baoyu-cover-image_skill

This skill generates article cover images with configurable type, style, text, mood and aspect to match content.
  • Python

7

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill jst-well-dan/skill-box --skill baoyu-cover-image

  • SKILL.md25.3 KB

Overview

This skill generates elegant article cover images using four configurable dimensions (type, style, text, mood) and a gallery of 20 hand-drawn or illustrative styles. It supports cinematic (2.35:1), widescreen (16:9) and square (1:1) aspects and saves outputs in a per-topic session folder with source and prompt metadata. Use it to produce consistent, publication-ready covers automatically or with manual confirmation.

How this skill works

The skill analyzes supplied article text or pasted content to auto-select the best Type, Style, Text density, and Mood unless the user specifies options. It builds a generation prompt, creates a session directory named by topic slug, saves source files and prompts, then outputs a cover.png. Preferences and quick-mode behavior are loaded from a project or user EXTEND.md when present; first-time setup collects defaults if missing.

When to use it

  • When you ask to generate cover image, create article cover, make cover, or mention the Chinese term “封面图”.
  • When you want a fast auto-selected cover from article content without manual design work.
  • When you need different aspect ratios for blog headers, social cards, or cinematic headers.
  • When you want consistent branding via saved preferences (watermark, default style, aspect).
  • When producing series, tutorials, or documentation that need systematic cover layouts.

Best practices

  • Provide a clear article title and a short summary to improve auto-selection quality.
  • Use --style, --type, --text, and --mood flags when you need precise visual direction.
  • Run first-time setup to store preferred defaults and avoid repeated confirmations.
  • Use --quick for batch or programmatic cover generation; omit it to confirm dimensions.
  • Keep titles short for title-only layouts (recommended ≤8 characters for some languages).

Example use cases

  • Generate a cinematic header for a product launch article using hero + bold-editorial + bold mood.
  • Create a technical conceptual cover for architecture or API docs with blueprint style.
  • Produce minimalist covers for thought leadership pieces with minimal type and subtle mood.
  • Make square social cards (1:1) for WeChat or Instagram using the notion or watercolor styles.
  • Generate visual-only art covers (--no-title) for photography or abstract essays.

FAQ

The skill will prompt a first-time setup to collect preferences and then create EXTEND.md before continuing.

How do I force a particular aspect ratio?

Pass --aspect with a supported ratio (e.g., 2.35:1, 16:9, 1:1) or set a default in preferences.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational