jev-agent-skill-router
Typed, confidence-aware agent skill routing with TypeSafe Jev.
How it uses Jev
68 of 72 synthetic requests routed correctly (94.4%), versus 51 of 72 (70.8%) for a lexical baseline. The final TypeSafe Jev run selected no wrong skills and made no needless loads, but returned three unnecessary reviews and one client-validation failure. Median end-to-end latency was 1,287 ms , with p95 1,406 ms .
Highlights
- route , no skill or review , with a selected skill only for route ;
- a three-valued specialist-needed judgement and its Noul probability;
- final Choice confidence and winner probability;
- every call's actual candidates, distribution and independent judgement evidence;
- measured end-to-end and per-call latency, plus API-returned token usage.
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.