gabbe-ai

Plugin gabbe-ai from marketplace gabbe in andreibesleaga/GABBE. Commands read from the repo's manifest — yesterday.

Skills (11)

• a2ui-protocols

  Design and enforce Agent-to-UI communication protocols. Use when: design agent ui protocol, implement a2ui, build genui.

• actor-agent-frameworks

  Implement and manage Actor and Agent Frameworks (e.g. LangGraph). Use when: setup langgraph, implement actor framework, configure agent framework.

• agent-communication

  Establish Agent-to-Agent (A2A) communication channels and topologies. Use when: setup swarm communication, implement a2a protocol, connect agents using mcp, design gossip protocol.

• agent-ui

  Build specialized user interfaces for interacting with Agents. Use when: build agent ui, create tracing dashboard, implement agent front-end.

• autonomous-swarm-patterns

  Implement self-organizing autonomous swarm architectures. Use when: implement swarm, deploy autonomous agents, setup swarm consensus.

• beyond-llms

  Implement advanced neuro-symbolic and genetic algorithm techniques. Use when: implement active inference, add neuro-symbolic logic, optimize using genetic algorithms.

• context-engineering

  Engineer what enters the model's context window for reliability and cost using Write, Select, Compress, and Isolate. Use when: context engineering, context window budget, context rot, prompt caching, just-in-time retrieval, context compaction, sub-agent context isolation, tool output distillation.

• llm-as-judge

  Score open-ended LLM/agent outputs with another LLM as evaluator while controlling for known judge biases. Use when: score open-ended output, llm as judge, evaluation rubric, pairwise comparison eval, judge bias mitigation, calibrate judge against humans.

• multi-agent-systems

  Orchestrate Multi-Agent System (MAS) architectures. Use when: design mas, setup multi-agent, orchestrate agents.

• rag-evaluation

  Evaluate retrieval-augmented-generation pipelines with reference-free metrics to detect silent retrieval and grounding failures. Use when: evaluate rag pipeline, measure faithfulness, context precision recall, detect rag hallucination, reference-free rag metrics, score retrieval quality.

• reasoning-patterns

  Select and apply test-time reasoning techniques (chain-of-thought, self-consistency, tree-of-thoughts, least-to-most, step-back, ReAct, reflexion) by cost, latency, and problem shape. Use when: chain of thought, self-consistency, tree of thoughts, least to most, step-back prompting, test-time comput

Similar plugins