Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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/zts212653/clowder-ai/image-generationnpx skills add zts212653/clowder-ai --skill image-generationgit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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/zts212653/clowder-ai/image-generation)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/image-generation"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/image-generation.svg" alt="Measured on agentmods" 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 | $0.00124 | $0.03508 |
| Opus 5 | $0.00062 | $0.01754 |
| Sonnet 5 | $0.00025 | $0.00702 |
| Haiku 4.5 | $0.00012 | $0.00351 |
Grade A, and why
image-generation 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 6d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 图片生成 Skill
用途：生成 AI 图片——优先原生 tool call，降级浏览器自动化 适用猫猫：所有猫
何时使用
- 需要为 feature 生成概念图、UI 参考图、像素画素材
- operator要求生成特定风格的图片
- 需要批量生成多个变体
- 需要直接生成完整 PPT/slide 页面、复杂架构图、企业信息图、封面或高密视觉 mock
- 用户明确说“不需要可编辑”“内部 mock”“直接生成完整页面”
Codex 原生能力校准：不要低估 imagegen
Codex image_gen 不只是“概念图/素材生成器”。当前实测能力可以直接生成完整高保真 raster 页面，包括：
- 企业 PPT / slide 页面：高密度模块、标题、图标、流程链路、判断框、页脚
- 复杂架构图 / 信息图：多分区、多节点、多箭头、多层级视觉组织
- 品牌风格 mock：如华为风格的红白黑企业战略页、发布会封面、白皮书页
- UI / poster / cover：需要强视觉完成度、但不要求 native editability 的图像产物
默认判断：当用户要的是“好看、完整、像最终稿”的视觉 mock，且不要求可编辑，先走整页 imagegen。不要先手写 SVG/HTML 去拼格子、排文字、合成素材。
Codex SVG 复发熔断闸
对 Codex / Maine Coon尤其重要：命中以下任一条件时，禁止先写 SVG/HTML/Canvas/脚本合成：
- 用户要“架构设计图 / 架构图 / PPT 页面 / 华为风 / 白底红黑 / 精美图 / 最终稿”
- 已有低保真草图、ASCII 蓝图或设计规格，用户要生成“精美版 / 设计图 / 图片”
- 用户没有明确要求“可编辑文字 / native PPT 元素 / SVG 源文件 / HTML 文件”
执行顺序：
- 先调用原生 imagegen 生成整页 raster。
- 只用 prompt 迭代 1-2 次修风格、层级、文字密度。
- 只有 imagegen 已失败，或用户明确要求可编辑 / native text / SVG 源文件，才允许降级 SVG/HTML/PPT。
- 若准备写 SVG/HTML，必须先写出
SVG override reason：指向已失败的 imagegen 产物，或引用用户的显式可编辑要求。
以下理由不合格，不能覆盖 imagegen-first：中文文字更可控 / 布局更可控 / 先画 SVG 再转 PNG / 架构图需要精确。
Full-page raster first
当用户说“不需要可编辑”“只要精美 mock”“直接生成完整 PPT 页面”时，按这个顺序：
- 整页直出：用一个完整 prompt 描述页面比例、风格、版式、文案、信息密度、图标、图表、负面约束，直接生成完整页面。
- 视觉评估：先看整体风格、信息密度、层级、可读性。若大方向对，用 prompt 迭代，而不是立刻拆成 SVG/合成管线。
- 参考图辅助：如果有低保真草图或同风格样张，把它当 reference / layout guide，但仍让 imagegen 生成整页最终图。多页交付（如 10 页 PPT 套图）时，第一页定稿后作为后续每页的 reference image / style anchor，让整套保持同一视觉系统。
- 失败才降级：连续 1-2 次整页直出都无法保住结构、文字或品牌风格时，再考虑 HTML/PPT/SVG/hybrid。
什么时候才写 SVG / HTML / hybrid
- 硬要求可编辑文字、native chart、PPT 元素可改
- 硬要求像素级对齐、可复用组件、可导出真实代码
- 需要用真实商标/logo/精确法律文本，且图片模型容易画错
- imagegen 已经尝试过整页直出但无法达到验收线
低保真蓝图是辅助 imagegen 理解布局，不是默认替代 imagegen 的最终渲染管线。不要为了“可控”牺牲用户真正要的视觉完成度。
路径选择（先问自己有没有原生能力）
你有内置图片生成 tool 吗？
├─ 是（Codex / Antigravity）→ 用原生 tool call（§ 原生路径）
│ 优势：快、自动发布到气泡、无需浏览器
│
├─ 否（Claude / 其他）→ 能 shell out 到有能力的 CLI 吗？
│ ├─ 是 → 借用（§ 跨引擎借用）
│ └─ 否 → 浏览器自动化（§ 浏览器路径）
│
└─ 需要特定风格控制 / inpainting / 局部编辑？
└─ 是 → 即使有原生能力也走浏览器路径
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.
- 6d ago First seen · 245 lines · 124 tokens per session scan A 87e1c0d9ed07
image-generation is a skill published in the GitHub repository zts212653/clowder-ai (2,904 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 3,508 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…