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 LazyAGI/LazyMind --skill image-prompt-craftgit clone --depth 1 https://github.com/LazyAGI/LazyMindWrote 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/lazyagi/lazymind/image-prompt-craft)<a href="https://agentmods.dev/skills/lazyagi/lazymind/image-prompt-craft"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/image-prompt-craft/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/lazyagi/lazymind/image-prompt-craft"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/image-prompt-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.01129 |
| Opus 5 | $0.00060 | $0.00564 |
| Sonnet 5 | $0.00024 | $0.00226 |
| Haiku 4.5 | $0.00012 | $0.00113 |
Grade A, and why
image-prompt-craft 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 7d 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.
What it actually says
Image Prompt Craft
把用户的视觉意图编译成可执行 Prompt。优先提高构图可控性、主体准确度、风格一致性和最终用途适配；不靠堆叠 beautiful、professional、high quality 等空泛词制造“质量感”。
先判断交付模式
只选当前任务需要的模式，并读取对应 Reference：
- 新图、产品图、摄影、插画、海报或单张配图：读取 通用图片 Prompt。
- 参考图生成、局部修改、换背景或风格迁移：读取 图片编辑与参考一致性。
- PPT、Keynote、演示文稿的底图、母版背景或一组页面背景：读取 PPT 底图 Prompt；若用户还要求整套统一，继续读取 系列一致性。
- 多张普通图片需要同一角色、产品、世界观或品牌风格：读取通用图片 Reference 和系列一致性 Reference。
“PPT 页面图”“PPT 海报页”不一定是底图。若标题、正文、图表仍由 PPT/HTML 排版层添加，则必须走纯底图模式；只有用户明确要求把整页文字烤进图片，才按海报/整页成品处理。
共同工作流
- 从用户原话中锁定不可改写项：主体、动作、数量、关系、用途、比例、文字、品牌要求、参考图职责和明确禁项。缺失信息不会改变核心结果时自行采用合理默认值，不追问。
- 先确定画布和区域分配，再描述主体。Prompt 的信息顺序优先为：
画布与用途 → 构图/留白 → 主体与动作 → 环境和可见细节 → 媒介/镜头 → 材质 → 光线 → 色板 → 一致性/保留项 → 精准禁项。 - 用 5–12 个可见名词和明确空间关系替换空泛形容词。材质、光线、色板分开写；只选一个主媒介或主拍摄语法，避免“摄影 + 水彩 + 3D + 扁平插画”无意混杂。
- 普通场景优先输出一段紧凑自然语言。只有产品渲染、复杂多区画面或多套相互作用的视觉系统，才使用结构化分区；不要为了显得专业而输出冗长 JSON。
- 只保留针对模型高概率错误的短禁项，例如多余肢体、伪品牌、乱码或塑料 CGI 感。不要生成占据主体篇幅的否定词清单。
- 最终 Prompt 默认使用清晰英文；用户要求出现在画面中的原文保持原语言并放入双引号。若调用方或模型明确更适合中文，则可输出中文，但结构与约束不变。
输出要求
- 用户只要求“优化提示词”时，直接给最终 Prompt；必要时附一行关键假设，不输出思维过程。
- 用户要求实际生图时，把最终 Prompt 原样交给当前可用的图片生成或编辑工具；本 Skill 不另建供应商调用方式。
- 用户要求多个方案时，方案之间改变一个有意义的轴，如构图、媒介或光线，不做只换形容词的伪变体。
- 用户提供的信息不足以支持特定品牌、人物身份或精确数据时，不擅自补造。
质量闸门
提交前检查：
- 第一段是否已经说明比例、用途和构图，而不是先堆主体细节？
- 主体、数量、动作和空间关系是否可以被画出来？
- 材质、光线、色板是否具体且互不冲突？
- 是否保留了用户所有硬约束和参考图职责？
- PPT 底图是否无文字、无 UI/图表、具有与实际内容布局匹配的低干扰安全区？
- 系列图片是否在每条独立 Prompt 中重复相同的系列锚点，同时有明确的单图变化？
- 删除任何空泛词后，画面是否仍然清楚？若不清楚，继续补充可见细节。
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.
- 7d ago First seen · 50 lines · 120 tokens per session scan A 1dd1b4f3c675
image-prompt-craft is a skill published in the GitHub repository LazyAGI/LazyMind (77 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 1,129 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 2026-09-05.
Other skills, from other repositories
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
frontend-dev
Full-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art. Builds complete, visually striking web pages with real media, advanced motion, and compelling copy. Use when: building landing pages, marketing sites, product pages…
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
3d-web-experience
Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing dep.