Results for skill-router

Local semantic skill router for gemini-cli-pro

Deterministic skill router for OpenCode — saves ~90% tokens by hiding skills from the system prompt and routing via keyword matching

Agent skills, MCP skill-router server, and dev tooling for Claude, Copilot, and other AI assistants

TF-IDF skill router plugin for OpenCode — auto-loads matching skills based on user prompts

OmniCoder core plugin for opencode: skill router (BM25), security guard, token budget, memory loader, personality injector, tool dispatcher, provider failover.

GraphRAG-based skill router for Claude Code — Claude Code plugin (TypeScript port).

iKhono MCP Server — runtime skill router for AI agents

OmniCoder — opencode fork con 170+ agents, skill router BM25, per-phase routing, memory layer y tema morado. Instalable via npm en Linux/macOS/Windows.

Context-aware skill router for Claude Code hooks

<div align="center"> <img src="https://raw.githubusercontent.com/apollographql/apollo-client-integrations/main/banner.jpg" width="500" alt="Apollo Client + Next.js App Router" /> </div>

Agentic Search-inspired non-vectorized routing and management for Agent Skills

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning...

Bayesian skill-rating router for AI agents. Routes tasks to the best specialist using TrueSkill-style ratings that improve with every interaction. Zero LLM calls.

Simple middleware-style router

Declarative routing for React

Modern and scalable routing for React applications

Nested/Data-driven/Framework-agnostic Routing

Modern and scalable routing for React applications

Modern and scalable routing for React applications

Declarative routing for React web applications

Universal skill router for AI agents

Tlon/Urbit skill for OpenClaw agents

Skillflag producer CLI reference implementation.

The open agent skills ecosystem

pikuri-vectordb gives a pikuri-core agent a +vectordb_search+ tool over a local document corpus — agentic search, the agent decides when to retrieve. Ships a swappable backend (a pure-Ruby +Backend::InMemory+ for teaching and a thin +Backend::Chroma+ HTTP client for persistence), a chunker, an embedder wrapper over +RubyLLM.embed+, and an optional +Reranker::LlamaServer+ that speaks +/v1/rerank+ against a cross-encoder model. Text extraction goes through +Pikuri::FileType.read_as_text+ in pikuri-core, which handles plain text / Markdown / PDF; HTML extraction is a deferred follow-up. Hosts wire the feature via +c.add_extension Pikuri::VectorDb::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-skills+. The bundled +Pikuri::VectorDb::LIBRARIAN+ persona is the privilege-separated sub-agent counterpart for hosts that want recall to flow through a child rather than the parent's context. Three model endpoints in the full setup — chat (via ruby_llm), an embedder (via +RubyLLM.embed+), and an optional reranker (HTTP +/v1/rerank+). A single +llama-server+ in router mode serves all three by default, loading each cached GGUF on demand; see the gem's README for details.