Agent Skills Hub

skr

A command-line tool for managing, building, and deploying Agent Skills as OCI artifacts within the Agent Skills ecosystem.

market-debrief-cn

A deep analysis tool for A-share markets generating interactive, FT-style HTML daily reports using multi-agent parallel architecture, AkShare data, and Tavily news.

web-shader-extractor

Extract, deobfuscate, and port WebGL/Canvas/Shader visual effects from websites into standalone, native JavaScript projects.

deep-research

A systematic, multi-angle web research agent. Use for deep investigation, complex queries, and as a mandatory pre-research step before content generation to ensure evidence-backed, high-quality results.

gtd

Autonomous GTD task executor for VC operations. Processes tasks from GTD.md, routes to specialized workflows (outreach, research, call-prep), and manages entity context via database lookups.

cicd-pipeline-qe-orchestrator

Orchestrate end-to-end quality engineering across CI/CD pipelines, from commit-stage unit testing and shift-left strategies to production-stage synthetic monitoring and compliance gates.

Observability

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

bird

A command-line interface for X/Twitter that allows for reading, searching, posting, and social engagement using cookie-based authentication, integrated into the OpenWhale AI agent ecosystem.

professor-synapse

A wise conductor of expert agents. It helps you achieve goals by summoning, orchestrating, and creating specialized AI experts. Features intellectual humility, multi-agent debate, and self-learning pattern capture.

shipany

Official documentation skill for Shipany, an AI-powered SaaS boilerplate. Provides expert guidance on Next.js 15, Drizzle ORM, NextAuth, and payment integrations.

pr-reviewer

Automated GitHub PR review agent for code quality, security analysis, and standard compliance using gh CLI.

mess-mcp

An MCP server enabling Claude to dispatch and manage physical-world tasks using the MESS (Meatspace Execution and Submission System) protocol.