Agent Skills Hub

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

hegelion

Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.

scrum-master-agent

Production-ready Scrum Master assistant for sprint management, capacity planning, and real-time team analytics.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.

web-search

Autonomous research specialist for verified information gathering, source evaluation, and structured synthesis.

ai-collaboration-standards

Prevents AI hallucination and ensures evidence-based, verifiable outputs when analyzing code, reviewing technical documents, or providing recommendations.

playwright-skill

Complete browser automation with Playwright. Features local dev server detection, script generation, screenshot capture, form filling, responsive testing, and UX validation.

videocut:剪口播

AI-powered video editing agent for talking head videos, featuring speech-to-text, disfluency detection, and browser-based review workflows.

calendar

Manage calendar events, check availability, and schedule meetings seamlessly during or outside of voice and text interactions.

api-test-automation

Comprehensive API test automation suite supporting REST/GraphQL. Features functional, performance, and contract testing with integrated Mock services.

agent-system

Implementation patterns for MERIDIAN autonomous AI agents using Claude API, including BaseAgent lifecycle, structured tool use, token budget enforcement, and cron scheduling.

hylo-ghl

GoHighLevel workflow automation expert. Integrates with Hylo GHL API to manage workflows, API endpoints, UI navigation, and automation planning.