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-/innovation_research)<a href="https://agentmods.dev/skills/cuic19053-hue/-skills-/innovation_research"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/innovation_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-/innovation_research"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/innovation_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 | $0.00115 | $0.35807 |
| Opus 5 | $0.00057 | $0.17903 |
| Sonnet 5 | $0.00023 | $0.07161 |
| Haiku 4.5 | $0.00012 | $0.03581 |
Grade A, and why
innovation_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 — 1,965 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大创-创新训练项目申报书 Skill（v3.0 案例优化版）
本 skill 处理"大学生创新创业训练计划-创新训练项目"申报书全流程：信息采集 → 栏目撰写 → docx 生成 → 质检。仅处理"创新训练"子类（学术研究型），创业训练/创业实践请走创业类 skill。
v3.0 升级要点：基于真实案例（消防无人机多模态融合移动目标定位与跟踪 28 页科研立项申报书）优化，新增 10 大章节规范（国家政策引用 / 科学挑战 3 段结构 / ≥30 篇文献综述 / 算法对比表 / 技术路线图 / 数学公式 / 社会经济效益量化 / 进度安排 / 三档字数版本 / JSON Schema），输出可匹敌真实国家级科研申报书的深度。
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）。
一、适用场景与触发条件
适用：用户提到"大创""创新训练项目""大学生创新创业训练计划""国家级/省级/校级大创申报书""创新训练项目申报"等关键词，且项目产出为论文/研究报告/原型系统（非商业计划书）。
不适用（需走其他 skill）：
- 创业训练项目（产出商业计划书）→ 走创业训练 skill
- 创业实践项目（已注册公司运营）→ 走创业实践 skill
- 校级科研立项（非大创体系）→ 走科研立项 skill
- 学科竞赛立项 → 走竞赛立项 skill
触发后第一步：确认项目类型为"创新训练"（非创业训练/创业实践）。若用户未明确，按创新训练处理并告知。
触发后第二步：确认项目级别（国家级/省级/校级），不同级别字数、经费、周期要求差异显著：
- 国家级：1.5 万字 / 经费 1~2 万 / 周期 24 个月 / 至少 2 个创新点 / 至少 30 篇文献
- 省级：1 万字 / 经费 5 千~1 万 / 周期 18 个月 / 至少 2 个创新点 / 至少 20 篇文献
- 校级：6 千字 / 经费 2~3 千 / 周期 12 个月 / 至少 1 个创新点 / 至少 10 篇文献
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（10~15 轮对话）： 按"通用必采 → 项目专属 → 团队成员 → 指导教师 → 内容素材 → 案例专属 8 字段 → 经费预算"顺序采集。每轮不超过 5 个字段。关键缺失字段必须追问，禁止编造。
阶段 2 内容撰写（一次性产出）： 按 12 栏目 + 10 大案例规范章节顺序撰写。每栏目字数严格控制在规范区间。创新点用"对比式"写法，预期成果必须可量化。
阶段 3 docx 生成：
调用 python build.py --data data.json --out output.docx 生成 Word 文档。data.json 字段定义见第十二章。新增 8 个案例专属字段（policy_citations / scientific_challenges / literature_review / algorithm_comparison / tech_roadmap / formulas / economic_benefits / project_schedule）。
阶段 4 质检： 按第十三章 30 项清单逐项检查（v2.0 15 项 + v3.0 新增 15 项案例规范检查）。任何一项不达标返回阶段 2 修改。
禁止行为：
- 跳过采集直接套模板
- 用"若干""一定""相关"等模糊词
- 编造数据/作者/期刊名
- 把创业训练的内容混入创新训练申报书
- 文献数 < 30 篇（国家级）/ < 20 篇（省级）/ < 10 篇（校级）
- 政策引用不按时间倒序、缺发文机关、缺关键表述摘录
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 | 项目名称，≤25 字 | 多模态融合的无人机消防目标检测系统 | "项目正式名称是什么？不超过 25 字" |
| project_level | 级别 | 国家级/省级/校级 | "申报哪个级别？" |
| leader_name | 负责人姓名 | 张三 | "项目负责人全名？" |
| leader_id | 负责人学号 | 202212345 | "学号？" |
| leader_major | 负责人专业 | 自动化 | "专业全称？" |
| leader_grade | 负责人年级 | 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 | 自动化工程学院 | "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 | 李教授 | "指导教师全名？" |
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 · 1,965 lines · 115 tokens per session scan A b3b52823c38a
innovation_research is a skill published in the GitHub repository cuic19053-hue/-skills- (10 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 35,807 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.