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 cuic19053-hue/-skills- --skill university_researchgit clone --depth 1 https://github.com/cuic19053-hue/-skills-Wrote 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/cuic19053-hue/-skills-/university_research)<a href="https://agentmods.dev/skills/cuic19053-hue/-skills-/university_research"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/university_research/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/cuic19053-hue/-skills-/university_research"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/university_research.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 | $0.00123 | $0.32500 |
| Opus 5 | $0.00062 | $0.16250 |
| Sonnet 5 | $0.00025 | $0.06500 |
| Haiku 4.5 | $0.00012 | $0.03250 |
Grade A, and why
university_research 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 11d 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 — 2,190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大学生校级科研立项申请书 Skill（v2.1 案例优化版）
本 skill 处理"大学生校级科研立项申请书（SRTP）"全流程：信息采集 → 栏目撰写 → docx 生成 → 质检。仅处理校级（不处理国家级/省级大创，那些走 innovation_research skill）。表格体格式（非书信体），与奖学金类申请书结构不同。
v2.1 案例优化重点：基于真实案例（28 页科研立项案例 1）提炼 12 项撰写规范，新增 8 大必加章节：国家政策引用规范、科学挑战 2 段结构、15+ 文献综述、算法对比表、2 张技术路线图、数学公式规范、社会效益 5 项量化指标、3 档字数版本。
输出文件：可提交的 .docx（A4 纸张，宋体小四正文，黑体三号标题，1.5 倍行距，首行缩进 2 字符，参考文献宋体五号）。
校级科研立项四大特征：经费 25 千（远低于大创 12 万）；周期 1 年（短于大创 12 年）；团队 13 人（小于大创 3~5 人）；必须有规范参考文献（GB/T 7714 格式，≥15 条含 5 篇英文，大创仅简略）。
一、适用场景与触发条件
适用：用户提到"校级科研立项""校科研立项""大学生科研立项""校级课题申报""校级科研课题""学生科研立项""SRTP""大学生科研训练""本科生科研训练"等关键词，且经费 25 千、周期 1 年、团队 13 人、需论文成果。
不适用（走其他 skill）：
- 国家级/省级大创（创新训练）→ 走 innovation_research skill
- 创业训练 / 创业实践 → 走创业类 skill
- 院级科研立项（经费 1~2 千、周期半年）→ 走 college_research skill
- 学科竞赛作品申报（挑战杯/互联网+）→ 走竞赛类 skill
触发后第一步：确认级别为"校级"（非大创体系）。区分要点：大创需教育部高教司立项编号，校级科研立项仅学校科研处编号。若用户混淆"大创"与"科研立项"，追问"是教育部大创项目还是学校科研处立项？"。
校级与院级差异：校级经费 25 千、周期 1 年、要求 1 篇论文；院级经费 12 千、周期半年、要求调研报告即可。若用户实际是院级，告知走 college_research skill。
二、工作流程总览
四阶段串行执行，每阶段完成后再进入下一阶段：
阶段 1 信息采集（10~14 轮对话）：按"通用必采 → 课题专属 → 团队成员 → 指导教师 → 内容素材 → 国家政策 → 科学挑战 → 文献综述 → 算法对比 → 技术路线 → 数学公式 → 社会效益 → 进度 → 参考文献 → 经费预算"顺序采集。每轮不超过 5 个字段。参考文献必须采集 15~20 条（中文 8+ / 英文 5+，覆盖期刊/会议/专著/学位论文/网络资源 5 类）。
阶段 2 内容撰写（一次性产出）：按 22 栏目顺序撰写。国内外研究现状必须评述式（不能简单罗列）。国家政策引用必须按时间倒序排列、含 4 要素。科学挑战采用 2 段结构。算法对比必须含 2~3 方法 × 3 维度。技术路线图必须 2 张。数学公式必须编号 + 变量定义。社会效益必须 5 项量化指标。创新点至少 1 个，用"对比式"写法。预期成果必须可量化，至少 1 篇论文。
阶段 3 docx 生成：调用 python build.py --data data.json --out output.docx 生成 Word 文档。data.json 字段定义见第十一章。
阶段 4 质检：按第十二章 25 项清单逐项检查。参考文献格式检查是校级科研立项的重点（GB/T 7714 五类文献格式必须规范）。
禁止行为：
- 跳过采集直接套模板
- 参考文献写"等""et al."省略作者
- 编造作者/期刊名/年份
- 国内外研究现状简单罗列不评述
- 把大创内容（5 千~2 万预算、2 年周期）混入校级申报书
- 经费预算全整数（如 1000/2000）无计算依据
- 政策文件只列名称不摘录关键表述
- 科学挑战段不分子挑战
- 算法对比表无选型结论
- 技术路线图节点无章节编号对应
- 数学公式无变量定义
三、信息采集清单
3.1 通用必采（10 字段）
| 字段 | 说明 | 示例 | 缺失追问策略 |
|---|---|---|---|
| project_name | 课题名称，≤30 字 | 大学生课堂手机使用行为干预研究 | "课题正式名称？不超过 30 字" |
| leader_name | 负责人姓名 | 张明 | "负责人全名？" |
| leader_id | 学号 | 2022123456 | "学号？" |
| leader_major | 专业 | 教育技术学 | "专业全称？" |
| leader_grade | 年级 | 2022 级 大三 | "入学年份与年级？" |
| leader_phone | 联系电话 | 138XXXXXXXX | "手机号？" |
| college | 学院全称 | 教育学院 | "学院全称？" |
| apply_date | 申报日期 | 2025 年 3 月 15 日 | "申报提交日期？" |
| advisor_name | 指导教师姓名 | 李华教授 | "指导教师全名？" |
| advisor_title | 指导教师职称 | 教授 | "职称？讲师/副教授/教授？" |
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.
- 11d ago First seen · 2,190 lines · 123 tokens per session scan A 8c005fda82ef
university_research is a skill published in the GitHub repository cuic19053-hue/-skills- (10 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 32,500 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.