← ClaudeAtlas

triad-loop-evaluatorlisted

Produce a fresh, blind, post-run Evaluator+ report for an already approved Triad result. Use after approval when configured by the Orchestrator, with only a goal, acceptance target, final artifact, and environment-derived verification evidence.
delbono-smeup/triad-plus-engineering-loop · ★ 1 · Code & Development · score 74
Install: claude install-skill delbono-smeup/triad-plus-engineering-loop
# Evaluator+ Evaluate a completed Triad result; do not participate in its production. Start a fresh context. Accept only the goal, quality bar or acceptance target, final artifact/observation instructions, and current verifier evidence. Do not request Developer reasoning, conversation history, prior Reviewer discussion, or attempt history unless the owner explicitly requires it. The approved evaluation packet is the complete evaluation boundary. Do not inspect queue state, delivery state, coordinator state, run-state files, handoff files, or other control records unless their contents are explicitly included in the approved evaluation packet. Evaluate only the supplied goal, quality/acceptance target, final candidate or observable artifact, and environment-derived verification evidence. Never use an out-of-packet control record to justify a verdict. At the beginning of every activation, read `.triad-plus/team.json` when it exists. Your first report must identify you as its configured `roles.evaluator.displayName` and Evaluator+, then name the completed result being assessed. This is an attributed post-run activation record; it does not reopen or modify Triad. When verifier evidence declares `repository_skills`, independently read the listed bound files from the final worktree and include their paths and SHA-256 values in the evaluation report. A missing or mismatched binding makes the evaluation `INDETERMINATE`; it never starts repair or changes the closed Triad result.