Sketch Image Prompt

What it does

When your agent uses it

• The user wants to create any kind of visual from text content — including banners
• Article illustrations
• Inline diagrams
• Concept visuals

Example prompts

• “turn this into a visual”
• “create an image prompt”
• “make an illustration for this”
• “/sketch-image-prompt”

Requirements

• Compatibility (from SKILL.md): Requires visualize tools for color palette widget display. Compatible with Midjourney, Stable Diffusion, and any AI image generation tool that accepts natural language prompts.
• Pre-approved tools (allowed-tools): visualize:show_widget, visualize:read_me

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1元素只有 3 个或更少 → 强制使用主角+卫星 / 对角线 / 错落分层，禁止单轴排列
2. 2元素 4 个以上 + 强顺序关系（步骤 1→2→3→4）→ 才能考虑流程型，但仍优先错落形式
3. 3一个明显主角 + 多个配角 → 主角放大居一侧 + 配角散布另一侧不同高度
4. 4多个等重元素 → 四象限 / 多区分布 / 对角线
5. 5循环关系 → 辐射 / 环形

What it can do on your machine

Read from SKILL.md and the folder at commit 7ffd3a4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • visualize:show_widget
  • visualize:read_me

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • black

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires visualize tools for color palette widget display. Compatible with Midjourney, Stable Diffusion, and any AI image generation tool that accepts natural language prompts.

  From compatibility in the SKILL.md frontmatter.

Context cost

Sketch Image Prompt loads about 1.8k tokens when it runs. Until then it costs about 171 tokens; SKILL.md has 382 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~171

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from okooo5km/Skills4U at commit 7ffd3a4, republished under its MIT licence (© okooo5km). 382 words, ~1,837 tokens.

name

sketch-image-prompt

description

Transforms article content or summaries into minimalist hand-drawn style JSON prompts for AI image generation tools. Use this skill whenever the user wants to create any kind of visual from text content — including banners, article illustrations, inline diagrams, infographics, or concept visuals. Trigger on requests like "turn this into a visual", "create an image prompt", "make an illustration for this", "generate a diagram from this article", "I need a sketch for this section", or any request combining content analysis with image/visual prompt generation. Always use this skill when the user provides text content and wants an AI-ready image prompt output.

allowed-tools

visualize:show_widget, visualize:read_me

compatibility

Requires visualize tools for color palette widget display. Compatible with Midjourney, Stable Diffusion, and any AI image generation tool that accepts natural language prompts.

license

MIT

metadata.version

1.3.0

metadata.created

2026-03-01

metadata.updated

2026-05-04

metadata.author

Boss

[一行设计摘要：背景色 + 构图类型 + 元素数量，例如：暖米色背景，水平三步流程，3个元素]

[final_prompt 正文]

[比例] [构图类型] composition. Elements distributed across the FULL canvas area, occupying both horizontal AND vertical space, NOT compressed to a single horizontal/vertical line. [背景色描述]. Only [N] elements with explicit spatial positioning: [元素1描述 + 位置如"on the upper-left"], [元素2描述 + 位置如"enlarged in the center taking 35% of canvas"], [元素3描述 + 位置如"on the lower-right"]. [连接方式描述]. Bold marker illustration, chunky brush-pen style, very thick black outlines with heavy stroke weight — like a fat-tipped marker, bold chunky lines. Dry brush texture with tiny gaps in ink coverage, organic slightly rough edges, natural line weight variation, imperfect circles and slightly wobbly lines, warm handmade feel — NOT perfect vector lines. [配色描述]. Minimal text labels only: [标签列表]. Generous whitespace BUT well-distributed (no large empty bands at top/bottom or left/right), clean and uncluttered, flat illustration with no shadows or gradients, rounded handwritten-style font. --ar [X:Y]

© okooo5km, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/sketch-image-prompt of okooo5km/Skills4U.

Open the folder on GitHubat commit 7ffd3a4