Profile My skills Saved My plugins Edit profile Submit a skill

Agent Eval Harness

Agent Eval Harness from plaited/agent-eval-harness.

by @plaited 3 skills

Skills in this plugin

3
  1. ▌
    Trial Runner · plaited
    End-to-end eval-suite orchestration with the `eval` command: run -> grade -> compare -> calibrate, using strict JSON contracts and schema discovery.
    1 install
  2. ▌
    Compare Trials · plaited bundle
    Analyze graded `trial_result` JSONL outputs from the eval pipeline, including reliability and custom slicing.
    1 install
  3. ▌
    Trial Adapters · plaited
    Build command-only adapters for `eval` run mode using strict stdin/stdout JSON contracts.
    1 install