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 tranfu-labs/tranfu-skills --skill article-cover-imagegit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/article-cover-image)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/article-cover-image"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/article-cover-image/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/tranfu-labs/tranfu-skills/article-cover-image"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/article-cover-image.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 | $0.00163 | $0.07376 |
| Opus 5 | $0.00081 | $0.03688 |
| Sonnet 5 | $0.00033 | $0.01475 |
| Haiku 4.5 | $0.00016 | $0.00738 |
Grade A, and why
article-cover-image 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 — 1,012 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill：article-cover-image
文章封面图｜默认 16:9｜主色 E63A46｜轻量多风格｜MiSans｜非塑料质感
0. 最高优先级规则
你的任务是：根据用户输入的标题或文章，直接生成一张横版文章封面图，默认比例为 16:9。
默认行为：
直接调用图像生成能力出图
默认带标题文字
标题文字必须少
标题默认使用 MiSans 字体风格
整体视觉系统必须统一
主色固定使用 #E63A46
默认避免塑料感、玩具感、廉价 C4D 感
不要先输出大段分析
不要只输出 Prompt
只有用户明确要求：
只要方案
只要 Prompt
先分析
不生成图
才输出文字方案。
0.1 适用边界与重定向
触发范围：
用户给标题，或给标题 + 正文，并要求生成文章、内容、视频、PPT 首页或网站 Banner 类封面图。
默认输出一张横版封面图；默认比例 16:9，除非用户显式指定其它比例。
不触发范围：
icon / 符号 / 黑白线性图标 → 转到 black-line-icon-style
信息图 / 知识卡片 / 对比表 / 流程长图 / 课程大纲图 → 转到专门的信息图或图表工作流
品牌正式 Logo 定稿 → 转到 logo 设计工作流或人工设计
只要文章文案 / 普通写作 Prompt / 非视觉分析 → 转到写作或 prompt 相关工作流
意图歧义处理：
用户说“只要 Prompt”且目标是文章封面图 → 使用本 Skill 的文字模式，输出封面图生成 Prompt，不调用图像生成。
用户说“只要 Prompt”但目标是文章写作、营销文案或普通提示词 → 不触发本 Skill。
用户说“不生成图”但仍要求封面视觉方案 → 使用文字模式；如果完全不需要视觉产物 → 不触发本 Skill。
ownership：
默认 ownership = edit/generate image：直接调用图像生成能力产出图片。
仅当用户显式说“只要 Prompt / 不生成图 / 先给方案”时，ownership = rewrite inline：只输出可复制的生成 Prompt 或方案，不生成图片。
完成标准：
done = 产出一张封面图，且 §5.6 的 9 项自检全部通过。
若用户只要 Prompt，done = 输出 §11 主 Prompt + §12 Negative Prompt，且不调用图像生成。
0.2 主流程
CREATE A TODO LIST FOR THE TASKS BELOW（内部执行，不向用户展示）：
1. 读取用户输入。若既没有标题，也无法从文章中提取主题 → 向用户索要标题并退出。
2. 识别输出模式。若用户显式要求“只要 Prompt / 不生成图 / 先分析” → 生成文字方案并结束；否则继续出图。
3. 提取原标题。若输入包含正文 → 用正文辅助理解主题，但正文不直接进入画面。
4. 生成短标题：若原标题包含解释、对比、流程、方法、教程或论证结构 → 执行子流程「复杂标题降维」；否则按 §4.1 压缩为短标题。
5. 选择风格：按 §8 路由到 §7.1 风格池；若没有明确命中 → 默认使用 B 现代产品 UI 风或 A 极简杂志风。
6. 确定单主体：按 §5.5 选择一个核心视觉主体；若标题含多个对象 → 先找单一视觉隐喻覆盖全部语义。
7. 拼接内部 Prompt：使用 §11 主 Prompt；若运行时支持 Negative Prompt → 附加 §12；否则按 §5.8 把关键负面约束写回主 Prompt。
8. 跑 §5.6 自检。若任一项不通过 → 按 §5.7 或 §5.8 纠偏后跳回第 5 步；若同一失败连续 2 次出现 → 降级为无字图或更抽象单主体方案后再试一次；仍失败 → 简短说明失败原因并结束，不宣称 done。
9. 调用图像生成能力产出封面图，简短回复结果，并结束。
子流程「复杂标题降维」：
1. 识别标题类型：对比型 → §5.3；流程型 → §5.4；其它解释 / 方法 / 教程型 → §5.1。
2. 删除解释词、修饰词、副标题、括号内容和长句结构。
3. 只保留一个核心判断或一个核心对象。
4. 输出符合 §4.1 的短标题，并返回主流程第 5 步。
1. 视觉系统统一规则
所有封面必须属于同一个品牌视觉系统。
统一要素包括：
1.1 主色统一
What ships with it
5 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.
- 11d ago First seen · 1,012 lines · 163 tokens per session scan A 684312b6c942
article-cover-image is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 163 tokens to every session and 7,376 once invoked, about $0.0008 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.