← ClaudeAtlas

polishlisted

Iteratively refines any artifact (prose, spec, prompt, API design, SKILL.md, code snippet) by running a decoupled evaluator → generator loop until explicit criteria are met or an iteration cap is reached. Locks criteria in Wave 1, isolates the evaluator from generation history to prevent sycophancy, and emits the best version with any remaining gaps flagged at cap.
griffinwork40/agent-afk · ★ 54 · AI & Automation · score 77
Install: claude install-skill griffinwork40/agent-afk
## Sub-agent contract /contract `polish` is a three-wave evaluator-optimizer loop that applies to any artifact at any workflow stage. Wave 1 locks concrete, testable criteria. Waves 2 and 3 alternate (evaluator → generator) until all criteria pass or the iteration cap is reached. The evaluator is always spawned stateless — it never sees prior generation history — eliminating the sycophancy failure mode that plagues shared-context review loops. The orchestrator coordinates but never edits the artifact directly. All revisions are produced by the Wave 3 generator, which receives only the `blocking_gaps` list from the evaluator (not its full reasoning). This constraint prevents scope-creep revisions and keeps each iteration focused on the delta between current state and the locked criteria. On cap exhaust the orchestrator emits the best-scoring version plus a structured `remaining_gaps` report so the caller can decide whether to extend the cap, escalate to a human, or ship with known gaps documented. --- ## Inputs | Field | Required | Description | |---|---|---| | `artifact` | yes | The text, spec, prompt, design doc, or code snippet to refine | | `goal` | yes | Natural-language quality intent ("make this safe for external stakeholders") | | `criteria` | no | Pre-supplied testable criteria — skips Wave 1 extraction if provided | | `threshold` | no | `pass_all` (default) or `pass_N` where N is an integer | | `cap` | no | Max refinement iterations (default: 4, max: 8) | ---