Jev Agent Skills

A CLI from Pinecone's DevRel team for testing Agent Skills and docs against tasks: run tasks across Claude, Copilot and Gemini in local or Modal sandboxes, compare with-skill, without-skill and with-docs variants, and grade with Claude or a TypeSafe System One backend.

A local Python service that keeps your skill catalog out of the main model's context: it reads your SKILL.md library, asks Jev which skills fit, and returns only the selected instructions through a single read-only MCP tool, with Claude Code, Codex, and Cursor adapters.

A Hermes Agent skill that turns an intention into a written finish line: machine-checkable requirements run as shell commands, fuzzy ones go to Jev for calibrated probabilities, and exit 1 names the weakest unmet requirement.

A Python CLI that ranks your own agent skills against a request so your agent can suggest the right one to invoke, printing JSON with a fit probability per skill and a gate probability for whether any skill applies. Ranking runs on Jev and costs two calls, 1.9 seconds on average.

Cisco's security scanner for agent skills added a System One analyzer: it sends the full skill text to POST /v1/systemone as one advisory Noul question and records the probability, while being deliberately unable to emit a finding or change a severity.