浏览和安装 Killer-Skills 目录中的数千个 AI Agent 技能。支持 Claude Code、Windsurf、Cursor 等。
The code-review-assist skill enhances human-in-the-loop review sessions for Claude Code users, helping developers evaluate code changes faster and more thoroughly. It assists in preparing users to review faster, surfacing key points, drafting comments, and tracking review process improvements.
Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator
The memory layer for AI-native development — giving AI persistent understanding of your software projects.
Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review.
Autonomous orchestration framework for Claude Code with MemPalace-inspired memory (4-layer stack, 818-token wake-up), parallel-first Agent Teams (6 teammates), Aristotle First Principles methodology, and 4-stage quality gates. 925+ tests, 22 active hooks, automatic learning pipeline.
Orchestration system for Claude Code with memory-driven planning, multi-agent coordination, Agent Teams integration, automatic learning, and comprehensive security validation (Grade A-). v2.94.0
Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for orchestration. Triggers on Team Coordinate .
Multi-CLI collaborative planning and execution skill with integrated execution phase. Triggers on workflow-multi-cli-plan.
Unified team skill for full lifecycle - spec/impl/test. All roles invoke this skill with --role arg for role-specific execution.
/Lumina-Intelligence, /Luminor-intelligence & /StarlightOrchestrator building Arcanea with swarm intelligence that overlays any AI. Ten Gates, Guardians & Godbeasts, context that compounds, and the creative civilization OS for creators who build universes.
Thoughtbox 是一个 AI 意图账本，用于评估和跟踪 AI 决策
Multi-agent system for software development