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 entrepreneurship_traininggit 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-/entrepreneurship_training)<a href="https://agentmods.dev/skills/cuic19053-hue/-skills-/entrepreneurship_training"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/entrepreneurship_training/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-/entrepreneurship_training"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/entrepreneurship_training.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 | $0.00183 | $0.34749 |
| Opus 5 | $0.00092 | $0.17375 |
| Sonnet 5 | $0.00037 | $0.06950 |
| Haiku 4.5 | $0.00018 | $0.03475 |
Grade A, and why
entrepreneurship_training 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 12d 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 — 2,083 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大创-创业训练项目申报书 Skill（v2.1，对齐案例 2 79 页范本）
本 skill 处理"大学生创新创业训练计划-创业训练项目"申报书全流程：信息采集 → 11 章内容撰写 → docx 生成 → 质检。仅处理"创业训练"子类（商业计划书型 + 技术研发型），不要求实际注册公司；区别于创新训练（学术研究型）与创业实践（实际运营型）。
v2.1 升级要点：基于河南工业大学姚奕晗《基于多模态融合与三维重构的消防无人机火场救援系统》（校级大创创业训练，79 页）案例 2 的真实结构，全面补强技术深度与商业完整度。案例 2 同时具备"科研立项的技术深度（科学挑战+文献综述+算法公式+技术路线图）"和"创业训练的商业完整度（4P+3C+SWOT+5 年三表+实践过程+技术壁垒）"，是创业训练申报书的最佳范本。
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），目标页数 30~80 页。
一、适用场景与触发条件
1.1 适用项目特征
用户提到"大创""创业训练项目""大学生创业训练""国家级/省级/校级创业训练申报书"等关键词，且项目产出为商业计划书 + 模拟运营报告 + 路演材料 + 技术研发报告（非单纯学术论文、非已注册公司报表）。
核心识别要点：
- 不要求实际注册公司（与创业实践区别）
- 含技术方案/算法设计/数学公式（与创新训练部分重叠，但创业训练强调商业落地）
- 含完整商业部分（4P/3C/SWOT/5 年三表，与创新训练区别）
- 含实践过程与实地考察（与纯理论研究区别）
1.2 不适用（走其他 skill）
| 不适用情形 | 走哪个 skill | 区别要点 |
|---|---|---|
| 创新训练项目 | innovation_training | 产出论文/研究报告，无商业部分 |
| 创业实践项目（已注册公司或运营 6 个月以上） | entrepreneurship_practice | 有真实营收、股权、工商注册号 |
| "互联网+"大赛、挑战杯创业赛道 | internet_plus / challenge_cup | 赛事申报书格式不同 |
| 校级科研立项 | college_research | 纯学术研究，无商业计划 |
1.3 触发后第一步
确认项目类型为"创业训练"。区分要点：
- 创新训练：偏学术，研究方法/视角创新，产出论文，无商业部分
- 创业训练：偏商业 + 技术研发，商业模式/产品形态创新，产出商业计划书 + 技术方案，不要求实际注册公司
- 创业实践：已注册公司或运营 6 个月以上，有真实营收数据
用户未明确时，按"是否要注册公司"区分——要注册走创业实践，不注册走创业训练。
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。
2.1 阶段 1：信息采集（18~25 轮对话）
按"通用必采 → 项目简介与优势 → 政策与文献 → 科学挑战 → 技术方案 → 商业模式 → 财务预测 → 实践过程 → 技术壁垒 → 进度与成果"顺序采集。每轮不超过 5 个字段。商业字段（TAM/SAM/SOM、CAC/LTV、定价、毛利、5 年三表）和技术字段（算法名称/数学公式/技术路线图）缺失必须追问，禁止编造市场数据或算法细节。
2.2 阶段 2：内容撰写（一次性产出）
按 11 大章顺序撰写，每章字数按 3 档版本控制（见 §10）：
- 国家级：总字数 ≥ 30000，含全部 11 章 + 30 篇文献 + 5 年三表 10 张
- 省级：总字数 ≥ 20000，含 11 章 + 20 篇文献 + 5 年三表 6 张
- 校级：总字数 ≥ 15000，含 11 章 + 10 篇文献 + 5 年三表 4 张
技术部分必须含数学公式（每个核心算法 ≥ 1 公式）、算法对比表（≥ 3 算法 × ≥ 4 维度）、技术路线图（≥ 3 张）。 商业部分必须含 4P（产品/价格/渠道/促销）+ 3C 定价 + SWOT + 5 年三表（销售/成本/管理/销售费用/现金流/NPV/盈利能力/资产负债/短期偿债/长期偿债 共 10 张表）。
2.3 阶段 3：docx 生成
调用 python build.py --data data.json --out output.docx 生成 Word 文档。data.json 字段定义见第七章 JSON Schema。
2.4 阶段 4：质检
按第十一章 30 项质检清单逐项检查。任何一项不达标返回阶段 2 修改。
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.
- 12d ago First seen · 2,083 lines · 183 tokens per session scan A 8c6cb044be73
entrepreneurship_training is a skill published in the GitHub repository cuic19053-hue/-skills- (10 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 34,749 once invoked, about $0.0009 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.