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 internet_plusgit 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-/internet_plus)<a href="https://agentmods.dev/skills/cuic19053-hue/-skills-/internet_plus"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/internet_plus/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-/internet_plus"><img src="https://agentmods.dev/badge/skills/cuic19053-hue/-skills-/internet_plus.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 | $0.00203 | $0.30010 |
| Opus 5 | $0.00102 | $0.15005 |
| Sonnet 5 | $0.00041 | $0.06002 |
| Haiku 4.5 | $0.00020 | $0.03001 |
Grade A, and why
internet_plus 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 9d 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 — 2,215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
互联网+大学生创新创业大赛商业计划书 Skill v2.1
本 skill 处理"互联网+大学生创新创业大赛"（即"中国国际大学生创新大赛"）商业计划书（BP）全流程：信息采集 → 11 大栏目撰写 → 案例化 11 项必加章节填充 → docx 生成 → 质检。仅处理商业计划书型（非学术作品、非调研报告、非论文）；与挑战杯创业计划赛道、大创创业训练差异见第十九章。
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，含商业模式画布 9 宫格、5 年财务三表、社会经济效益量化表、4 维度评审对应章节、技术路线图说明）。
2025 起评审维度变化：往年"创新性 + 商业性 + 团队 + 社会价值"四维，2025 起改为个人成长 30% + 项目创新 30% + 产业价值 25% + 团队协作 15%，最显著变化是"个人成长"权重 30% 跃居首位——BP 必须突出"学生本人学到了什么、改变了什么"，不只是项目本身；同时"项目创新"30% 要求 BP 必须有技术深度支撑（科学挑战、算法对比、技术路线、数学公式），而非纯商业描述。
v2.1 升级要点（基于真实案例 case2 优化）：
- 新增国家政策引用规范（10+ 文件，按时间倒序，含发文机关+文号+标题+时间+关键表述）
- 新增科学挑战 3 段结构（数据→算法→系统 / 感知→认知→决策层层递进）
- 新增国内外研究现状综述（30+ 文献，英文 ≥60%，含 SCI 一区/二区）
- 新增算法对比表（≥3 维度对比 + 选型结论）
- 新增 3 张技术路线图（研究内容关系图 + 研究方法图 + 技术路线图）
- 新增数学公式规范（每个核心算法含公式+变量定义+编号）
- 新增社会经济效益量化（12 项指标，传统 vs 系统 4 列对比）
- 新增 4 维度评审对应章节（个人成长 3 段/项目创新 3 套/产业价值 4 维度/团队协作 4 维度）
- 新增完整商业部分（4P + 3C + SWOT + 5 年三表）
- 新增实践过程章节 + 技术壁垒章节
- 新增 JSON Schema + build.py 接口 + 3 档字数版本 + 质检清单
重要纠偏：v1.x 版本"坑 10：把学术研究内容混入 BP"是错误指导。案例 case2（已获省赛金奖）证明：2025 互联网+ "项目创新 30%"维度必须有技术深度支撑，BP 含科学挑战、文献综述、算法对比、技术路线、数学公式不是"学术内容混入"，而是"项目创新 30%"维度的核心得分点。但需注意：技术内容必须服务商业叙事，不能写成纯学术论文。
一、适用场景与触发条件
适用：用户提到"互联网+""互联网+大赛""高教主赛道""红色之旅""职教赛道""互联网+商业计划书""中国国际大学生创新大赛"等关键词，且需提交"商业计划书"形态文档（非学术论文、非调研报告）。
不适用（走其他 skill）：
- 挑战杯课外学术科技作品（论文/调查报告/发明实物）→ 走挑战杯 skill
- 大创-创业训练项目（教学项目，非参赛）→ 走创业训练 skill
- 大创-创业实践（已注册公司但非参赛）→ 走创业实践 skill
- 创青春创业大赛（团中央主办）→ 走创业训练 skill（结构相近）
三大赛道区分：
| 赛道 | 适用对象 | 评审侧重 | 特色要求 |
|---|---|---|---|
| 高教主赛道 | 本科生/研究生 | 创新 + 商业 + 成长 | 项目创新性与商业化潜力，含技术深度 |
| 红色之旅 | 全体在校生 | 红色基因 + 乡村振兴 | 必含老区/乡村帮扶成效 + 红色教育 |
| 职教赛道 | 高职/中职生 | 技能 + 就业 + 落地 | 强调技术技能与岗位对接 |
触发后第一步：先确认赛道（三选一）。用户未明确时问"你报哪个赛道？高教主赛道/红色之旅/职教赛道，分别对应本科生、红色主题、职教生"。赛道确认后才能定调。
触发后第二步：确认项目是否含技术深度（算法/硬件/系统）。如含技术，必须启用第 5~10 章（国家政策/科学挑战/文献综述/算法对比/技术路线/数学公式）；如纯商业模式创新项目（如纯互联网产品），可省略数学公式章节，但其他必加。
二、工作流程总览
六阶段串行执行，每阶段完成后再进入下一阶段：
阶段 1 信息采集（15~22 轮对话）：按"通用必采 → 赛道专属 → 项目/市场/产品 → 商业模式 → 运营现状 → 财务预测 → 融资计划 → 团队 → 风险 → 个人成长素材 → 政策文件 → 技术深度（科学挑战/文献/算法/公式）→ 实践过程 → 技术壁垒 → 社会效益"顺序采集。每轮不超过 5 个字段。商业字段（TAM/SAM/SOM、CAC/LTV、定价、毛利率）+ 政策文件 + 技术深度字段缺失必须追问，禁止编造市场数据、政策文件名、文献引用。
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.
- 9d ago First seen · 2,215 lines · 203 tokens per session scan A 33ba5b9b7338
internet_plus is a skill published in the GitHub repository cuic19053-hue/-skills- (10 stars, last pushed 1mo ago), licensed MIT. It adds 203 tokens to every session and 30,010 once invoked, about $0.0010 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
behuman
"BeHuman" intends to assist AI in thinking and writing like a human statistically using the novel Penta-State Probabilistic Model.
ios-hig-pro-max
Apple ecosystem experience architect skill for SwiftUI development. Invoke this skill whenever the user wants to build, design, review, or polish ANY iOS/iPadOS/macOS interface using SwiftUI — even if they just say "make a screen", "write a SwiftUI view", "help with my app UI", "build an iOS feature", or name any app…
global-collaboration-rules
Universal collaboration rules for AI coding agents. Covers output standards, token optimization (90% cache hit, 98% tool output reduction), requirements locking with anti-drift checks, context compression (9-section CC template at 85%), skill borrowing workflow, image fallback without vision models, code comment…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…