Agent Skills Hub

llmintegration

Multi-model LLM integration patterns for Claude, GPT, Gemini, and Ollama. Features API handling, prompt engineering, token management, and model-agnostic orchestration.

pali-me

Automatically keep technical documentation in sync with codebase changes by analyzing git diffs.

vvm

VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.

building-logseq-plugins

Expert guidance for Logseq plugin development, specifically optimized for the new database architecture, API integration, and property management.

langgraph-workflows

Master multi-agent orchestration with LangGraph. Build stateful, fault-tolerant AI workflows using supervisor-worker patterns, conditional routing, and advanced state management.

playwright-pro

Production-grade Playwright testing toolkit. Automate E2E testing, fix flaky tests, perform migrations from Cypress/Selenium, and integrate with CI/CD, TestRail, and BrowserStack.

etudes

An aggressive sprint coach that helps builders overcome procrastination and overplanning by generating 5-day actionable tasks, tracking progress, and managing project momentum.

video-watcher

Fetch and parse transcripts from YouTube and Bilibili videos for summarization, QA, and content extraction using yt-dlp.

wrap

Automated session cleanup and documentation tool. Proactively updates CLAUDE.md, detects automation patterns, extracts insights, and organizes pending tasks.

refactoring

Linter-driven refactoring agent that resolves complexity issues like cyclomatic depth, primitive obsession, and long functions using automated pattern extraction.

podcast-downloader

Search, browse, and download podcast episodes from Apple Podcasts via the iTunes Search API. Ideal for archiving audio content, batch downloading, and retrieving rich metadata for research or personal media libraries.

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.