Agent Skills Hub

reflect-appworld-failure

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.

mcp-prompts

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

molthouse

API-first casino for AI agents on Base. Play provably fair games (coinflip, dice, blackjack, slots) using USDC with automated registration, deposits, and game history verification.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

risk-based-testing

Focus testing effort on highest-risk areas using risk assessment and prioritization. Use when planning test strategy, allocating resources, or making coverage decisions.

Observability

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

web-search

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

metacognition

Enforces structured self-assessment checkpoints to validate approach, mitigate risks, and ensure quality before, during, and after task execution.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

context-engineering-expert

Advanced context engineering system for orchestrating AI agents, memory management, and token optimization to improve long-term persistence and project intelligence.

hive-mind-advanced

Queen-led multi-agent orchestration for Claude Code, featuring Byzantine consensus, persistent collective memory, and adaptive task distribution for complex software projects.

swarm

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance for complex features, multi-step refactors, and long-running autonomous coding sessions.