consensus-mechanisms
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.
LangChain tool creation and integration utilities for agent systems
Generate MCP capability declarations from tool and resource inventory with proper versioning and feature flags.
Map application errors to MCP error codes with proper messages, error types, and recovery suggestions.
Token-efficient prompt compression techniques for cost optimization
Query expansion, HyDE, and multi-query generation for improved retrieval
Design and train reinforcement learning agents — environment setup, reward shaping, policy gradient methods, and evaluation.
RL training for robot control using simulation with sim-to-real transfer