SkillProof tested Claude skills

Multi-Model Adversarial Review

Runs claude/codex/gemini as independent reviewers, has them cross-critique, then synthesizes one deduped report

di prime-radiant-inc · prime-radiant-inc/parallel-adversarial-review

Richiede configurazione ★ 8.0/10

Multi-Model Adversarial Review — Runs claude/codex/gemini as independent reviewers, has them cross-critique, then synthesizes one deduped report

Cosa fa

A three-stage driver (parallel review, NxN-1 cross-critique, synthesis) that shells out to whichever coding-agent CLIs you have installed, drops findings a critic proves are fabricated, and escalates severity on disagreement. Triggers on 'MMAR review', 'multi-model review', 'cross-model adversarial', or 'review with all the models' for high-stakes diffs; the project's own guidance says to use its cheaper sibling skill for routine review.

Rapporto di test

The SKILL.md body calls ${CLAUDE_PLUGIN_ROOT}/scripts/mmar.py, a 645-line driver that lives at the repo root, not inside the skill folder -- a bare copy 404s in real GitHub raw fetches and errors 'No such file or directory' when actually run; but running the real driver in the project's own mock mode against its bundled fixtures worked perfectly (4/4 eval fixtures passed, and it correctly caught and dropped a fabricated Gemini finding that two other reviewers flagged as fiction) -- so the mechanism itself is genuinely good, it just needs the whole repo/plugin, not the skill subfolder alone.

Testato il: 2026-07-15 · Claude Code 2.x (agent harness)

Installazione

git clone https://github.com/prime-radiant-inc/parallel-adversarial-review
cd parallel-adversarial-review
mkdir -p ~/.claude/skills
cp -r skills/multi-model-adversarial-review ~/.claude/skills/multi-model-adversarial-review

Comandi e prompt di esempio

  • /multi-model-adversarial-reviewRuns claude/codex/gemini as independent reviewers, has them cross-critique, then synthesizes one deduped report

Gli skill si attivano con richieste in linguaggio naturale, senza comandi da ricordare. Dopo l'installazione, prompt come questi lo attivano (in inglese):

  • Run a full cross-model review on this PR before we merge to main
  • This diff is security-critical, get several models to cross-check each other
  • One reviewer isn't enough here, have Claude, Codex, and Gemini all weigh in

Rapporto completo →