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.
$npx -y skills add kanevry/session-orchestrator --skill evalInstalls into the current project.
Run `npx skills use "https://github.com/kanevry/session-orchestrator" --skill "kanevry/session-orchestrator/eval"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/kanevry/session-orchestrator" that are relevant to the current task. Run `npx skills add "https://github.com/kanevry/session-orchestrator"` and select the relevant skills, then follow their instructions.