Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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-/exchange_program)<a href="https://agentmods.dev/skills/cuic19053-hue/-skills-/exchange_program"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/exchange_program.svg" alt="Measured on agentmods" 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 | $0.00223 | $0.26788 |
| Opus 5 | $0.00112 | $0.13394 |
| Sonnet 5 | $0.00045 | $0.05358 |
| Haiku 4.5 | $0.00022 | $0.02679 |
Grade A, and why
exchange_program 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 6d 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 — 1,392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
交流项目申请书 SKILL
§0 适用场景与三渠道分流
0.1 本 skill 的适用范围
- 在校本科生(少数项目含研究生)申请学期/学年交换项目
- 校际交换、院际交换、CSC 公派留学三类项目任一
- 目标院校为境外(含港澳台)正规高校,含联合培养/双学位/3+1/2+2/学期交换/暑期学校等模式
- 涵盖纸质邮寄、电子上传、系统填报三类提交方式
0.2 交流项目 vs 留学申请
| 维度 | 交流项目(本 skill) | 出国留学 PS/SOP |
|---|---|---|
| 申请阶段 | 本科在校期间(学籍保留在本校) | 本科毕业申请研究生 |
| 学籍归属 | 学籍保留本校,交流期满回本校 | 学籍转入目标院校 |
| 学位授予 | 不授目标院校学位(少数双学位项目除外) | 授目标院校学位 |
| 语言 | 多为中文申请书 + 英文成绩单 | 全英文 SOP/PS |
| 字数 | 1500~2500 字(中文) | 500~1000 字(英文) |
| 评审重点 | 学业 + 交流动机 + 学习计划 + 文化交流 + 安全 | 学术潜力 + 研究方向匹配 |
| 资金来源 | 校际协议免除学费 / CSC 资助 / 自费 | 自费 / 学校全奖 / CSC |
0.3 三渠道分流决策
申请人应根据自身学业水平、外语成绩与目标方向选择合适渠道:
| 渠道 | 时间窗 | 选拔概率 | 申请人定位 |
|---|---|---|---|
| 校际交换 | 每年 3 |
中(按学业排名择优) | 学业前 20% + 语言达标 + 对方院校有合作 |
| 院际交换 | 每年 3~5 月(学院合作项目分散选拔) | 较高(院系推荐 + 简化程序) | 学业前 30% + 院系认可 |
| CSC 公派 | 每年 1~3 月(国家留学基金委统一选拔) | 较低(全国竞争 + 严格评审) | 学业前 5% + 语言达标 + 有科研潜力 |
渠道选择建议:
- 学业硬指标强(GPA 前 5%)+ 语言达标(雅思 6.5+/托福 90+)+ 顶校合作:优先校际交换冲 QS 前 50
- 学业合格(前 20%)+ 语言达标 + 想体验海外学习:选院际交换冲目标院校
- 学业突出(前 5%)+ 有科研论文 + 想读博深造:CSC 公派冲 QS 前 30
- 自费预算充足 + 灵活时间:选暑期学校或短期项目(4~8 周)
0.4 触发条件与不触发场景
触发条件:用户提到"交流项目""学期交换""学年交换""校际交流""院际交流""出境交流""海外交流""交换生""交换生申请""交流项目申请""CSC 公派""国家公派""短期交流""暑期学校""暑期课程""海外学习""联合培养""双学位项目""3+1 项目""2+2 项目""学期项目""访学""访学申请"等任一关键词时激活。
不触发:
- 用户明确说"出国留学申请 PS"——属英文留学文书 skill
- 用户明确说"考研报名表"——属考研 skill
- 用户明确说"保研推免"——属 graduate_recommendation skill
- 用户明确说"研究生复试简历"——属复试 skill
- 用户明确说"实习申请"——属实习 skill
0.5 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 §5 信息采集清单分批采集,先采学业硬指标,再采交流项目信息,最后采学习计划与文化交流意愿。每采完一类即复述确认。
阶段 2:栏目内容撰写(60~90 分钟) 按 §2 五段结构 + §3 4 维度动机 + §4 3 阶段学习计划撰写。重点:交流动机(按 §3 4 维度)、学习计划(按 §4 3 阶段)。
阶段 3:docx 生成(5 分钟) 按 §13 build.py 接口生成 docx,按 §14 质检清单逐项排查。
阶段 4:用户复核与提交(10~20 分钟) 用户复核后修改提交。
§1 交流项目 3 类对照表(必加章节 1)
1.1 3 类交流项目对照表
| 维度 | 校际交换 | 院际交换 | CSC 公派 |
|---|---|---|---|
| 面向人群 | 全校本科生(部分含研究生) | 院系内本科生 | 全国高校在校生 |
| 申请门槛 | GPA 前 20% + 雅思 6.0+/托福 80+ | GPA 前 30% + 雅思 6.0+ | GPA 前 5% + 雅思 6.5+/托福 95+ |
| 时长 | 1 学期或 1 学年(4~10 个月) | 1 学期或 1 学年 | 6~24 个月(含联合培养博士) |
| 费用 | 学费互免 + 自付生活费(约 5~15 万) | 学费互免或减免 + 自付生活费 | CSC 全额资助(含学费+生活费+往返机票) |
| 学分转换 | 经本校教务认定可转换学分 | 经本院教务认定可转换 | 需双方导师共同制定学习计划 |
| 申请材料 | 申请书 + 成绩单 + 语言证书 + 推荐信 1~2 封 | 申请书 + 成绩单 + 语言证书 | 申请书 + 学习计划 + 推荐信 2~3 封 + 研究计划 |
| 选拔流程 | 学校初审 + 目标院校复审 | 院系推荐 + 学校备案 | 学校推荐 + CSC 全国评审 |
| 评审侧重 | 学业 + 交流动机 + 学习计划 | 学业 + 院系适配度 | 学业 + 科研潜力 + 国家需求匹配 |
| 录取结果 | 通知本校国际处 + 个人邮箱 | 通知本院外事秘书 | CSC 公示 + 学校国际处通知 |
| 学位授予 | 不授学位(仅成绩单) | 不授学位(仅成绩单) | 联合培养博士可授双方学位 |
| 回国义务 | 无强制回国义务 | 无强制回国义务 | 必须回国服务 2 年(CSC 协议) |
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.
- 6d ago First seen · 1,392 lines · 223 tokens per session scan A 5970d183a562
exchange_program is a skill published in the GitHub repository cuic19053-hue/-skills- (10 stars, last pushed 1mo ago), licensed MIT. It adds 223 tokens to every session and 26,788 once invoked, about $0.0011 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
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".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
habit-formation
Atomic habits, cue-routine-reward loops, habit stacking, accountability systems, and behavior change.