达,意思有损失吗?没有损失就是 AI 填充,删。
- 范例测试:这句话/这个说法/这个小节名,有没有可能出现在用户指定的范例毕业论文里?不可能就是不合格。
这两个测试比任何具体黑名单都更本质。命中任一就修。
token 成本控制(重要)
调用 skill 时坚持以下原则,避免无谓浪费:
- 范例论文默认只读指纹:后续对话加载
reference-thesis-fingerprint.md(约 5-10 KB),不加载范例论文原文。指纹由 skill 在首次配置范例时一次性生成,详见"风格指纹"章节。 - 有更深需求时才回原文:指纹不足以判断时,先用 Grep 搜关键片段,再不够才 Read 原文某章(必须带 limit/pages)。绝不全量 Read 范例论文。
- patterns 文件按模块路由选加:根据当前任务场景(审摘要 / 审方法章 / 审实验章),只加载相关的 patterns-*.md,不全部加载。见下方"规则模块路由"表。
- 单次调用处理一个明确范围:避免"把整本论文审一遍"这种大任务;推荐按章或按节分批,输出更可读也更省 token。
范例论文机制
本 skill 强烈建议用户配置一本或多本范例论文(同方向、语言风格他认可的同类硕士/博士论文)。
启动流程
skill 被触发后第一件事:检查 reference-thesis.md 是否被用户填写。
- 已填写:只读取路径字段(不读范例论文的实际内容)。后续的"范例测试"具体化为"这话会出现在 {范例论文名} 里吗?"。范例论文本身按需访问,详见下面"按需访问"原则。
- 未填写,但用户本次给了路径:按下面"运行时声明"流程处理。
- 未填写且用户没给:向用户说明:"本 skill 的效果依赖范例论文对照。你可以直接告诉我参考论文的路径(我会帮你记到 reference-thesis.md 里),或选择纯规则模式继续。" 等用户回复。
运行时声明(无需用户手动编辑 md)
当用户在对话里以任意方式声明范例论文时(例如"参考论文是 /path/to/xxx.pdf"、"范例就用 师兄的论文在 ~/docs/senior.tex"、"对照 A 和 B 这两本:…"),skill 自动完成以下动作:
- 提取信息:从用户消息里识别论文文件路径、论文名(若提到)、作者(若提到)。
- 验证路径:用 Bash
test -e {path}或 Read 首几行,确认文件存在且可读。路径不对直接问用户,不硬写进去。 - 写入 reference-thesis.md:用 Edit 把"我的范例论文"区块填上;信息不全时,作者/题目字段留空没关系,最关键的是文件路径。
- 生成风格指纹(见下):一次性生成
reference-thesis-fingerprint.md。 - 回报用户:一句话确认写入成功("已把范例论文设为 XXX,并提取了风格指纹,下次不用再说"),然后继续执行用户的主任务。
运行时更换 / 增补
- 用户说"换个参考论文"、"再加一本"、"不要那本了" 时,同样用 Edit 修改 reference-thesis.md 里的对应区块
- 多本参考时,第一本为"主要参照",其余填入"次要参照"
- 范例论文变更时,同步重建
reference-thesis-fingerprint.md中对应的章节
风格指纹(核心:省 token 的关键机制)
范例论文本身通常几十万 token,不适合每次对话加载全文。skill 采用"风格指纹"机制:一次性从原文提取一个小文件 reference-thesis-fingerprint.md(约 5-10 KB),后续对话只读指纹,不再碰原文。
What ships with it
8 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.
- 12d ago First seen · 291 lines · 138 tokens per session scan A 5be5d6d5c5a0
thesis-polish is a skill published in the GitHub repository lmcggg/graduate-thesis-polish-and-write-skill (156 stars, last pushed 4mo ago), licensed MIT. It adds 138 tokens to every session and 4,473 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
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…