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 gogoingai/wenqu-skills --skill wenqu-imagegit clone --depth 1 https://github.com/gogoingai/wenqu-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/gogoingai/wenqu-skills/wenqu-image)<a href="https://agentmods.dev/skills/gogoingai/wenqu-skills/wenqu-image"><img src="https://agentmods.dev/badge/skills/gogoingai/wenqu-skills/wenqu-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/gogoingai/wenqu-skills/wenqu-image"><img src="https://agentmods.dev/badge/skills/gogoingai/wenqu-skills/wenqu-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 | $0.00106 | $0.03644 |
| Opus 5 | $0.00053 | $0.01822 |
| Sonnet 5 | $0.00021 | $0.00729 |
| Haiku 4.5 | $0.00011 | $0.00364 |
Grade A, and why
wenqu-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 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内容配图与生图 Skill
与调用方的接口约定
其他写作技能(如 wenqu-write)在正文里为图片预留位置时,用两种标记之一:
| 标记 | 含义 | 谁来写 |
|---|---|---|
> 🖼️ 待配图:[一句话描述这张图要表达的核心内容] |
占位标记,只知道这里需要一张图,还没想好具体画法 | 调用方(写作阶段) |
```(代码块)第一行 # 画图提示:[描述] |
完整画图提示,规范已写全,可以直接生成 | 本技能,或调用方已自行写好 |
本技能被调用时,先把占位标记转换成完整画图提示,再进入生成流程——两步不能合并,写法未确认前不要直接生成。
完整画图提示必须带风格 YAML frontmatter,格式是 # 画图提示 代码块内、提示正文之前加一段 YAML,风格、参考图路径、版本记录都写进提示本身,不能只存在对话记忆里——不然下次改图或复现时,所用风格、参考图与版本记录都无从解析:
style: 单色马克笔 # 对应风格库表里的风格名;无风格关键词时写"默认极简PPT" ref: mono-marker/mono-marker-02-branch-decision.png # 实际用过的参考图:styles/ 下的相对路径(不含域名),由 wenqu image fetch-ref 解析为受管缓存路径;临时本地路径不得写入;本轮没用 --ref 时保持原值不动;该字段从未用过时才省略 versions: # 历次生成的版本记录;每项必须是 HTTPS CDN URL,含质检不通过/用户否决版本,编号递增,不删除、不覆盖 v1: https://cdn.example.com/article-img-1111aaaa2222bbbb.png # 简要说明 generation: # 与 versions 同编号,记录实际渲染后端;不存密钥或 API 地址 v1: provider: codex model: codex-image-gen
画图提示:[图片标题]
...(提示正文,四条核心原则见下方)
转换占位标记、或用户直接给风格关键词时,都按这个格式写;references/styles/*.md 里该风格追加的专属描述句,直接拼进提示正文,不要另起一段脱离 YAML 之外的"风格说明",避免以后只读提示正文时丢失风格信息。每次实际传入 --ref 后,把这次真正生效的参考来源回填进 ref 字段:风格资产用 GitHub raw URL,已采用图片用 HTTPS CDN URL;命令中临时使用的 /tmp 文件不得回填。ref 记的是“这次生成实际参考了什么”,不是“这个风格理论上可以参考什么”;没用 --ref 的这一轮,不要动 ref: 字段,保留上一次的记录。只有上传成功、拿到 HTTPS CDN URL 的版本才可写入 versions,同时把本次实际 provider/model 写入同编号 generation;正文的 ![]() 只指向当前采用的那一版,其余版本仅留存在 versions 里供回看对比,具体写入规则见 references/gen-workflow.md 第四步。
用户输入工具
当本技能需要用户确认选择、补充必要信息或授权有副作用的操作时:
- 优先使用当前运行时提供的原生用户输入工具,例如
AskUserQuestion、request_user_input、clarify、ask_user或等价能力。 - 若没有此类工具,使用带编号或字母选项的文本问答。
- 同一决策阶段中彼此独立的问题可合并提问;后一个问题依赖前一回答时,按优先级逐个问。
- 已由用户当前指令、调用方或文章偏好提供的信息,不重复询问。
- 文中出现的具体工具名均为示例;应替换为当前运行时的等价能力。
模型配置提问规则
先检查全局配置 ~/.gogoingai/wenqu-skills/image/config.json,再检查本篇
{项目根目录}/wenqu-skills/{文件名}/config/image.json:
- 两者都没有时,用原生输入工具一次询问默认 provider、模型与画幅;不要索要密钥,仅告知用户运行
wenqu image doctor查看本机凭证文件路径,然后创建全局非敏感配置。 - 有全局配置、本篇没有配置时,在首次为本篇实际生成前询问是否沿用全局选择;拒绝后询问本篇选择并写入文章级配置。
- 有本篇配置、或用户已在当前指令/命令中指定 provider/model 时,不重复询问。
- 直接生图(非文章场景)只读取全局配置;运行时命令由
wenqu image提供。
What ships with it
17 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.
- references/core-principles.md 4.8 KB
- references/design-principles.md 5.5 KB
- references/diagram-examples.md 9.5 KB
- references/diagram-type-selector.md 5.3 KB
- references/gen-workflow.md 21 KB
- references/pitfalls.md 7.6 KB
- references/styles/cream-outline.md 5.2 KB
- references/styles/doodle-watercolor.md 6.9 KB
- references/styles/excalidraw.md 6.4 KB
- references/styles/handdrawn.md 4.3 KB
- references/styles/mono-marker.md 4.2 KB
- references/styles/pencil-sketch.md 4.7 KB
- references/styles/techppt.md 3.3 KB
- references/templates/architecture.md 4.6 KB
- references/templates/comparison.md 4.6 KB
- references/templates/data-viz.md 4.7 KB
- references/templates/flow.md 8.8 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 · 166 lines · 106 tokens per session scan A 25bcd20b458f
wenqu-image is a skill published in the GitHub repository gogoingai/wenqu-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 3,644 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 2026-08-31.
Other skills, from other repositories
card-design
A visual design system for social-media cards and posters, covering colour choices, Chinese typography, layouts, content density, and quality checks.
infographic-generator
Generate branded infographic specifications from any content or data. Outputs structured layout, copy, data visualization, and color scheme — ready to render as HTML/CSS, Satori, Canva, or any design tool. Use this skill when the user wants an infographic, data visual, social media image, comparison chart, stat card…
banana
Direct, generate, edit, compare, and review visual assets with current Google Gemini image models. Use for image creation, image editing, reference-based consistency, product and character visuals, text-bearing graphics, grounded diagrams, video-derived images, and multi-model image portfolios.
mstar-design-md
DESIGN.md design system specification for Morning Star projects. Create, audit, and maintain project-level design tokens (Colors, Typography, Spacing, Elevation, Motion, Shapes, Components, Voice & Content) using Vercel Geist as reference template. Three-level completeness checklist (MVP/Standard/Production) with…
smart-illustrator
An image-generation tool for adding illustrations to articles, creating slide presentations and infographics, or making cover images and thumbnails. It can also create prompts without generating the images.
ui-ux-pro-max
UI/UX design intelligence with 50+ styles, 161 palettes, 57 font pairings, 99 UX guidelines, and 25 chart types. Searchable database with priority-based recommendations for web and mobile.