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 zhylq/yuan-skills --skill zhy-article-illustratorgit clone --depth 1 https://github.com/zhylq/yuan-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/zhylq/yuan-skills/zhy-article-illustrator)<a href="https://agentmods.dev/skills/zhylq/yuan-skills/zhy-article-illustrator"><img src="https://agentmods.dev/badge/skills/zhylq/yuan-skills/zhy-article-illustrator/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/zhylq/yuan-skills/zhy-article-illustrator"><img src="https://agentmods.dev/badge/skills/zhylq/yuan-skills/zhy-article-illustrator.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 | $0.00043 | $0.04051 |
| Opus 5 | $0.00022 | $0.02025 |
| Sonnet 5 | $0.00009 | $0.00810 |
| Haiku 4.5 | $0.00004 | $0.00405 |
Grade A, and why
zhy-article-illustrator 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zhy-article-illustrator
Purpose
为任意 Markdown 文章自动规划并生成配图。技能默认采用“高完成度编辑视觉”作为 全局质量基线:不是简单插画,不是装饰图标拼贴,也不是低信息密度草图。系统会先 为文章生成统一的 visual bible,再为每张图生成结构化提示词,使同一篇文章的配图 共享统一风格语言,同时根据章节内容调整构图、信息重点和版式。
默认优先兼容 Gemini Nano Banana 工作流,并默认走 Xiaomi Gemini 兼容接口;同时支持 Gemini 原生代理 / 中转站模式与官方 Gemini 接口。
When to Use
- 用户请求“为文章配图”、“illustrate article”、“add images to article”
zhy-wechat-writing技能的 Step 6 调用(with_illustrations=true)- 用户希望生成更适合公众号场景的高完成度专题视觉
- 用户希望将本地图片上传到七牛云获取 CDN URL
Prerequisites
- 文章 Markdown 文件已存在
- 已配置至少一种可用生图通道:
- Gemini 官方直连:
GEMINI_API_KEY或GOOGLE_API_KEY - Gemini 原生代理 / 中转站:
IMAGE_PROVIDER=gemini、IMAGE_API_KEY、可选IMAGE_BASE_URL - Xiaomi Gemini 兼容接口:
IMAGE_PROVIDER=xiaomi或XIAOMI_API_KEY,可选XIAOMI_BASE_URL - 若启用上传:七牛云配置已就绪(技能根目录
.env中的QINIU_ACCESS_KEY/QINIU_SECRET_KEY/QINIU_BUCKET/QINIU_DOMAIN)
- Gemini 官方直连:
Workflow
Step 1: 分析文章
目标:理解文章结构,确定配图数量、位置与表达方式
操作:
- 读取
article_path的完整内容 - 解析文章结构:标题、各章节标题(
##/###)、段落数、代码块位置 - 识别核心信息点:
- 关键概念 / 术语解释 -> 适合信息图
- 对比 / 差异描述 -> 适合对比图
- 步骤 / 流程描述 -> 适合流程图
- 架构 / 框架描述 -> 适合架构图
- 数据 / 统计 -> 适合数据可视化
- 场景 / 叙事描述 -> 适合专题插画或编辑场景图
- 根据
density确定配图策略:minimal:仅为最核心的 1-2 个信息点配图balanced:每个##级主要章节配一张图rich:每 300 字左右或每个重要段落配一张图
- 确定
slug:- 若用户提供
slug:直接使用 - 否则从文章 H1 标题推导
kebab-case
- 若用户提供
- 创建输出目录:
{article_dir}/illustrations/{slug}/
输出:文章结构分析结果、配图位置列表
Step 2: 生成 visual bible 与配图规划
目标:为整篇文章建立统一视觉基线,并生成每张图的规划信息
操作:
- 先生成文章级
visual_bible,保存到{article_dir}/illustrations/{slug}/visual-bible.md visual_bible必须覆盖:quality_baseline:统一采用高完成度编辑视觉 / 专题配图标准visual_theme:本篇文章的整体风格方向color_system:主色、辅色、强调色、背景倾向graphic_language:图形语言、线条/材质/光感、信息层级方式layout_discipline:页面留白、模块密度、标题区与内容区节奏text_policy:默认简体中文;仅english_terms_whitelist中的术语保留英文negative_rules:禁止简单画图、低幼卡通、无意义装饰、英文乱码、随意混搭风格
- 再对每个配图位置生成 outline 条目,至少包含:
position:插入位置(在哪个章节/段落之后)purpose:这张图要传达什么信息image_type:对比图 / 流程图 / 架构图 / 数据图 / 场景图 / 编辑专题视觉core_message:本图唯一核心表达content_blocks:画面中必须出现的内容块text_blocks:图中需要出现的标题、标签、注释(默认中文)english_terms_used:本图允许出现的英文术语子集layout_hint:布局方向与信息分区filename:输出文件名(格式:NN-简短描述.png)alt_text:Markdown 图片的 alt 文本
- 保存到
{article_dir}/illustrations/{slug}/outline.md - 同时为每张图生成独立提示词文件,保存到
{article_dir}/illustrations/{slug}/prompts/
What ships with it
10 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.
- .env.example 454 B
- .gitignore 388 B
- README.md 1.8 KB
- references/config-schema.md 6.3 KB
- references/prompt-guide.md 11 KB
- scripts/illustrate-article.ts 17 KB runs code
- scripts/image-gen.ts 15 KB runs code
- scripts/plan-illustrations.ts 32 KB runs code
- scripts/qiniu-upload.ts 10 KB runs code
- tsconfig.json 713 B
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 · 361 lines · 43 tokens per session scan A 49611d43878e
zhy-article-illustrator is a skill published in the GitHub repository zhylq/yuan-skills (36 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 4,051 once invoked, about $0.0002 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
tong-jincheng-perspective
A Chinese-language framework for thinking about relationships, attraction, social situations, and personal growth from the perspective of a livestream relationship creator.
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.
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…