Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

WeChat Article Cover & Illustration Generator

Reads your article's title and body, then designs and generates AI cover art and in-body illustrations for WeChat official-account posts.

Image & VideoIntermediate★ 564⑂ 87AI score 9/10Last updated: Sep 6, 2026

What it does

  • Parses article.md plus .aws-article/config.yaml, extracting every ![type：description](placeholder) marker into an image plan.
  • Covers: a seven-step derivation (find the tension → define the relationship → find the metaphor → pick a visual language → 2.35:1 layout → write it as prose → review) and picks one of 12 built-in cover archetypes. The prompt spells out the 4–7 character headline, its size, color and placement.
  • In-body images: 8 archetypes selected by one test — if you delete this image, does the reader fail to understand (informational slot) or fail to keep reading (rhythm slot)? If neither, the image is dropped.
  • Calls an image API via scripts/image_create.py with explicit failure branches: not configured (exit 2 → optional agent fallback), network errors (auto-retry once), 401/403 credential errors (no silent fallback), 400 parameter errors.
  • Forces reuse of an existing product screenshot library before spending API calls on new generations, and re-verifies file references when images are regenerated (extensions can change from .png to .jpg).

Recommended for

  • WeChat official-account editors, self-media creators and brand marketers
  • Teams that need a reusable, consistent cover-style system across many posts
  • Users who already hold an image-generation API key (DALL·E, gpt-image, Gemini/nano-banana class)

Usage examples

  1. "Make a cover for this article" → derives the article's core tension, writes a 2.35:1 prose prompt, generates cover.png, then self-reviews thumbnail legibility, element count (≤3) and topical relevance.
  2. Writing a product tutorial → first scans .aws-article/products/*/images/ for real UI screenshots to cite, and only generates new art for the remaining gaps.
  3. "Swap in the photos I uploaded and re-publish to drafts" → drops files into imgs/, rebuilds img_analysis.md (exactly one cover), regenerates the HTML, and re-runs publishing.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/aiworkskills/wechat-article-skills/HEAD/skills/aws-wechat-article-images/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/aws-wechat-article-images folder from the GitHub repo aiworkskills/wechat-article-skills into my ~/.claude/skills/aws-wechat-article-images/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/aiworkskills/wechat-article-skills.git && mkdir -p ~/.claude/skills && cp -r wechat-article-skills/skills/* ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/aiworkskills/wechat-article-skills.git
  2. Create the skills folder: mkdir -p ~/.claude/skills
  3. Copy all nine slugs together — the skills reference each other's files: cp -r wechat-article-skills/skills/* ~/.claude/skills/
  4. Verify Python 3 is available: python3 --version (on Windows use py -3 -X utf8).
  5. In your working repo root, create aws.env containing IMAGE_MODEL_API_KEY=your_key. Use a dedicated, least-privilege key rather than an account master key.
  6. Fill in image_model (provider, base_url, model, default_size) and cover_aspect in .aws-article/config.yaml. base_url must be the full endpoint path, e.g. https://.../v1/images/generations or /v1/chat/completions.
  7. Test connectivity: python3 ~/.claude/skills/aws-wechat-article-images/scripts/image_create.py test
  8. In Claude Code, ask something like "generate a cover and illustrations for this article" to trigger the skill.
View source on GitHub ↗License: Apache-2.0