skilld
All skills
jimliu avatar

/baoyu-cover-image

@b0ac523 official
by Jim Liu 宝玉jimliu/baoyu-skills26k stars
2,896

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".

Ask your Agent

Use this Skill: https://skilld.dev/gh/jimliu/baoyu-skills/baoyu-cover-image

This session only. Nothing lands on disk.

referencespaletteswarm.md

≈181 tokens on demand. Your agent reads this file only when SKILL.md points to it.

warm

Friendly, approachable, human-centered

Color Palette

Role Color Hex
Primary 1 Warm Orange #ED8936
Primary 2 Golden Yellow #F6AD55
Primary 3 Terracotta #C05621
Background Cream #FFFAF0
Background Alt Soft Peach #FED7AA
Accent 1 Deep Brown #744210
Accent 2 Soft Red #E53E3E

Decorative Hints

  • Sun rays, warm lighting effects
  • Rounded shapes, organic curves
  • Hearts, smiling faces, friendly icons
  • Warm gradient overlays

Semantic Constraint

Do NOT render color names, hex codes, or role labels as visible text in the image.

Best For

Personal growth, lifestyle, education, human stories, emotion, community

Source: SKILL.md on GitHub

Third-party checks

1 warning16d5 checks · Risk MEDIUM
  • Gen Agent Trust Hub16d

    The skill generates article cover images by processing article content and user preferences. It employs dynamic execution patterns by searching for and running external scripts based on runtime discovery and environment variables. It also lacks specific sanitization for article content, making it potentially vulnerable to indirect instructions embedded in processed data.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer6mo

    33 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at b0ac523. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 4 months ago

Capability

version
1.117.5
Other metadata
metadata
{
  "openclaw": {
    "homepage": "https://github.com/JimLiu/baoyu-skills#baoyu-cover-image"
  }
}

Topics

  • Design
  • cover-image
  • image-generation
  • article
  • prompt-based

README badge

README badge for jimliu/baoyu-skills/baoyu-cover-image

What it does

Generates article cover images with 5-dimensional customization (type, palette, rendering, text, mood) supporting cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Combines 11 color palettes and 7 rendering styles for visual variety. Resolves image backends (Codex, Cursor, baoyu-image-gen) and confirms dimensions before rendering.

Generated from the current SKILL.md.

Frequently asked

What image backends does this skill support?
It auto-selects in order: Codex `imagegen`, Codex via CLI, Cursor `GenerateImage`, other runtime-native tools, or installed non-native backends like `baoyu-image-gen`. You can override with `--quick` to skip confirmation or pin a preference in `EXTEND.md`.
Does this skill require confirmation before generating?
Yes, by default. It confirms your chosen dimensions, aspect ratio, palette, rendering style, and backend before generation. Pass `--quick` or set `quick_mode: true` in `EXTEND.md` to skip.
What aspect ratios are supported?
16:9 (default), 2.35:1 (cinematic), 1:1 (square), 4:3, 3:2, and 3:4. Specify with `--aspect`.
Can I include reference images to guide the style?
Yes, use `--ref <files...>` to pass reference images. If they contain people who should appear in the cover, the skill will either pass them directly to the model (if supported) or embed character descriptions in the prompt.
What customization dimensions does this offer?
Five dimensions: type (hero, conceptual, typography, metaphor, scene, minimal), palette (11 options including warm, elegant, cool, dark, vivid, etc.), rendering (7 styles including flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print), text level (none, title-only, title-subtitle, text-rich), and mood (subtle, balanced, bold).

Generated from the current SKILL.md. These answers refresh after source changes.