wewrite-visual

Generate cover images and in-article illustrations for WeChat articles from prompts.

3.2k|513|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/oaker-io/wewrite --skill wewrite-visual
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wewrite-visual
Source: https://github.com/oaker-io/wewrite/tree/main/skills/wewrite-visual
Command: npx skills add https://github.com/oaker-io/wewrite --skill wewrite-visual

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Creating cover images and in-article illustrations for WeChat Official Account articles requires manual prompt writing, image generation calls, budget control, and file verification, which is repetitive and error-prone when done by hand.

Core Features & Use Cases

  • Three generation modes: cover-only, full (cover plus necessary in-article images), or prompts-only, selected from the user's request and recorded via wewrite run update.
  • Prompt engineering from the article: extracts 3-5 concrete entities and the article's dominant mood to build a unified color palette, composition, and texture across all images.
  • Budget and count enforcement: calls wewrite image-gen with --max-images and --max-cost, reducing in-article images when the budget pre-check fails instead of bypassing limits.
  • Illustrated copy output: inserts accepted in-article images into a separate <filename>-illustrated.md copy while never overwriting the original article.
  • Use Case: After finishing a WeChat article draft, ask for a cover and supporting illustrations; the Skill writes prompts, generates images within the cost cap, verifies each file opens correctly, and delivers an illustrated copy.

Quick Start

Generate a cover image and in-article illustrations for my finished WeChat article using the wewrite-visual skill.

Frequently Asked Questions about wewrite-visual

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a cover image for a WeChat article?

Provide the finished article and request a cover; the Skill extracts key entities and mood, writes a cover prompt for the 2.35:1 ratio, and calls wewrite image-gen to produce the image within the configured cost limit.

How to add in-article illustrations to a WeChat post?

Use the full mode, which adds images only to paragraphs that need explanation or reading pauses, then inserts accepted images into a separate illustrated markdown copy. The original article file is never overwritten.

Can I get image prompts without paying for generation?

Yes, the prompts mode writes complete prompts to the image_prompts artifact without calling the paid image service. The task is still marked completed with a note that no images or costs were produced.

Does it limit image generation costs?

Yes, every generation call passes --max-images and optionally --max-cost to wewrite image-gen. If the budget pre-check fails, the Skill reduces the number of in-article images rather than exceeding the cap.

What happens if image generation fails?

The Skill keeps the complete prompts and continues the workflow when the image service fails. It retries only clearly failed individual images once, and checks every output file for format validity and recognizable subjects.