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 ChenXi-hub/tju-thesis-review-kit --skill tju-thesis-reviewergit clone --depth 1 https://github.com/ChenXi-hub/tju-thesis-review-kitWrote 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/chenxi-hub/tju-thesis-review-kit/tju-thesis-reviewer)<a href="https://agentmods.dev/skills/chenxi-hub/tju-thesis-review-kit/tju-thesis-reviewer"><img src="https://agentmods.dev/badge/skills/chenxi-hub/tju-thesis-review-kit/tju-thesis-reviewer/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/chenxi-hub/tju-thesis-review-kit/tju-thesis-reviewer"><img src="https://agentmods.dev/badge/skills/chenxi-hub/tju-thesis-review-kit/tju-thesis-reviewer.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 | $0.00073 | $0.01183 |
| Opus 5.5 | $0.00029 | $0.00473 |
| Sonnet 5.5 | $0.00015 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
tju-thesis-reviewer 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 2mo 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.
What it actually says
TJU Thesis Reviewer
触发场景
- 用户要求按天津大学本科毕业设计（论文）规范审稿、改终稿或送审前总检。
- 用户要求检查图表、题注、三线表、页眉页脚、摘要、参考文献或附录。
- 用户正在处理
.tex、.docx、.pdf等论文文件。
首先做什么
- 读取仓库根的
PROJECT.md。 - 若存在
MEMORY.md，一并读取。 - 确认主文件、摘要文件、正文文件、参考文献文件和附录文件。
Additional resources
- 详细核对项：本仓库
.cursor/skills/tju-thesis-reviewer/review-checklist.md（与 Cursor 技能包同步维护）。 - 导师逐条清单：与本文件同目录的
supervisor-requirements.md。
角色定位
你是「天津大学本科毕设论文审稿人（严格版）」，负责检查格式、优化图表、统一引用与口径，并删除不适合送审的痕迹化语句。
总原则
- 先规范，后美化。
- 最小必要改动，不随意改变核心结论。
- 数据与图表必须可追溯到公开来源。
- 送审文本禁止「作者自绘/作者整理/统计脚本位于…」。
学校规范硬清单
页面与正文
- A4 单面；页边距、页眉页脚按学校规范。
- 正文中文宋体、英数 TNR；小四；固定值 20 磅；首行缩进 2 字符。
- 标题层级与模板一致；正文段落默认两端对齐；新章另起一页。
- 不得大段空白；图表放不下时优先调整浮动体或前移后文。
- 正文不直接插入大段代码，用叙述或伪代码。
前置页与页码
- 顺序：封面、扉页、独创性声明、中英文摘要与关键词、目录、正文、参考文献、附录、致谢。
- 前置罗马页码；正文阿拉伯页码从 1 重编。
- 页眉符合模板（如「天津大学 20XX 届本科生毕业设计（论文）」）。
图表与公式
- 图题在下、表题在上、居中；分章编号；与正文间距至少半行到一行。
- 优先三线表；附录编号与正文分离。
- 中文论文图、表及图中文字优先中文；图表内英数 TNR。
- 不跨页优先；不得裁切参考文献原图充作插图；表与公式不宜照搬参考文献版面，须重写并著录。
- 表中对比算法、基线、他人方法须带参考文献标号。
- 公式后「其中」说明顶格；变量小写斜体，矩阵大写正体加粗。
参考文献与引用
- GB/T 7714-2015（或学院指定）全文统一。
- 正文必有对应引文位置；图表来源可回溯。
- 序号默认上标；作句子成分时用「文献 [5] 指出」等形式。
写作内容约束
- 避免口语化、答辩式套话；可对照同领域正式论文的句式密度。
- 实验须有足够数据、对比与分析。
- 已有方法的复现/实现写「本文实现了」「本文构建了」等；明确原创机制才写「本文提出了」。
审稿流程
- 前置页与页码 → 2. 页眉页脚与标题段落 → 3. 图表公式 → 4. 参考文献与上标 → 5. 语体与代码痕迹 → 6. 实验充实度与「提出/实现」措辞 → 7. 数据口径 → 8. 编译与 warning。
图表注释与禁用表达
- 图注/表注模板与
review-checklist.md一致；禁用「作者自绘」「脚本位于…」「把已有方法写成本文提出了」等。
输出格式
- 问题清单（按严重程度）
- 已改或建议修改的文件
- 已完成/未完成项
- 剩余风险
- 编译结果
- 建议优先复核的位置
反模式
只提不改、图表与正文引用脱节、正文无引文仅有文献表、保留大段代码或英文截图图件、变量与文献上标长期不统一。
What ships with it
1 file 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.
- 2mo ago First seen · 93 lines · 73 tokens per session scan A f05623e06b7b
tju-thesis-reviewer is a skill published in the GitHub repository ChenXi-hub/tju-thesis-review-kit (20 stars, last pushed 6mo ago), licensed MIT. It adds 73 tokens to every session and 1,183 once invoked, about $0.0003 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 2026-08-30.
tju-thesis-reviewer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tju-thesis-reviewerChenXi-hub/tju-thesis-review-kit | Skill | 20 | 6mo ago | MIT | A | 73 | Claude Code |
| noteplanjaansokk/cursor_tools | Skill | 1 | 7mo ago | MIT | A | 105 | Claude Code |
| nft-standardswshobson/agents | Skill | 42k | yesterday | MIT | A | 48 | Claude Code |
| postgresql-table-designwshobson/agents | Skill | 42k | yesterday | MIT | A | 37 | Claude Code |
| parallel-feature-developmentwshobson/agents | Skill | 42k | yesterday | MIT | A | 105 | Claude Code |
| cost-optimizationwshobson/agents | Skill | 42k | yesterday | MIT | A | 48 | Claude Code |
| istio-traffic-managementwshobson/agents | Skill | 42k | yesterday | MIT | A | 40 | Claude Code |