ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

cover-image

Generate article cover images with structured dimensions and bundled generation tooling. Use when the user asks to create a cover image, article cover, blog header, newsletter hero image, or banner-style key visual.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/632657122/cover-image
Or

Cover Image Generation (cover-image)

Reference Images (Important)

If you use reference images (image-to-image / series reference / consistency refs):

  • Reference images must be public URLs.
  • HTTPS is strongly recommended.
  • http:// may work but is insecure and can be blocked by some networks.
  • Local file paths and data: URLs are not supported by the WeryAI gateway.

This skill turns a vague "make a cover image" request into a stable set of structured decisions instead of starting from scratch every time.

Script:

  • scripts/scaffold.ts
  • scripts/build-batch.ts

Safety & Scope

  • Network: This skill calls the WeryAI gateway over HTTPS (https://api.weryai.com).
  • Auth: Uses IMAGE_GEN_API_KEY. The key is never printed. It may be persisted only when you explicitly run npm run setup -- --persist-api-key.
  • Reference images: Must be public URLs (https:// recommended). http:// may work but is insecure. Local file paths and data: URLs are rejected.
  • No arbitrary shell: The generation runtime does not execute arbitrary shell commands.
  • Files written: Output images and optional local config under .image-skills/cover-image/ (project) and/or ~/.image-skills/cover-image/ (home).

Use Cases

  • article cover images
  • blog headers or hero images
  • newsletter covers
  • banner-style key visuals
  • any single visual that should feel like a cover rather than an infographic or comic

Core Dimensions

Choose these six dimensions, then assemble the prompt:

  1. type
  2. palette
  3. rendering
  4. text
  5. mood
  6. aspect

See references/dimensions.md.

Commands

ScriptPurpose
scripts/scaffold.tsInitialize brief.md and prompts/cover.md
scripts/build-batch.tsGenerate batch.json from multiple prompt variants
npm run generateGenerate the cover image
./scripts/vendor/compression-runtime/scripts/main.tsCompress output for delivery

Workflow

Step 1: Initialize Working Files

Create the working directory:

${BUN_X} {baseDir}/scripts/scaffold.ts \
  --output-dir cover-image/topic-slug \
  --topic "Why Habits Stick" \
  --concept "A repeating loop turning into visible momentum" \
  --type conceptual \
  --palette elegant \
  --rendering editorial \
  --text title-only \
  --mood balanced \
  --aspect 16:9 \
  --lang en

This creates:

  • brief.md
  • prompts/cover.md

Step 2: Understand the Content

Extract:

  • the main theme
  • the target reader
  • the keywords
  • whether the content fits a person, a scene, or an abstract metaphor
  • whether title text needs to appear
  • the user's language, when it matters for on-canvas text

Step 3: Choose the Dimensions

Default priorities:

  • type: conceptual
  • palette: elegant
  • rendering: editorial or poster
  • text: title-only
  • mood: balanced
  • aspect: 16:9

Metadata

Author@632657122
Stars3788
Views0
Updated2026-04-04
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-632657122-cover-image": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.