skill-router

Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.

How it uses Jev

1. You start a Claude Code session in a project where skill-router is set up. 2. If your first message makes the goal clear, Claude works it out. If not, Claude asks one question: "What are you trying to get done this session?" 3. Claude runs skill-router intent set " " . 4. The tool lists every skill installed on your machine and asks Jev, a decision model from TypeSafe AI, to rank them against your goal. Jev is no…

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to skill-router

Browse all
jev-agent-skill-router project preview
Typed, confidence-aware agent skill routing with TypeSafe Jev.
jev-skill-suggester project preview
Agent tooling
用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.
everything-about-jev project preview
tell you everything about jev,TypeSafe AI's System One model for typed decisions.
langchain-loadout project preview
Integrations
Per-turn skill selection for LangChain and deepagents agents: a fast judge picks the few skills a turn needs, so a catalog of hundreds stays out of the prompt.
jev-kit project preview
Browser & computer use
Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers.
hermes-jev-skills project preview
Browser & computer use
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
jev-lens.nvim project preview
Integrations
Neovim popup for jev-lens verdicts: do I need to look, which files, and strip the debris.
system-one-router project preview
Benchmarks & research
A fast System One decision model (Jev or local Laya) picks which LLM answers each prompt: OpenAI-compatible Go gateway + decision benchmark