Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.
metadata
{"internal":true}
Evaluate Presets
Overview
Systematically test all hat collection presets using shell scripts. Direct CLI invocationโno meta-orchestration complexity.
When to Use
Testing preset configurations after changes
Auditing the preset library for quality
Validating new presets work correctly
After modifying hat routing logic
Quick Start
Evaluate a single preset:
./tools/evaluate-preset.sh tdd-red-green claude
Evaluate all presets:
./tools/evaluate-all-presets.sh claude
Arguments:
First arg: preset name (without .yml extension)
Second arg: backend (claude or kiro, defaults to claude)
Bash Tool Configuration
IMPORTANT: When invoking these scripts via the Bash tool, use these settings:
Single preset evaluation: Use timeout: 600000 (10 minutes max) and run_in_background: true
All presets evaluation: Use timeout: 600000 (10 minutes max) and run_in_background: true
Since preset evaluations can run for hours (especially the full suite), always run in background mode and use the TaskOutput tool to check progress periodically.
completed โ Whether completion promise was reached
Hat Routing Performance
Critical: Validate that hats get fresh context per Tenet #1 ("Fresh Context Is Reliability").
What Good Looks Like
Each hat should execute in its own iteration:
Iter 1: Ralph โ publishes starting event โ STOPS
Iter 2: Hat A โ does work โ publishes next event โ STOPS
Iter 3: Hat B โ does work โ publishes next event โ STOPS
Iter 4: Hat C โ does work โ LOOP_COMPLETE
Red Flags (Same-Iteration Hat Switching)
BAD: Multiple hat personas in one iteration:
Iter 2: Ralph does Blue Team + Red Team + Fixer work
^^^ All in one bloated context!
