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.
SkillScore68Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/15/2026
What it changes
Passed 10 of 15 test cases with the skill, and 2 of 15 without it.
Without skill14%
With skill68%
Checks it passed that the model alone missed
Configures exit_code as the result_type setting
Recommends proceeding with /ship to create the pull request
Directs the user to fix issues using /go before re-running /eval
and 15 more in the full report
15 fixed0 passed either way4 still failing3 broke
Pass-rate lift
+55 pp
Tokens
+43%
Agent turns
0%
Response time
-77%
Model gemini-3.6-flashMeasured 8/15/2026v215 of 22 cases passed with skill · 15 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
What is the exact relative path under the harness directory where the runner expects to read eval.yaml?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies the configuration file path as $HARNESS_DIR/eval/eval.yaml
Missed
Passed
case-16 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md204 linessingle file
Eval — Quality & Regression Gate
CRITICAL: Run HARNESS_DIR=$(epic path) first. Never use .harness/ in the project directory.
When to Trigger
Before /ship creates a PR (automatic if eval.yaml exists)
After /go completes a feature
On explicit /eval command
When user mentions "regression", "baseline", "eval suite", "quality check"
CI: make eval or epic eval --json
Execution Modes
4 dimensions run in parallel where possible:
eval:correctness — Test pass rate, mutation score, assertion density