Aaronontheweb

Ralph Run Diagnostics — Productivity skill for Claude Code

Productivity community

Evaluates whether the RALPH loop followed policy: correct task selection, verification level selection, required tests, skill usage, logging completeness, and justification for deviations.

How to install Ralph Run Diagnostics

Installs to ~/.claude/skills/aaronontheweb-netclaw-ralph-run-diagnostics/SKILL.md

Terminal

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

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

What Ralph Run Diagnostics does

name: ralph-run-diagnostics description: Evaluates whether the RALPH loop followed policy: correct task selection, verification level selection, required tests, skill usage, logging completeness, and justification for deviations.

RALPH Run Diagnostics (System-Performance)

Goal

Determine whether the agent system behaved correctly: followed RALPH rules, used required skills, chose correct verification levels, and produced adequate evidence.

This is NOT a code correctness review. It

Alternatives in Productivity

Configure Claude HUD — FIRST: Use the Read tool to load ~/.claude/plugins/claude-hud/config.json if it exists 10.9k ★
C-level Advisor — Executive advisory skills for C-level decisions 5.3k ★
Om Correct — Sweep a corrected fact through the vault — finds every note restating it, applies the correction at the single 4.6k ★