# Eval

> Use this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed orchestrator session against the pre-registered rubric-v1 dimensions, run /eval, evaluate this session, produce an eval report, or re-verify a stored eval run for reproducibility. Deterministic-first with an optional advisory LLM judge; never produces a global score.

- Skill: `kanevry/eval` (Agent Skill)
- Install (CLI): `npx skillmds@latest add kanevry/eval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kanevry/eval/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Kanevry (https://skillmd.com/u/kanevry)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/kanevry/eval

---


# eval

Canonical skill: `skills/eval/SKILL.md`

Read that file and follow it exactly. Resolve relative links against `skills/eval/`, not this wrapper.

Cursor has no Skill tool. Treat "invoke the eval skill" as: Read `skills/eval/SKILL.md`.