Doubt-Driven Review

Adversarial pre-mortem gate for risky diffs, migrations, and 'this is safe' claims

Autor: pimenov · pimenov/codex-first-skills-pack

Testowano · Działa ★ 9.2/10

Doubt-Driven Review — Adversarial pre-mortem gate for risky diffs, migrations, and 'this is safe' claims

Co robi ten skill

A single self-contained methodology skill: state the claim, extract artifact+contract, run an adversarial 'find what's wrong' review (fresh subagent, external CLI with approval, or labeled degraded self-review), classify every finding, and stop only on a defined exit condition. Triggers before production, auth, data, billing, or irreversible changes are allowed to stand as 'safe' or 'done'.

Raport z testu

Ran a real prod-column-drop scenario baseline-vs-skill: baseline gave a decent ad-hoc safety checklist, the skill forced an explicit CLAIM/CONTRACT/adversarial-findings structure that surfaced a missing-backup gap and a lock-contention-under-load edge case the baseline only hinted at, and ended in an auditable 'revise, don't approve yet' decision instead of a soft 'looks fine if...'.

Testowano: 2026-07-14 · Claude Code 2.x (agent harness)

Instalacja

git clone https://github.com/pimenov/codex-first-skills-pack
cd codex-first-skills-pack
mkdir -p ~/.claude/skills
cp -r skills/doubt-driven-review ~/.claude/skills/doubt-driven-review

Komendy i przykładowe prompty

/doubt-driven-reviewAdversarial pre-mortem gate for risky diffs, migrations, and 'this is safe' claims

Skille uruchamiają się na zwykłe polecenia — bez komend do zapamiętania. Po instalacji aktywują go prompty takie jak te (po angielsku):

Is it actually safe to drop this column in production?
Pre-mortem this migration before I ship it tomorrow
Challenge my claim that this refactor is behaviour-preserving

Pełny raport →