Break — Testing skill for Claude Code
Scout the current prompt and repository, then spawn Breaker (Opus) to generate a layered spec/milestones/quality/validation structure under .bnb/ /.
How to install Break
Installs to ~/.claude/skills/mbruhler-break-n-bake-break/SKILL.md
mkdir -p ~/.claude/skills/mbruhler-break-n-bake-break && curl -fsSL https://raw.githubusercontent.com/mbruhler/break-n-bake/HEAD/commands/break.md -o ~/.claude/skills/mbruhler-break-n-bake-break/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Break does
description: Scout the current prompt and repository, then spawn Breaker (Opus) to generate a layered spec/milestones/quality/validation structure under .bnb//. Use when you've pasted a long prompt or the task has a large blast radius.
/break-n-bake:break
Transform the current conversation's working prompt into a structured `.bnb//` spec.
Input
The "working prompt" is either:
$ARGUMENTSif the user passed text after/break-n-bake:break, or- The most recent
Alternatives in Testing
- OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
- Langgraphjs — by langchain-ai - Offers comprehensive build and test commands with detailed TypeScript style guidelines, laye 2.7k ★
- Check Package — Run full validation (build + lint + test + typecheck) on a package 1.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Axiom — Development Changelog
Purpose: Historical record of Axiom development milestones, TDD testing results, and architectural decisions.
Agent Shopping Arena
GPT-6 Sol vs Claude Opus 5.5: same Playwright harness, same 10 shopping tasks on real DTC stores, plus a live
Pressure Test
Pressure-test the current approach against scalability, long-term, and efficiency, then recommend the best opt
Set OKRs
Structure OKRs — define objectives, write measurable key results, align to strategy, stress-test for quality,
Buildable Design
Create a Buildable UI/UX design brief from a prompt or current app spec.
Q Status
Check Spec-Kit-Plus workflow status with Quality Gate grades - shows phase progress, validation reports, and n
Related Agents
Bnb Breaker
Heavy-cognitive-load agent that transforms a raw user prompt plus scout report into a layered spec directory u
Cr Docs Guard
Documentation lens — catches docs that assert what is no longer true, broken paths and links, commands that do
Adversarial Breaker
Actively tries to break the app — wrong inputs, unexpected sequences, auth bypasses, race conditions, state co