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 graduate_recommendationgit 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-/graduate_recommendation)<a href="https://agentmods.dev/skills/cuic19053-hue/-skills-/graduate_recommendation"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/graduate_recommendation/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-/graduate_recommendation"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/graduate_recommendation.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 | $0.00093 | $0.13350 |
| Opus 5 | $0.00046 | $0.06675 |
| Sonnet 5 | $0.00019 | $0.02670 |
| Haiku 4.5 | $0.00009 | $0.01335 |
Grade A, and why
graduate_recommendation 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 — 966 lines — stays where its author put it; the contents beside it link to each section on GitHub.
保研推免申请书 SKILL
一、适用场景与触发条件
本 skill 用于生成保研推免申请书，适用范围：
- 大三学生申请外校或本校研究生推免资格
- 夏令营（5
7 月）、预推免（89 月）、九推（9 月底~10 月）三种渠道任一 - 申请方向为学术型硕士、专业型硕士、直博
保研推免 vs 考研：
| 维度 | 保研推免 | 考研 |
|---|---|---|
| 入口 | 本校推免资格 + 目标院校接收 | 全国统考 |
| 时间线 | 大三下至大四上 | 大四上 12 月统考 |
| 材料重点 | 学业 + 科研 + 匹配度 | 初试分数 + 复试表现 |
| 申请书性质 | 自荐材料 + 个人陈述 | 复试简历 |
| 评审节奏 | 短时间多投递，匹配度优先 | 一校一志愿 |
三种渠道差异：
| 渠道 | 时间 | 录取概率 | 材料侧重点 |
|---|---|---|---|
| 夏令营 | 5~7 月 | 高（优营基本直录） | 学业 + 科研潜力 |
| 预推免 | 8~9 月 | 中 | 学业 + 科研成果 + 匹配度 |
| 九推 | 9.28~10.20 | 低（捡漏为主） | 已有 offer + 应急材料 |
触发条件：用户提到"保研""推免""夏令营申请""预推免""九推""研究生推免""保研申请书""保研个人陈述"任一关键词时激活。
不触发：用户明确说"考研报名表""研究生复试简历"——属其他 skill 范围。
二、工作流程总览
四阶段流程，禁止跳步：
阶段 1：信息采集（30~50 分钟） 按第四节"信息采集清单"分批采集，先采学业硬指标，再采科研软实力，最后采申请信息与推荐信。每采完一类即复述确认。
阶段 2：栏目内容撰写（60~90 分钟） 按栏目顺序撰写：基本信息 → 学业情况 → 科研经历 → 个人陈述 → 推荐信情况 → 附件清单。个人陈述与科研经历为重点，需单独校对。
阶段 3：docx 生成（5 分钟） 调用 build.py 生成 docx，自动应用统一格式标准。生成后由用户人工补充签字、盖章。
阶段 4：质检与提交（15 分钟） 按第十二节"质检清单"逐项核对，确认无缺失字段、无禁用句、附件齐全后提交。
禁止行为：
- 不替用户编造数据（GPA、排名、论文级别必须真实）
- 不套用网络模板（个人陈述一旦套用直接淘汰）
- 不省略推荐信情况栏（即使推荐信未寄出也要写明推荐人信息）
- 不在科研经历栏只写"参与"（必须含角色与产出）
- 不长篇大论家庭背景（除非与研究方向直接相关）
三、信息采集清单
3.1 学业硬指标（必采）
| 字段 | 说明 | 示例 |
|---|---|---|
| gpa_6sem | 前 6 学期 GPA（含分母） | 3.92/4.0 |
| weighted_avg | 加权平均分 | 91.5/100 |
| rank | 专业排名（X/N） | 1/87 |
| rank_percent | 排名百分比 | 前 1.1% |
| main_courses | 主修课程（含学期/学分/成绩） | 数组 |
| scholarships | 奖学金（时间/名称/级别） | 数组 |
| cet4 | CET-4 成绩 | 580 |
| cet6 | CET-6 成绩 | 580 |
| toefl | TOEFL 成绩（如有） | 105 |
| ielts | IELTS 成绩（如有） | 7.5 |
| recommend_qualified | 是否已取得本校推免资格 | 是/否 |
追问话术：
- "你前 6 学期 GPA 是多少？分母是 4.0 还是 5.0？"
- "专业排名 X/N，N 是专业总人数还是同年级人数？"
- "CET-6 考了几次？最高分多少？"
- "奖学金请按时间倒序列出，注明级别（国家/省/校/院）"
3.2 科研软实力（必采）
论文（每篇）：
- title 题目
- journal 期刊或会议全称
- level 级别（SCI 一区/二区/EI/CCF-A/B/C/中文核心/普通）
- author_order 作者排序（1/2/3...）
- status 状态（已发表/已录用/在审/已投）
- publish_date 发表或录用时间
专利（每项）：
- name 专利名称
- type 类型（发明/实用新型/外观）
- apply_no 申请号
- status 状态（已授权/实质审查/已公开/已受理）
- inventor_order 发明人排序
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 · 966 lines · 93 tokens per session scan A cc99721cbc50
graduate_recommendation is a skill published in the GitHub repository cuic19053-hue/-skills- (10 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 13,350 once invoked, about $0.0005 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
stage-dsl
The map for reading and editing an OpenMAIC stage document with readstage, patchstage, and grepstage. Load it before patching a structure you have not patched before, when patchstage rejects an operation, or whenever the path from a stage, outline, scene, content object, or action to the field you need is uncertain.…
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.
dev-camp-deck
Creates a professional PowerPoint presentation about a Copilot Dev Camp lab or topic. Researches Microsoft Learn documentation, organizes content into a slide structure, and generates a polished deck with speaker notes. Use when user asks to "create a presentation on", "make a deck about", "build a slideshow for"…
read-book
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to…
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
training-report
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training report", "workshop report", "compte rendu", "compte rendu de formation", "formation report", "debriefing a workshop", "write up a training session", "résumé de formation", or any request to document a…