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 HenryLiu0405/njupt-thesis-skill --skill njupt-thesisgit clone --depth 1 https://github.com/HenryLiu0405/njupt-thesis-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/henryliu0405/njupt-thesis-skill/njupt-thesis)<a href="https://agentmods.dev/skills/henryliu0405/njupt-thesis-skill/njupt-thesis"><img src="https://agentmods.dev/badge/skills/henryliu0405/njupt-thesis-skill/njupt-thesis/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/henryliu0405/njupt-thesis-skill/njupt-thesis"><img src="https://agentmods.dev/badge/skills/henryliu0405/njupt-thesis-skill/njupt-thesis.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 | $0.00388 | $0.02896 |
| Opus 5.5 | $0.00155 | $0.01158 |
| Sonnet 5.5 | $0.00078 | $0.00579 |
| Haiku 4.5 | $0.00039 | $0.00290 |
Grade A, and why
njupt-thesis 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 1mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
南邮毕业设计(论文)全流程助手
本技能由一位学长的完整毕设项目沉淀而来,覆盖从立题到答辩归档的全部环节。他的课题是理工科方向(英文论文 + 仿真 → 中文毕业论文),但本技能的流程、格式与工作方法对南邮各专业通用;涉及具体学科的地方会注明"以你的源材料为准"。
第零步:定位阶段,索要源材料
毕设是一个 5 个月的长流程。接到任何请求,先弄清两件事:
1. 学生处在哪个阶段? 据此决定读哪份参考文件:
| 阶段 | 大致时间 | 产出物 | 详细指引 |
|---|---|---|---|
| 立题与任务书 | 12 月下旬 | 立题审批表、任务书 | references/materials-checklist.md |
| 开题 | 1 月 | 开题报告 | 同上 |
| 外文翻译 | 寒假~3 月 | 翻译封面+译文+原文 | 同上 |
| 中期检查 | 3 月底 | 中期检查表 | 同上 |
| 论文撰写 | 2~4 月 | 论文初稿(逐章) | references/format-spec.md + references/writing-workflows.md |
| 定稿与检测 | 5 月初 | 查重报告、AIGC 检测报告、批注修改 | references/writing-workflows.md |
| 答辩 | 5 月中下旬 | 答辩资格审查表、PPT、讲稿、指导记录 | references/defense.md + references/materials-checklist.md |
2. 源材料在哪? 在写任何内容之前,向学生索要(或确认已上传):
- 学校/学院当年下发的官方模板和通知(格式细节每年可能微调,官方模板永远优先于本技能记录的规格);
- 学生自己的一手研究材料:英文论文 PDF、实验/仿真代码、原始数据、实际生成的图;
- 需要修改的官方表格原件(任务书、指导记录等),用于保留官方表头格式。
三条铁律(全流程任何任务都适用)
铁律一:先读后写,绝不编造。 写论文内容前,必须先打开并读完对应的源材料——英文原文 PDF 的对应小节、MATLAB/Python 代码的实际输出、仿真图的真实曲线。公式要逐项对照英文原文转写,不能凭印象默写;图表描述要对照真实图片(曲线走势、坐标轴、图例、数值)来写,不能编造"性能提升了 X%"这类源材料里没有的结论。如果某条公式或数据无法核对,在交付文档中用灰色斜体注释显式标出"此处请对照原稿核对",而不是悄悄给一个看起来合理的版本。这条铁律存在的原因:毕设论文要经过导师审阅、查重、答辩三道关,任何一处编造都会在某一关暴露,且学生自己往往发现不了。
铁律二:增量交付,先定风格。 不要一次性生成整本论文。先交付一章(或一节),让学生确认语言风格、格式、公式处理方式都符合预期后,再按同样规格批量推进。每章交付时给出清晰的"论文小节 ↔ 英文原文小节 ↔ 代码文件"对应关系,方便学生核对。
铁律三:完成必核,渲染检查。 每生成或修改一个 docx,都要:① 用 docx 技能的 validate.py 校验;② 用 soffice.py 转 PDF、pdftoppm 渲染成图片,亲眼逐页查看版式(页眉页码、标题层级、公式段落、表格边框)是否正确,再交付。文字层面"看起来对"和渲染出来"真的对"经常不一致。
论文撰写(最高频任务)
论文结构(固定顺序)
封面 → 毕业设计(论文)原创性声明 → 中文摘要+关键词 → 英文 ABSTRACT+Key words → 目录 → 正文各章(理工科典型:概述/系统模型/问题建模/算法设计/仿真分析/结论,共 5~6 章) → 结束语(个人学习感悟,与"结论"章的技术总结不同) → 致谢 → 参考文献(→ 附录,可选)。
前置部分(声明~目录)无页眉无页码;正文起每页页眉"南京邮电大学 20XX 届本科毕业设计(论文)"(宋体五号居中,下加细横线),页脚页码"- N -"居中,从第一章第 1 页起算。
核心格式速查(完整规格见 references/format-spec.md)
- 正文:中文宋体小四(12pt)、西文/数字 Times New Roman,两端对齐,首行缩进 2 字符,1.5 倍行距(本届实测固定值 24 磅与官方模板视觉一致,以学院模板为准);
- 章标题"第X章 标题"黑体三号居中;二级标题黑体四号左对齐;三级标题黑体小四左对齐;
- 公式:居中,编号"式(章-序)"右对齐;
- 图:居中,图题在图下方居中,"图5.1 系统性能收敛曲线"格式;表:表题在表上方居中,"表5.1 仿真主要参数汇总";
- 参考文献:GB/T 7714-2015,作者姓全大写、名缩写,[J]/[C]/[D] 标识,总数通常要求 30 篇左右(以导师要求为准)。
What ships with it
5 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.
- 1mo ago First seen · 91 lines · 388 tokens per session scan A b06c9af206f2
njupt-thesis is a skill published in the GitHub repository HenryLiu0405/njupt-thesis-skill (6 stars, last pushed 4mo ago), licensed MIT. It adds 388 tokens to every session and 2,896 once invoked, about $0.0016 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.