Design & VisualWritingPythonMIT
kael-cover
Branded covers, compiled
A clean-room rebuild of the MIT-era cover workflow. It reads the article, decides metaphor and audience, picks exactly one style from a local registry, compiles a single prompt, renders one image, then checks dimensions and title-safe area before exporting WeChat, Xiaohongshu and Weibo/X assets. Each run writes generation.json beside the image, so the prompt, the style choice and the reason behind it are reproducible.
What it does
- Reads article.json or Markdown and derives title, subtitle, subject, audience, mood and metaphor before any prompt is written.
- Style registry with explicit topic-to-style rules: etching-editorial, research-paper, editorial-grid, retro-future, black-red-editorial, midcentury-editorial, paper-relief, pixel-mechanism.
- Compiles one prompt through scripts/compile_prompt.py — one style per image, never two.
- Quality gate: rejects missing or clipped titles, unrelated subjects and generic presentation-slide compositions.
- Exports per-platform sizes with sips instead of stretching a landscape cover into a portrait one.
- Writes generation.json next to the output, keeping the prompt, the chosen style and the reason for the next run.
When it triggers
“Make a WeChat cover for this article”
“小红书封面,主题是本地大模型显存”
“A square post image for X, same article”
Inside SKILL.md
SKILL.md 44 lines · click to read
# Kael Cover V2 A clean-room cover workflow rebuilt from the MIT-era Punk Cover baseline. It uses a local style registry and an explicit compiler instead of copying later proprietary prompt text. ## Operating rules - Analyze the article before choosing a visual metaphor. - Use exactly one style per image. - Prefer one strong subject and one readable title hierarchy. - Generate independently for each platform ratio; never stretch a landscape cover into a portrait cover. - Keep title text short enough for reliable image rendering; preserve the full title in metadata and prompt files. - Save the compiled prompt and generation metadata beside the output. - Never claim an image was saved unless the generator returned a current-run file path or URL. ## Supported targets - WeChat/site: landscape; current generator maps this to `landscape`. - Xiaohongshu: portrait; current generator maps this to `portrait`. - Weibo/X: landscape or square according to the post template. ## Pipeline 1. Read `article.json` or the source Markdown. 2. Derive title, short subtitle, subject, audience, mood, metaphor, and forbidden elements. 3. Choose one style from `styles/registry.json` using the topic-to-style rules. 4. Compile a single prompt with `scripts/compile_prompt.py`. 5. Generate one image with the image tool. 6. Copy only the explicit returned artifact into the requested output path. 7. Validate dimensions, title-safe area, file type, and non-empty image content. 8. Derive platform files with `sips`; keep the original PNG. ## Style selection - research, code, engineering: `etching-editorial` or `research-paper` - products, startups, AI tools: `editorial-grid` or `retro-future` - social criticism or security incidents: `black-red-editorial` or `etching-editorial` - career and work: `midcentury-editorial` or `paper-relief` - abstract mechanisms: `paper-relief` or `pixel-mechanism` When no style is specified, select one automatically and record the reason in `generation.json`. ## Quality gate Reject and regenerate if the title is missing, severely misspelled, clipped, the subject is unrelated, the image is a generic presentation slide, or the composition has multiple competing focal points. Text in generated images is not trusted automatically: inspect the image and retain the exact title in the prompt metadata.
Install
git clone https://github.com/KaelZhang321/kael-cover.git
cp -R kael-cover ~/.claude/skills/kael-cover
Inside the repo
SKILL.md
scripts/compile_prompt.py
styles/registry.json
PROVENANCE.md
LICENSE