This project offers an AI-powered operational assistant for WeChat official accounts, automating the full content lifecycle from topic ideation to publishing. It targets users seeking streamlined operations without requiring design or coding expertise, providing a comprehensive, end-to-end solution.

How It Works

It utilizes a modular "Skill" architecture compatible with various AI agents (OpenClaw, Cursor, etc.). Users configure preferences via a web UI (aiworkskills.cn) or config files. A sequence of 9 specialized AI skills—topic selection, writing, review, formatting, image generation, publishing, and asset management—executes the workflow. This modular design ensures flexibility and customization.

Quick Start & Requirements

Installation is simplified via AI chat commands (e.g., "Install this skill: [URL]") for Claw agents or repository cloning for others. Configuration is primarily handled through the aiworkskills.cn visual platform, generating .aws packages for personalized settings. Requirements include a compatible AI agent and LLM access (API keys).

Highlighted Details

• 9 Core Skills: Automates topic research, writing, review, Markdown-to-HTML formatting, image generation, direct WeChat publishing, and asset management.
• Visual Configuration: aiworkskills.cn allows intuitive setup for account positioning, writing styles, visual themes, cover/image styles, and publishing parameters.
• Business Data Library: .aws-article/products/ stores product-specific context for AI reuse, enhancing content relevance.
• Broad LLM Support: Integrates numerous LLMs and OpenAI-compatible APIs, with local API key storage.

Maintenance & Community

Active development is indicated by frequent updates. Community support is available via GitHub Discussions and Issues.

Licensing & Compatibility

Released under the Apache License 2.0, permitting commercial use and integration into closed-source projects.

Limitations & Caveats

Advanced customization requires direct config file editing. Recent updates focus on mitigating "AI taste" in content, suggesting ongoing refinement. Reliance on external LLM and WeChat APIs introduces potential points of failure.