Aaronontheweb

Ralph Output Adversarial Review — Testing skill for Claude Code

Testing community

Adversarially reviews the artifacts produced by a RALPH run (code/tests/UI/config) against repo policy (testing-strategy, architecture).

How to install Ralph Output Adversarial Review

Installs to ~/.claude/skills/aaronontheweb-netclaw-ralph-output-adversarial-review/SKILL.md

Terminal

mkdir -p ~/.claude/skills/aaronontheweb-netclaw-ralph-output-adversarial-review && curl -fsSL https://raw.githubusercontent.com/Aaronontheweb/netclaw/HEAD/.claude/skills/ralph-output-adversarial-review.md -o ~/.claude/skills/aaronontheweb-netclaw-ralph-output-adversarial-review/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Ralph Output Adversarial Review does

name: ralph-output-adversarial-review description: Adversarially reviews the artifacts produced by a RALPH run (code/tests/UI/config) against repo policy (testing-strategy, architecture). Produces fix-it tasks (NOW vs PARKED) with objective DoD and verification levels.

RALPH Output Adversarial Review (Artifact-Quality)

Goal

Critically evaluate the OUTPUT of the RALPH run: code, tests, UI, configuration. This is a correctness/completeness review against repo policy and architecture

Alternatives in Testing

#29 — #52, #103) 92.5k ★
Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
Grid Tester — Use the @grid-tester agent for test strategy, TDD, or flaky test diagnosis: $ARGUMENTS 523 ★