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 agentmods add skills/renky1025/agent-skills/infocardnpx skills add renky1025/agent-skills --skill infocardgit clone --depth 1 https://github.com/renky1025/agent-skillsWhat 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 | $0.00117 | $0.04533 |
| Opus 5 | $0.00059 | $0.02266 |
| Sonnet 5 | $0.00023 | $0.00907 |
| Haiku 4.5 | $0.00012 | $0.00453 |
Grade A, and why
infocard scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- URL：Twitter/X → `twitter tweet <URL>`；GitHub → `gh` 或 Jina；微信公众号 → Exa MCP / Camoufox；通用 → `curl -s "https://r.jina.ai/<URL>"` 或 WebFetch。 How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
infocard: 智能信息卡片生成器
没有"默认布局"。先读懂内容，再让视觉形式从内容的思想形状中长出来。
用法
/infocard <URL|文本> [--theme=<theme>] [--width=<width>] [--output=<name>] [--lang=auto|zh|en|both]
| 参数 | 说明 | 默认 |
|---|---|---|
| 输入 | 网页链接或纯文本（必填） | — |
--theme |
配色：guofeng、slate、sunset、coral、indigo、forest、purple、dashboard、editorial(默认) |
editorial |
--width |
图片宽度 | 1080 |
--output |
输出文件名（无扩展名） | 自动提取 |
--lang |
语言：auto(自动) / zh / en / both(双语) |
auto |
输出：~/Downloads/infocard-img/{name}.png（双语为 _zh.png / _en.png，目录自动创建）。
执行流程
0. 解析输入：提取首个非 -- 的 token 作输入；http(s):// 开头为 URL，否则为文本。--theme/--width/--output/--lang 取对应值，缺省如上。无输入则提示用户。
1. 获取内容
- URL：Twitter/X →
twitter tweet <URL>；GitHub →gh或 Jina；微信公众号 → Exa MCP / Camoufox；通用 →curl -s "https://r.jina.ai/<URL>"或 WebFetch。 - 文本：直接采用，跳过本步。 提取正文、作者、来源。
2. 提取元信息：标题(≤15字)、副标题(≤30字)、来源、核心要点、金句(<25字)、数据。 三类模式：概念解说（提问题 + 类比 + 机制，回答"为什么"）/ 金句（一句话主导，留白≥50%）/ 密集知识（分层编号，留白≤30%）。
内容硬规则（贯穿全程）
- 知识分享，不是摘要：沿原文逻辑（问题→分析→解法）展开，解释"为什么"而非罗列"是什么"；读者读完应能复述。
- 用类比替代术语：每个抽象概念配生活类比或具体场景。
- 不编造：内容须有原文依据，不脱离原文做通用卡，不虚构类比/例子。
- 产品/对比类：额外提取核心优势(3-5)、对比数值、规格参数、benchmark；数值优先于模糊描述（写"69.4% vs 64.8%"，不写"更优"）。
3. 三维判断
- 密度：稀(≤50字,留白≥60%) / 中(50-200字) / 密(200+字,留白≤30%)。
- 结构：单点 / 对比(分栏) / 层级(堆叠) / 流程(纵向) / 辐射(中心) / 并列(网格)。
- 情绪→配色：沉思→slate/indigo；锐利→coral/sunset；温暖/科研→forest；技术→purple；优雅→guofeng；发布(产品/模型/对比/benchmark)→dashboard。
4. 输出决策（内部自检）：密度 / 结构 / 情绪 / 锚点 / 配色；发布类另列核心优势、对比数据、规格参数。
5. 布局：按结构选形式；dashboard 与 editorial 有专门规范（见「主题配色」）。
6. 语言：auto 按原文生成单语（中文占比>50% 判中文）；zh/en 跨语言须用 /translate-polisher（运行时依赖，未安装时降级为内部直译并标注"未校对"）翻译，严禁直译；术语/品牌名(Claude Code、HTML、MCP…)及无法准确对译的短语(one-shot、intent alignment)保留英文。
7. 生成 HTML（见下「HTML 规范」）。单语：中文 Noto Sans SC / 英文 Inter，写 /tmp/infocard_{name}.html；双语：先译后写，分别 _zh.html / _en.html。
8. 截图
mkdir -p ~/Downloads/infocard-img
node ~/.claude/skills/infocard/assets/capture.js /tmp/infocard_{name}.html ~/Downloads/infocard-img/{name}.png 1080 800 fullpage
# 双语：对 _zh.html / _en.html 各跑一次
What ships with it
6 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.
- 2d ago First seen · 224 lines · 117 tokens per session scan A 6e86e0f13a7a
infocard is a skill published in the GitHub repository renky1025/agent-skills (9 stars, last pushed 3d ago), licensed MIT. It adds 117 tokens to every session and 4,533 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…