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 HYYH-code/agent-skills --skill ganggang-xiaohongshu-cardgit clone --depth 1 https://github.com/HYYH-code/agent-skillsWrote 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/hyyh-code/agent-skills/ganggang-xiaohongshu-card)<a href="https://agentmods.dev/skills/hyyh-code/agent-skills/ganggang-xiaohongshu-card"><img src="https://agentmods.dev/badge/skills/hyyh-code/agent-skills/ganggang-xiaohongshu-card/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/hyyh-code/agent-skills/ganggang-xiaohongshu-card"><img src="https://agentmods.dev/badge/skills/hyyh-code/agent-skills/ganggang-xiaohongshu-card.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 | $0.00084 | $0.02263 |
| Opus 5 | $0.00042 | $0.01131 |
| Sonnet 5 | $0.00017 | $0.00453 |
| Haiku 4.5 | $0.00008 | $0.00226 |
Grade A, and why
ganggang-xiaohongshu-card 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
刚刚风格小红书卡片 Skill
把一篇 AI / 科技新闻整理成一组可连续滑动阅读的小红书长图卡片，或根据参考图反推同款版式。这里的“刚刚风格”指本项目素材中观察到的视觉系统，不要求复制具体账号水印、真实 logo 或原文排版。
适用请求
- “做一组刚刚风格的小红书卡片”
- “把这篇 AI 新闻排成刚刚风格”
- “根据这几张图反推一个卡片 skill”
- “生成封面、正文页、证据页和总结页”
不把这个 skill 用于普通营销海报、纯图片提示词反推、横版 PPT 或长文排版；这些任务应使用更匹配的工具或 skill。
核心结果
交付一组统一的中文信息卡片方案，至少包含：
- 先完成
card-plan：每页阅读任务、标题、正文、证据、重点高亮；以 templates/card-plan.yaml 为模板。 - 页面类型：
cover、event-confirmation、core-capability、comparison、impact-closing；有证据时加入evidence-screenshot。 - 每页完整文案与版式说明，不能用“略”或省略号代替正文。
- 统一视觉 token、封面主题、画布比例、内容密度、组件位置和移动端可读性检查结果。
- 如用户要求生成图片，使用 HTML/CSS 排版并在生成后检查尺寸、文字溢出、层级、留白和系列一致性。
工作流
1. 先判断内容结构
先提炼一条新闻主线：发生了什么、证据在哪里、它具体强在哪里、对象之间是什么关系、影响是什么。把素材分成 4–7 个逻辑阶段，不为填满页数而硬拆句子。
默认分页顺序：
- 封面：品牌/产品或事件 + 冲击性结论。
- 事件确认：时间或场景、核心对象和 2–4 条事实。
- 核心能力：只讲一个主题，最多 3 个能力点。
- 对比/关系：明确比较维度，区分主对象和陪衬对象。
- 影响与结论：1 个核心判断、2–3 条影响和最后一句记忆点。
如果内容更短，可以合并页面；如果内容更长，优先增加同一模板的正文页，不改变视觉系统。
在写 HTML 前，把每页的 page_type、reading_question、claim、supporting_facts、visual_modules 与 evidence 写入 card-plan。证据必须标注为用户提供的原始材料、结构化整理，或编辑判断；不要把结构化整理伪装成来源截图。
2. 设置生成参数
每次生成前先读取 references/input-contract.yaml，再确定以下参数：
{
coverStyle: "auto",
colorTheme: "violet-tech",
ratio: "3:4",
density: "balanced",
pageCount: "auto"
}
参数规则：
coverStyle：auto、breaking-type、product-symbol、technical-event、original-big-type。colorTheme：violet-tech、signal-red、electric-blue、acid-green、warm-orange。ratio：3:4、4:5、9:16；默认3:4。density：compact、balanced、airy；正文默认balanced，封面和收束页可用airy。pageCount：根据内容自动确定，通常为 4–7 页。
如果用户没有指定参数，按事件类型自动选择：
- 泄露、突发、重磅：
breaking-type+signal-red - 硬件、具体产品、界面：
product-symbol+violet-tech - 芯片、架构、模型组合：
technical-event+electric-blue - 无明确视觉对象或需要做封面测试：
original-big-type+violet-tech
3. 选择页面模板
阅读 references/page-types.md，按内容启用组件。不要让所有页面都强行放日期、截图、编号或小节标题。
封面可从以下四类方向中选择，也可以并行生成供比较：
What ships with it
9 files 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.
- agents/openai.yaml 464 B
- references/input-contract.yaml 1.1 KB
- references/page-types.md 3.3 KB
- references/reverse-findings.md 4.2 KB
- references/visual-system.md 4.2 KB
- scripts/export-cards.mjs 1.3 KB runs code
- scripts/validate-cards.mjs 2.9 KB runs code
- skill-ir.yaml 1.8 KB
- templates/card-plan.yaml 1.1 KB
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 · 134 lines · 84 tokens per session scan A 9d3ffe67eedb
ganggang-xiaohongshu-card is a skill published in the GitHub repository HYYH-code/agent-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 84 tokens to every session and 2,263 once invoked, about $0.0004 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…