eval-looplisted

Use to run a quality check on any generated artifact, or when the user says "evaluate this", "score this draft", "is this good enough", "run the eval", "review this output", "check it against the rubric". Runs generate, judge, revise, re-judge, approve with the judge in a separate context so nothing grades its own work. Logs every cycle including failures. Writes to workspace/evals/log/. Scores your AI system output against a rubric you wrote. Not for writing that rubric (`eval-spec-authoring`), and not the pre-handoff gate on a deliverable this repo produced, which is `artifact-eval`.
guerrilla2799/ops-and-scale-os · ★ 1 · AI & Automation · score 74

Install: claude install-skill guerrilla2799/ops-and-scale-os

# Eval Loop Generate, judge independently, revise, re-judge, approve. The separation between generator and judge is structural, and it is the highest-leverage architectural choice in this repo. ## When to use - Any artifact with an eval spec is produced - Before anything reaches an external surface - Spot-checking a batch of agent output - A quality complaint needs diagnosing ## Inputs - Reads: `workspace/evals/specs/<type>.md`, the draft - Needs from user: the artifact type, and a title for the log entry ## Workflow ### 1. Understand why separation is not optional A context that produced a draft knows what it meant. Asked to grade it, it reads its own intent rather than the text, and passes almost everything. Moving the same rubric into a genuinely separate context that receives only the artifact and the spec drops pass rates substantially, and what it starts catching is what a reader would have caught. **A different prompt in the same context is not independence.** Independence is a separate context window that never saw the reasoning. ### 2. Run the loop ``` GENERATE the draft, in its own context ↓ JUDGE separate context. Receives ONLY the artifact + the spec. Runs gates, then dimensions, then verdict. Never revises. Returns verdict + guidance + a log line. ↓ ├── PASS → approve, return with the receipt ├── REVISE → REVISE (separate context again) │ Receives draft + verdict. Fixes the named weaknes