@chunhualiao

openclaw-docker-setup guides users through installing and configuring a production-ready dockerized openclaw instance on macos, with multi-instance support, discord integration, and optional gmail and google drive connectivity.

rotate-openrouter-key handles safe replacement of openrouter api credentials across all openclaw config files, with backup, verification, and multi-host support via a helper script.

wechat-article-extractor converts WeChat public account article URLs to clean markdown by attempting direct fetch first, then searching mirror aggregator sites when blocked. includes metadata extraction, image preservation, and chrome relay fallback for niche content.

scrapbook-illustrator generates hand-crafted scrapbook-style images and inserts them into articles at logical break points. supports glm and openrouter providers with parallel image generation and multi-language text handling.

git-repo-to-book orchestrates multi-agent workflows to generate 60k-100k word technical manuscripts from git repositories or topics. supports chapter revision without full regeneration. cost-aware with pre-flight estimation and budget tracking.

skill-mermaid-diagrams automates generation of 12 diagram types with template-based rendering, LLM-powered content creation, and validation. covers architecture, flowchart, sequence, gantt, state, and uml diagrams with consistent styling and error handling.

openclaw-usecase-catalog is a 15-category reference of real-world use cases pulled from community sources, with bilingual findings workflow. lacks procedural depth and actionable steps for implementation.

Extract tweet content from x.com URLs without credentials using browser automation. Use when user asks to "extract tweet", "download x.com link", "get tweet...

Check Claude Max plan usage limits by launching Claude Code and running /usage. Use when the user asks about Claude plan usage, remaining quota, rate limits,...

Generate images using GLM-Image API. Use when the user wants to generate, create, or draw an image from a text prompt. Triggers on requests like "generate an...

Provides a structured 7-phase process to investigate, diagnose, restore, prevent, monitor, and document OpenClaw system failures including config loss, crash...

Release skills to ClawhHub through the full publication pipeline — auto-scaffolding, OPSEC scan, dual review (agent + user), force-push release, security sca...

Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester suba...

Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronousl...

End-to-end 微信公众号 article writing and publishing — from topic ideation to published article, with quality gates.