Agent Skills Hub

Observability

Real-time observability dashboard for PAI multi-agent activity, featuring live WebSocket streaming, session tracing, and agent workflow debugging.

data-extraction-patterns

Proven patterns for extracting, caching, and processing analytics data from GA4 and GSC using MCP servers.

event-store-design

Design and implement robust, scalable event stores for event-sourced systems, covering architectural patterns, technology selection, and persistence strategies.

markdown-converter

Convert various documents, media, and web content into Markdown using markitdown, ideal for LLM processing and text analysis.

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.

context-compression

Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.

vibe-prd

A structured PRD generator for vibe-coding MVPs. It guides you through defining product requirements, target audiences, and success metrics, ensuring a clear foundation for your development workflow.

archon

Interactive Archon integration for knowledge base and project management. Features RAG-powered semantic search, website crawling, document versioning, and hierarchical task management via REST API.

guard

Epistemic safety analysis for JSON data in prompts to prevent LLM hallucinations and reasoning errors when handling incomplete or large-scale datasets.

document

Interactive terminal canvas for rendering, editing, and selecting markdown text, emails, and project documentation in Claude Code.

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.