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 cass-2003/local-workflow-skill --skill ai-image-promptgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote 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/cass-2003/local-workflow-skill/ai-image-prompt)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/ai-image-prompt"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/ai-image-prompt/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/cass-2003/local-workflow-skill/ai-image-prompt"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/ai-image-prompt.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 | $0.00097 | $0.05623 |
| Opus 5 | $0.00048 | $0.02812 |
| Sonnet 5 | $0.00019 | $0.01125 |
| Haiku 4.5 | $0.00010 | $0.00562 |
Grade A, and why
ai-image-prompt 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 10d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 生图提示词实战排障版
定位:把“帮我生成一张图”变成可执行闭环:目标 / 画面 / 约束 / 证据 → 场景执行卡 → 高频坑 / 防遗漏 → 输出要求 → 约束 → 高频 Bug 反例库 → 2024-2026 新坑速查 → 与相邻技能的边界。 铁律:prompt 不是形容词堆叠,而是视觉导演说明;未确认用途、画面变量、模型能力和复验标准时,必须标“需验证”,不能包装成稳定可用。
快速总则
- 先定目标:用途、受众、载体、平台、商业/非商业、是否后期排版、是否要保留空白安全区。
- 再定画面:主体、composition、空间层级、camera angle、lighting、depth of field、材质、color palette、情绪和审美边界。
- 用户说“高级、别土、现代、像能用”但没给风格时,默认解释为浅色极简、少颜色、强对齐、低噪声,而不是更花、更亮、更炫。
- 用户不会专业描述 UI 或画面时,先把口语需求归一成用途、主体、布局、色彩预算、负向排除和审图标准;缺少非关键细节时写默认假设并继续。
- UI mockup、后台、SaaS、工作台、表单、列表、订单页生图默认使用 light minimal product screenshot:白/浅灰画布、细边框、少阴影、1 个主操作色、状态色只做小 badge。
- 再定约束:aspect ratio、尺寸、是否使用 reference image、是否锁定 seed、是否需要 inpainting / outpainting、是否禁文字、logo 或人物。
- 最后给证据:每条 prompt 都要说明适用模型、关键变量、negative prompt / exclude、参数、迭代方式和审图清单。
- 默认输出正向 prompt、negative prompt、参数建议、variation 方案、复验点;用户只要中文也可给中英双语。
- 不确定模型能力、平台政策、版权授权、商标可用性时,写“需验证”,不擅自承诺可商用。
- 真实品牌、产品、人物、logo、typography、IP 资产优先用 reference image 和人工复核;AI image 只负责生成或编辑视觉,不替代法务与品牌审批。
场景执行卡
1. 一句话需求升级为可执行 prompt
- 适用:用户只说“高级感海报 / 科技感背景 / 更现代的图”。
- 先查:用途、受众、平台、模型、比例、是否有素材、禁止风格。
- 动作:把抽象词拆成主体、composition、材质、lighting、camera angle、color palette、约束和负向排除。
- UI/产品界面类口语需求默认不要加复杂插画、暗色大侧栏和彩色图标墙;先做浅色极简、最多 3 个主导色族、真实组件截图感。
- 证据:给 2-3 个方向,每个方向说明适合模型、关键变量和审图标准。
- 失败兜底:需求模糊时先列假设;不要只翻译成英文。
2. App 图标 / logo / 品牌符号
- 适用:App icon、品牌 mark、logo 概念、启动图标。
- 先查:品牌名、行业、核心隐喻、小尺寸可读性、是否需要字标和商标注册。
- 动作:只保留 1 个主隐喻;强调 clear silhouette、vector-like clarity、balanced negative space、brand consistency。
- 约束:不要让模型生成关键文字;typography 和正式字标后期设计;logo 相似性、copyright、IP 风险需人工复核。
- 复验:16/32/64px 预览、单色版、深浅背景、负空间、可注册性线索。
3. 宣传图 / 海报 / 社媒封面
- 适用:产品海报、App Store 素材、官网 hero、活动 KV、小红书/Instagram 封面。
- 先查:卖点、文案区、平台裁切、横竖版、品牌色、是否后期排字。
- 动作:定义 foreground / midground / background,留 safe area for typography,不让模型生成关键文案。
- 约束:画面焦点单一,低噪声背景,避免满屏元素和库存图审美。
- 复验:裁切后主体是否完整,文字区是否干净,移动端缩略图是否可读。
4. UI mockup / 界面参考图
- 适用:用户要生成 UI 设计图、界面参考、后台截图、App 页面、SaaS dashboard 或给前端复刻的图片。
- 默认 prompt:light minimal SaaS product screenshot, 90% neutral white and zinc surfaces, one subdued primary action color, status colors only as small soft badges, thin borders, compact scan-friendly density, no decorative gradients, no colorful icon wall, no dark sidebar unless explicitly requested。
- 画面:先说明 layout 和真实组件,如 sidebar、top search、KPI cards、table、timeline、detail panel;再说明色彩预算,不要只说高级感。
- negative prompt:overly colorful dashboard, neon gradients, purple-blue glow, glassmorphism, decorative blobs, dark marketing sidebar, random colorful icons, stock-photo hero, lorem ipsum。
- 复验:主导色是否超过 3 个、是否浅色为主、是否像真实产品截图、是否能被 HTML/CSS 复刻。
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.
- 10d ago First seen · 260 lines · 97 tokens per session scan A d3556bf74b9b
ai-image-prompt is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 5,623 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 2026-08-30.
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.