K
Kael Skills
agent skills, published as repos
Skills/kael-cover
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.

Short answer

kael-cover — One topic-led prompt per cover, compiled from a style registry — then validated and exported at each platform's ratio. It ships as a folder containing SKILL.md, installs by copying into ~/.claude/skills/, and runs in any agent that loads skill folders.

Repokael-cover
LanguagePython
LicenceMIT
Last push2026-11-16
Size2.5 KB SKILL.md

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.

Open the raw file ↗

Common questions

What does kael-cover do?
One topic-led prompt per cover, compiled from a style registry — then validated and exported at each platform's ratio. Reads article.json or Markdown and derives title, subtitle, subject, audience, mood and metaphor before any prompt is written.
How do I install kael-cover?
Run git clone https://github.com/KaelZhang321/kael-cover, then copy the skill folder into ~/.claude/skills/. The Install panel on this page has the exact two commands.
Is kael-cover free to use?
Yes. The repository is public and MIT licensed, so reuse only requires keeping the licence notice.

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