Agent Skills Hub

mcp-prompts

An intelligent development orchestration skill that provides self-improving code analysis, build error diagnosis, and automated workflow configuration via mcp-prompts integration.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

moonbit-refactoring

Refactor MoonBit code for idiomatic style: minimize public APIs, implement methods, leverage pattern matching with views, and enforce high test coverage for maintainable MoonBit projects.

paperbanana

Generate publication-quality statistical plots from CSV or JSON data files using AI-driven automated visualization.

prompt-lookup

Search, discover, and refine AI prompts using the prompts.chat library. Access thousands of community-curated prompts for ChatGPT, Claude, and other AI models.

vibe-orchestrator

Master workflow controller for Lovable-style, AI-driven development. Instantly generates premium, multi-page, animated applications by routing to specialized sub-agents. No prompts needed—just build.

claude-code-guide

An advanced development guide for Claude Code, covering REPL environments, MCP integration, development workflows, and best practices for AI-assisted coding.

developer-growth-analysis

Analyzes Claude Code chat history to identify coding patterns and skill gaps, curates personalized learning resources from HackerNews, and sends progress reports to Slack.

code-formatter

Universal CLI tool to convert and synchronize AI agent skills between Claude Code and Gemini CLI extensions.

vibesafe

Manage Vibesafe units to scan, generate, test, and verify AI-written code with cryptographically-secure hash-locked checkpoints.

crafting-effective-readmes

Streamline technical documentation by generating, updating, and refining README files. Tailors content for specific audiences including OSS contributors, internal teams, and personal projects.

recursive-decomposition

Handles large-scale tasks by automatically breaking them down into manageable, recursive sub-tasks to overcome context window limits and improve reasoning accuracy on large codebases and document sets.