Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Design & media
markdown-to-minimal-image
Try itRead an attached Markdown document, analyze and summarize it, then generate a minimalist image from the summary using the default image model. Ask the user for aspect ratio when needed, and support social-banner formats such as 5:2 and 5:4. Use when the user wants a document turned into a simple tutorial-style visual with handwritten whiteboard aesthetics.
What it does
Use this skill when the user provides a Markdown document and wants: A concise summary of the document. One generated image based on that summary. A specific aspect ratio for social media or hero banners. A minimalist, handwritten, whiteboard-like visual style.
The skill document
Markdown to Minimal Image
When to Use
Use this skill when the user provides a Markdown document and wants:
- A concise summary of the document.
- One generated image based on that summary.
- A specific aspect ratio for social media or hero banners.
- A minimalist, handwritten, whiteboard-like visual style.
When NOT to Use
Do NOT use this skill for:
- Generating photorealistic images or detailed illustrations.
- Creating multi-image documents or slide decks.
- Processing non-Markdown file formats (PDF, Word, plain text without conversion).
- Tasks where the user explicitly requests a different visual style (photography, 3D rendering, oil painting).
- Generating images without a source document to summarize.
Inputs
document— Attached Markdown file to read and analyze.- Required: yes
- Type: file (
.md)
aspect_ratio— Desired image aspect ratio, e.g.5:2,5:4,16:9,1:1.- Required: no
- Type: string
- Default: none (user will be prompted)
color_scheme— Color scheme for the image, e.g.black-and-white,blue accent,warm beige,pastel.- Required: no
- Type: string
- Default: neutral minimalist palette
Outputs
summary— String. 3–5 bullet points or one short paragraph summarizing the document.image— Generated image object. Exactly one image in the requested aspect ratio and color scheme.image_path— String. File path where the image is saved:$HOME/.hermes/cache/{date}-{subject}.png.aspect_ratio— String. The aspect ratio used for generation (resolved from input or user prompt).color_scheme— String. The color scheme used for generation (resolved from input or default).
Procedure
- Read the attached Markdown document using file tools.
- Detect the document language. If the document is in Simplified Chinese, all output (summary, image text) must be in Simplified Chinese. If English, all output must be in English.
- Identify the core topic, key ideas, and actionable points.
- Summarize the document in 3–5 short bullets or one short paragraph.
- If
aspect_ratiois missing, ask the user for it before proceeding. Accept only valid ratios (5:2, 5:4, 16:9, 1:1, or a custom ratio the user specifies). - If
color_schemeis missing, ask the user or default to a neutral minimalist palette. - Build an image prompt from the summary that incorporates the aspect ratio, color scheme, and whiteboard-tutorial style.
- Generate exactly one image using the default image generation model.
- Save the generated image to
$HOME/.hermes/cache/{date}-{subject}.png. - Call
present_filesto surface the saved image to the user. - Return the summary alongside the image.
Verification
- The summary must be non-empty and accurately reflect the source document.
- The generated image must match the requested aspect ratio exactly.
- The generated image must use the requested color scheme (or default).
- The image style must be minimalist, whiteboard-like, with handwritten text — not photorealistic or cluttered.
- The language of the image text must match the source document language (English or Simplified Chinese).
Error Handling
- Missing document: If no Markdown file is attached, inform the user and halt.
- Invalid aspect ratio: If the user provides an unsupported ratio, list valid options and ask again.
- Image generation failure: If the model fails to produce an image, retry once with a simplified prompt. If still failing, report the error and suggest a different model or lower resolution.
- Unreadable document: If the file cannot be parsed as Markdown, inform the user and request a valid
.mdfile.
Style Notes
- Handwritten tutorial on whiteboard.
- Minimalist composition with clean layout.
- Simple color palette matching the requested scheme.
- Low resolution acceptable for social media or hero-banner use.
- Prefer simple diagrams, arrows, boxes, labels, and short notes.
- Avoid heavy detail, photorealism, or decorative clutter.
Supported Aspect Ratios
- 5:2 — social banner
- 5:4 — social banner
- 16:9 — hero / widescreen
- 1:1 — square / social post
- Custom ratios accepted on request
Related skills
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
More from j3ffyang
Browse all skillsPolish a technical blog draft into an 800–1000 word, 3–4 section zh-CN article, preserve technical terms/code, and generate consistent hero + per-section image prompts when the user asks to polish and translate a blog with images.
Generate video from supplied image using Veo-3.0 async API. Gemini vision analyzes image, Veo creates video via predictLongRunning. All outputs in ~/.openclaw/workspace/tibetanProc/ with yymmddHHMM prefix.
Read a plain Markdown file (e.g. 260321_openclawConfig.md), generate header and section images using the default OpenClaw image model and API key from ~/openclaw/.env, create a new *_img.md copy with embedded PNGs, and move all generated images into an img/ folder next to the original file.
Polish a technical blog draft into a 1000–1200 word, 4–5 section en-US article, preserve technical terms/code, and generate one consistent hero image prompt.
Help the user draft, review, and polish blog posts in Markdown, keeping the original languages and informal tone.
Generate a daily AI news newsletter from fresh web sources. Use when the user asks for a current AI digest, AI news roundup, curated newsletter, or daily AI...