Evaluate Presets

Evaluate Presets is a Quality skill for Claude Code, published by mikeyobrien in ralph-orchestrator.

3.1K stars285 forkson mikeyobrien/ralph-orchestratorAdded 2026/08/17Repository updated 2026/08/16

aiai-agentsai-agents-frameworkai-developer-toolsclaude-codeclaude-code-clicodex-clidevelopment-toolsdevelopment-workflowgemini-clikirokiro-cliopencoderalph-loopralph-wiggum

Install in seconds

Install Evaluate Presets

Copy Evaluate Presets into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/mikeyobrien/ralph-orchestrator/tree/main/.claude/skills/evaluate-presets ~/.claude/skills/evaluate-presets

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/mikeyobrien/ralph-orchestrator.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/evaluate-presets/SKILL.md in mikeyobrien/ralph-orchestrator
Installs to: ~/.claude/skills/evaluate-presets
Collection: One of 20 skills cataloged from this repository
Category: Quality — 1354 skills

What Evaluate Presets does

Evaluate Presets runs shell scripts to test Ralph's hat collection presets, validating configurations and auditing the preset library for bugs and UX issues.

Evaluate Presets is cataloged under Quality on DirSkills. Evaluate Presets comes from a repository tagged ai, ai-agents, ai-agents-framework, ai-developer-tools and claude-code.

Documentation

README

Excerpt

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:

This is the opening of the README. Read the full README on GitHub.

Commands Evaluate Presets provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/code-task-generator
/code-assist

Frequently asked about Evaluate Presets

What else does mikeyobrien publish alongside Evaluate Presets?
Evaluate Presets is one of 20 skills that DirSkills catalogs from mikeyobrien/ralph-orchestrator, the repository it ships in. Its siblings there include Code Assist, Code Task Generator and Complex Test. Each one is a separate skill with its own page in this directory, installs the same way Evaluate Presets does, and is maintained by mikeyobrien in that same repository. The rest of the collection is listed on the mikeyobrien/ralph-orchestrator page.
How does Evaluate Presets compare to other Quality skills?
Evaluate Presets ranks #419 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Evaluate Presets against them. Open each page to compare what they document and how they install.