wechat-studio
Launch a local WeChat article workbench for Markdown import, WeChat HTML preview, theme tuning, image selection, and optional draft push. Use when Codex needs a browser-based preview and manual QA layer before publishing.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/abigale-cyber/content-system-wechat-studioWeChat Studio
Use wechat-studio as the manual workbench between generated article assets and final publishing. On ClawHub, this skill is published as content-system-wechat-studio.
Quick Start
Install the shared Python dependencies and the workbench frontend dependency:
.venv/bin/pip install -r requirements.txt
cd skills/wechat-studio/frontend && npm install
Start the local server:
python3 skills/wechat-studio/frontend/server.py
Open the workbench in the browser:
http://127.0.0.1:4173
The image defaults shown in the settings page should reflect the adjacent generate-image runtime:
provider: openai
api base: https://new.suxi.ai/v1
model: nano-nx
Use This Skill When
- You need a local WeChat preview before publishing
- You want to import Markdown into a reusable article workspace
- You want to adjust theme, typography, and layout manually
- You need to review cover images or inline image slots
- You want to push a checked article into the WeChat draft box
Default Workflow
- Start the server and open the local workbench.
- Import a Markdown article or switch to an existing article workspace.
- Review the generated WeChat preview and article metadata.
- Tune theme, typography, cover, and inline images.
- Push the final checked version to the WeChat draft box if needed.
Use the settings page to distinguish:
- configured image values from the current
md2wechatsetup - effective image values that
generate-imageactually injects at runtime
Related Skills
wechat-formatterprovides the WeChat HTML render stepgenerate-imageprovides the article companion imagescase-writer-hybridandhumanizer-zhtypically feed the upstream article draft
Notes
- This is a workbench skill, not a pure one-shot executor
- Draft push depends on the local WeChat publishing configuration already being available
- Article workspaces live under
skills/wechat-studio/content/articles/ - Users with an existing 香蕉制作平台 can use it directly
- Users without one can open job.suxi.ai, generate an
SK, place it into the token field, and log in
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-abigale-cyber-content-system-wechat-studio": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
humanizer-zh
Remove obvious AI-writing traces from Chinese text in a constrained way. Use when Codex needs to reduce AI smell without changing facts, data, or the article's core argument.
news-aggregator-skill
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 28 sources including Hacker News, GitHub, Hugging Face Papers, AI Newsletters, WallStreetCN, Weibo, and Podcasts. Use when user requests 'daily scans', 'tech news', 'finance updates', 'AI briefings', 'deep analysis', or says '如意如意' to open the interactive menu.
feishu-bitable-sync
Sync a local `wechat-report` result into Feishu Bitable after the user has reviewed the report and confirmed the sync.
wechat-formatter
Render article markdown into WeChat-style HTML as an independent executor. Use when Codex needs公众号排版预览, WeChat HTML output, or a publishable HTML artifact generated from an article markdown draft.
tavily-research
Conduct comprehensive AI-powered research with citations via the Tavily CLI. Use this skill when the user wants deep research, a detailed report, a comparison, market analysis, literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", "what does the market look like for", or needs multi-source synthesis with explicit citations. Returns a structured report grounded in web sources. Takes 30-120 seconds. For quick fact-finding, use tavily-search instead.