Skip to content
Get packs

Article Cover Image Generator

Makes styled article cover images by choosing type, palette, rendering, text and mood with an image backend.

Source Download skill
Repository
JimLiu/baoyu-skills
Stars
27,191
Licence
MIT
Files
15 files

What it does

Once installed, the agent can design a cover image for a written article. It walks through choices like layout type, colour palette, drawing style, how much text appears, and mood, then writes a detailed image prompt to a file and asks an available image-generation tool to render it as a bitmap. It asks you to confirm the choices before generating, and it is not supposed to fake images with SVG or HTML or fix text by painting over the picture.

Great for

  • Bloggers or newsletter writers who need a quick, consistent cover image for an article
  • People using Codex, Cursor or another agent that already has an image-generation tool

Skip it if

  • Users without any image-generation backend installed, since the skill will stop and ask how to proceed rather than produce art itself
  • Situations needing exact brand logos or precisely correct text, because AI-rendered text can be wrong and the skill forbids fixing it afterwards

Try asking

  • “Generate a cover image for my article about remote work in a warm palette with a title only”
  • “Make a widescreen 16:9 article cover in a dark, bold style”
  • “Create a cinematic 2.35:1 cover image for my essay with a title and subtitle”
Step-by-step guide: how to use Article Cover Image GeneratorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    baoyu-cover-image.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip baoyu-cover-image.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip baoyu-cover-image.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Confirm the aspect ratio and text level at the prompt, since the skill asks before generating unless you say to skip confirmation
  • Set a preferred_image_backend in EXTEND.md so the same tool is used every time

What's inside

  • references/auto-selection.md
  • references/base-prompt.md
  • references/codex-imagegen.md
  • references/compatibility.md
  • references/config/first-time-setup.md
  • references/config/preferences-schema.md
  • references/config/watermark-guide.md
  • references/dimensions/font.md
  • references/dimensions/mood.md
  • references/dimensions/text.md
  • references/palettes/cool.md
  • references/palettes/dark.md
  • references/palettes/duotone.md
  • references/palettes/earth.md
  • SKILL.md

Redistributed unmodified from JimLiu/baoyu-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.