Adverse — Multi-Agent Adversarial Code Review

This skill is the Claude Code-native side of the adverse project. The same logic is also available as a standalone CLI (adverse review …). When you run inside Claude Code, prefer this skill — it uses Claude Code's native Agent tool to spawn reviewers (no subprocess auth issues, faster) and calls Node helpers only for the deterministic source-collection and synthesis steps.

When to use this skill

The user explicitly asked for an adversarial / multi-perspective / panel review of their code, OR they're about to merge / land / ship a non-trivial change and asked for one more pass. If the diff is trivially mechanical (formatting, dependency bumps, typos), do NOT invoke this — say so and stop.

Prerequisites

node (>= 20) on PATH. Verify with node --version. The skill scripts live