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 college_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-/college_research)<a href="https://agentmods.dev/skills/cuic19053-hue/-skills-/college_research"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/college_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-/college_research"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/college_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 | $0.00166 | $0.31166 |
| Opus 5 | $0.00083 | $0.15583 |
| Sonnet 5 | $0.00033 | $0.06233 |
| Haiku 4.5 | $0.00017 | $0.03117 |
Grade A, and why
college_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 — 1,760 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大学生院级科研立项申请书 Skill（v2.1 案例优化版）
本 skill 处理"大学生院级科研立项申请书"全流程：信息采集 → 9 项强化章节撰写 → 16 栏目 docx 生成 → 质检。仅处理院级（不处理国家级/省级大创，也不处理校级科研立项）。表格体格式（非书信体），与奖学金类申请书结构不同。
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）。
院级科研立项核心特征（v2.1 调整）
院级科研立项比校级更轻量：
| 维度 | 院级（本 skill） | 校级（university_research） | 国家级大创（innovation_research） |
|---|---|---|---|
| 经费 | 500~2000 元 | 2~5 千元 | 5 千~2 万元 |
| 周期 | 3~6 个月 | 6~12 个月 | 12~24 个月 |
| 团队 | 1~2 人 | 1~3 人 | 3~5 人 |
| 主要产出 | 调研报告（≥1 份） | 论文 1 篇或报告 1 份 | 论文 1~2 篇 + 专利/软件 |
| 文献要求 | ≥5 条覆盖 ≥3 类，含 3 篇英文 | ≥8 条覆盖 ≥5 类 | ≥15 条覆盖 ≥5 类 |
| 评审组织 | 学院科研办 | 学校科研处 | 教育部/省教育厅 |
| 评审专家 | 本院老师 2~3 人 | 校内跨学院 3~5 人 | 校外专家 3~5 人 |
| 通过率 | 60~80% | 50~70% | 30~50% |
| 录取线 | 70+ 分 | 75+ 分 | 80+ 分 |
v2.1 新增：基于案例 1（科研立项简化版）的 9 项强化章节，使院级申报书在轻量化基础上达到评审高分标准。
一、适用场景与触发条件
适用：用户提到"院级科研立项""院科研立项""学院科研立项""院级课题申报""院级科研课题""院级立项申请书""学院立项"等关键词，且经费 5002000 元、周期 36 个月、团队 1~2 人、需论文或调研报告成果。
不适用（走其他 skill）：
- 国家级/省级大创（创新训练）→ 走 innovation_research skill
- 校级科研立项（经费 2
5 千、周期 612 个月、团队 1~3 人）→ 走 university_research skill - 创业训练 / 创业实践 → 走创业类 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"院级"（非大创、非校级）。区分要点：大创需教育部高教司立项编号；校级科研立项由学校科研处编号；院级科研立项由学院教学办或科研办编号，经费显著更低、周期更短。若用户混淆"科研立项"与"大创"，追问"是教育部大创项目、学校科研处立项，还是学院科研办立项？经费大概多少？周期多长？"。
院级与校级差异：校级经费 25 千、周期 612 个月、要求 1 篇论文、评审由学校科研处组织；院级经费 5002000 元、周期 36 个月、要求 1 份调研报告或 1 篇论文、评审由学院组织本院老师。若用户实际是校级，告知走 university_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（5~8 轮对话）：按"通用必采 → 课题专属 → 团队成员 → 指导教师 → 内容素材 → 参考文献 → 9 项强化字段"顺序采集。每轮不超过 5 个字段。比校级采集轮次少 2~3 轮（院级字数要求低，素材量也小）。新增 7 个强化字段（policy_citations / scientific_challenges / literature_review / method_comparison / tech_roadmap / formulas / social_benefits）的采集，每个字段单独一轮或合并采集。
阶段 2 内容撰写（一次性产出）：按 16 栏目 + 9 项强化章节顺序撰写。国内外研究现状必须评述式（不能简单罗列）。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 篇论文或 1 份调研报告。撰写时严格按院级字数规范（详见第五章），不套用校级字数。参考文献编号与正文引用一一对应。
阶段 3 docx 生成：调用 python build.py --data data.json --out output.docx 生成 Word 文档。data.json 字段定义见第十七章。生成时 build.py 自动校验院级硬上限：经费 ≤2000 元、团队 ≤2 人、周期 ≤6 个月、参考文献 ≥5 条覆盖 ≥3 类含 3 篇英文、政策引用 ≥3 条、文献综述 ≥10 条、科学挑战 1~2 个、方法对比表 ≥2 方法×3 维度、社会效益 ≥3 项、进度 ≥4 阶段。超限触发警告但不阻断生成，需用户确认后提交。
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 · 1,760 lines · 166 tokens per session scan A 262ecddc3eaa
college_research is a skill published in the GitHub repository cuic19053-hue/-skills- (10 stars, last pushed 1mo ago), licensed MIT. It adds 166 tokens to every session and 31,166 once invoked, about $0.0008 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.