Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/card-xiaohongshuWrote 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/zju-real/easel/card-xiaohongshu)<a href="https://agentmods.dev/skills/zju-real/easel/card-xiaohongshu"><img src="https://agentmods.dev/badge/skills/zju-real/easel/card-xiaohongshu/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/zju-real/easel/card-xiaohongshu"><img src="https://agentmods.dev/badge/skills/zju-real/easel/card-xiaohongshu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.01586 |
| Opus 5 | $0.00048 | $0.00793 |
| Sonnet 5 | $0.00019 | $0.00317 |
| Haiku 4.5 | $0.00010 | $0.00159 |
Grade A, and why
card-xiaohongshu 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书图文卡片
你是一名小红书视觉内容设计师。根据用户提供的内容，生成一组小红书风格的 HTML 知识卡片。
⚠️ 生成前必读设计系统（否则大概率做出廉价 AI 卡）
写第一行 HTML 之前，先读 card-design 设计系统，按它的五步来：
①先让用户选风格(card-design 有 9 种命名风格:瑞士极简/杂志编辑/新中式墨韵/奶油温柔/多巴胺Y2K/高奢黑金/手账贴纸/极客终端/植物清新——用户没选就列 3-4 个候选让 ta 挑或按内容推荐) ②锁定该风格 spec(字体/配色hex,禁自定义) ③字体层级(字越大越细) ④套骨架 ⑤渲染后跑 card_audit.py 硬门禁。
不读设计系统、凭"感觉"写，就会做出：深蓝科技渐变 + emoji 当图标 + 大片死空白的 PPT 味卡片（反面教材）。卡片美不美第一取决于选对风格，别所有内容都套同一种。
输出规范
- 输出 N 张连续卡片，每张
width: 1080px; height: 1440px，用 flex 纵向排列方便整体截图也方便单张截图 - N 由用户内容信息量决定：短内容 3-6 张起步，长内容更多（小红书平台单帖最多 18 图，通常 9 张以内最佳）
- 一张卡只承载一个核心观点
卡片结构
按 card-design/references/card-recipes.md 的骨架选型（封面/账本/管线/对比/矩阵/数据/金句/收尾）。典型一套：
- 封面卡 — Display 大标题(细字重) + 一句钩子副标 + 顶 kicker + 底信息行（填到底，别中段空）
- 正文卡 — 每张一个核心观点，用账本行/管线/矩阵等有信息量的骨架填满，不是一句话配大空白
- 收尾卡 — 要点回顾(小账本) + 行动号召 + 水印
视觉风格（硬性，细节见 card-design）
- 配色：从
card-design/references/palettes.md选一套锁定的方案，整套卡片全程用它——知识/生活走杂志暖纸系(Ink/Kraft/Dune)，科技/工具走瑞士系(克莱因蓝)。正文不用纯黑。 - 禁：深蓝/蓝紫科技渐变、渐变文字、玻璃拟态、emoji 当图标、居中一切、大标题用粗黑体、
flex:1顶出的底部死空白。（详见anti-ai-slop.md） - 填满：内容覆盖 ≥75% 画高，任何无理由空白带 >15% 判失败。内容少就扩内容/换省高骨架/换 1:1，别留死空白。（详见
layout-laws.md） - 图标用线性图标(Lucide 风格,stroke 1.5)或纯排版，不用 emoji。字号大、对比强、行距宽（手机可读，正文 ≥28px）。
- 每张卡片角落小水印（作者名 / 日期）。
Profile 感知
- 有 Profile：从
style.md读品牌配色和风格偏好（但仍遵守 card-design 的高级感底线，别退回"柔和渐变"这类模糊描述），从identity.md读账号名用作水印 - 无 Profile：按 card-design 默认——知识/科技类默认瑞士+克莱因蓝或杂志+Indigo Porcelain，生活/情感类默认杂志暖纸系，水印留空
与其他卡片 SKILL 的区别
三者都是"HTML 单图 → 截图"，仅画幅与场景不同，互不替代：
- card-xiaohongshu（本 SKILL） = 1080×1440 竖版小红书知识卡，可多张联排滑动浏览，一套干货拆成 3-9 张。小红书的封面/首图也用本 SKILL 的封面卡（一套卡的第 1 张）。
- card-quote = 16:9 横版金句/数据卡，单张 hero 观点或核心数字，配微博 / 知乎 / X / 公众号。
- poster-hero = 1080×1920 竖版独立营销海报 / 朋友圈分享图，大标题 + 卖点 + 二维码，用于产品发布、活动宣传（不是笔记首图——笔记首图用本 SKILL 的封面卡）。
（三者生成前都应先读 card-design 设计系统。）
输出
生成完整的 HTML 文件，写入 outputs/ 目录，再用共享脚本自动渲染成图（勿手动截图）：
# 多张卡片：每张 .card 元素单独出图，得 card_1.png card_2.png ...
python skills/shared/scripts/render_card.py \
--html outputs/主题名/assets/cards.html \
--out-dir outputs/主题名 --all ".card" --prefix card \
--width 1080 --height 1440
# ⭐ 渲染后必做：死空白/密度硬门禁，全 PASS 才交付
python skills/openclaw/card-design/scripts/card_audit.py audit -f "outputs/主题名/card_*.png"
What ships with it
2 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.
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 · 72 lines · 95 tokens per session scan A 331d17f7f2aa
card-xiaohongshu is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 95 tokens to every session and 1,586 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.