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

WeChat Official Account End-to-End Article Orchestrator

A master entry-point skill that chains eight sub-skills to take a WeChat Official Account article from topic selection all the way to publishing in one request.

AutomationAdvanced★ 564⑂ 87AI score 8/10Last updated: Sep 6, 2026

What it does

  • Orchestrates the full WeChat Official Account content pipeline from one entry point: topics → writing → content review → formatting/HTML → images → final review → publish.
  • Enforces a blocking environment check before any drafting: verify .aws-article/config.yaml and aws.env exist, run validate_env.py (must exit 0), then create preset and tmp directories.
  • Includes OS-aware Python detection rules (py -3 -X utf8 on Windows, python3 on macOS/Linux) plus a Python 3.10+ requirement, avoiding GBK mojibake and the Microsoft Store alias trap.
  • Uses artifact gates so steps cannot be skipped: no formatting without a non-empty article.md; no "done" claim if cover.* is missing or placeholder still appears in the body.
  • Publishing safety: publish_method defaults to draft (drafts box only); real publishing requires an explicit user request via published or full --publish.
  • Clear credential policy: the agent must never ask for or accept AppSecret/API keys in chat; it only checks that keys exist and are non-empty.

Who it's for

  • WeChat Official Account editors, self-media creators, and brand content teams
  • Chinese-market content operators repeating topic research, drafting, proofing, layout, imagery, and posting by hand
  • Teams running multiple accounts (WECHAT_1, WECHAT_2 …) who want tone and publishing policy stored in config files

Examples

  1. Full run: "Produce a complete WeChat article on topic X" → env check, title and slug confirmation, create drafts/20240101-title-slug/, init article.yaml, run all six stages, land in the drafts box.
  2. Resume: "Continue yesterday's piece" → the skill inspects existing artifacts (draft.md, article.md, article.html) and restarts from the right stage.
  3. Swap images and repost: "I don't like the draft images, use the ones I uploaded" → drop images into imgs/, set image_source: user, re-format, final review, then rerun publish.py full.

· · · 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-main/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-main folder from the GitHub repo aiworkskills/wechat-article-skills into my ~/.claude/skills/aws-wechat-article-main/.
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 go to your working directory.
  2. Clone the repo: git clone https://github.com/aiworkskills/wechat-article-skills.git
  3. Create the skills folder and copy all nine slugs (installing only main will break the pipeline): mkdir -p ~/.claude/skills && cp -r wechat-article-skills/skills/* ~/.claude/skills/
  4. Confirm Python 3.10+ is available: python3 --version on macOS/Linux, py -3 --version on Windows.
  5. In your project root, create aws.env and fill WRITING_MODEL_API_KEY, IMAGE_MODEL_API_KEY, WECHAT_1_APPID, WECHAT_1_APPSECRET yourself in an editor (never paste secrets into chat).
  6. In the same root, create .aws-article/config.yaml; copying ~/.claude/skills/aws-wechat-article-main/references/config.example.yaml is easiest, and keep publish_method: draft.
  7. Validate: python3 ~/.claude/skills/aws-wechat-article-main/scripts/validate_env.py (exit code 0 means ready).
  8. In Claude Code, say something like "write and publish a full WeChat article" to trigger the skill.
View source on GitHub ↗License: Apache-2.0