reviewing-code-prior-art-survey — SKILL.md

Variant: standard · When to use: judging a produced prior-art artifact (keyword map, per-angle search output, or extraction) — deciding whether it is sound enough to build on, then emitting one verdict — VERDICT: approve|revise by default — with actionable findings.

Overview

This skill is the acceptance gate over the search wave of an open-source code prior-art survey — the independent reviewer for what code-prior-art-survey produces. Loaded by a reviewer holding the artifact (and the scope context it was made for), it answers one question: is this search artifact sound — honest, complete against its own contracts, and proportionate — enough for the survey's later stages to build on? It applies a fixed twenty-two-condition bar, then emits a single machine-parseable verdict plus findings the producer acts on.