Purity — Testing skill for Claude Code
Test the product.
How to install Purity
Installs to ~/.claude/commands/derekherman-walter-purity.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/derekherman/walter/HEAD/.claude/commands/purity.md -o ~/.claude/commands/derekherman-walter-purity.md Restart Claude Code, or start a new session, for it to be picked up.
What Purity does
name: purity description: Test the product. Tests passing ≠ done right. Does the work match the formula? 99.1% or nothing. argument-hint: "[scope]"
/purity
99.1% pure.
Intent
You're verifying quality. Not "does it run" — does it actually work? Does it match the intent? Tests passing is not the same as done right.
Load Skill
Load the `walter` skill first. Then read its `quality`, `execution`, and `decomposition` references. If the work involves frontend, UI, or vis
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- /test-factory - Test Generated Skills Or Agents — Quick testing helper for generated skills and agents to ensure they work correctly 618 ★
- Adversarial Spec — A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a 514 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
TDD Implement
by jerseycheese - Implements Test-Driven Development by analyzing feature requirements, creating tests first (
Claude Code Receipts
Claude Code plugin that checks the agent's end-of-turn claims against what it actually did this session — flag
Red First Review Skill
Review a PR by measuring which of its own guards its own test suite actually catches. Neutralise each guard, r
Se Test
The general red-first rule — design any test so you have seen it fail for the right reason before you trust it
QA Release
Run the release QA gate before calling feature or project work done.
Rogue Ab Test Setup Skill
Design, analyze, and document A/B tests for conversion, onboarding, pricing, lifecycle, and product experiment
Related Agents
Refuting Reviewer
Independent reviewer that cannot edit files and tries to refute a claim that work is done, fixed, passing or s
Execution
Reviews whether the task actually got done — plan followed, work finished rather than finished-looking, nothin
QA Test Engineer
Use this agent when you need to verify that features work correctly, ensure product quality, validate performa