prove-fix
433Command
Prove the current change actually works, by running it (base-fail / head-pass).
2,999 tagged Testing, measured the same way as everything else here.
Browse within: agentic-workflow 44claude-plugin 33ai-development 32agentic-coding 31code-quality 31spec-driven-development 27agent-orchestration 26agent-framework 25ai-assistant 25agentic 21ai-workflow 21Multi-Agent 20claude-code-skills 20documentation 20
Command
Prove the current change actually works, by running it (base-fail / head-pass).
Command
Part of bayesian-modeling
Execute Bayesian models with test data and report convergence diagnostics.
Command Claude Code
Test MCP server connection and all tools.
Command Claude Code
Add a claude-code-enforcer rule end to end — class, Sisu index, tests, IT fixture, pom wiring and docs.
Command
Part of claude-code-mastery
Generate and run end-to-end Playwright tests for critical user journeys. Captures screenshots, videos, and traces on failure.
Command
Part of claude-code-mastery
Enforce test-driven development workflow. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage.
Command Claude Code
Run the unified skill integration test that supports all SDK implementations (Java, Python, and future SDKs).
Command
Part of skill-up
Upgrade a skill through TDD-based testing and improvement. Creates scenario tests, evaluates discoverability, and enhances skill quality.
Command Claude Code
USE THIS SUBAGENT ANY TIME you need to run Pest tests, validate a fix, check the full suite, or filter tests. Returns a compact summary (max 20 lines) even when many tests fail. NEVER writes code.
Command Claude Code
A command for generating software test cases, including checks before starting, the generation process, its outputs, and next steps.
Command Claude Code
A command for planning software tests, including checks before testing, the testing process, its outputs, and next steps.
Command Claude Code
Map edited routes & launch tests.
Command
Agile development execution with TDD workflow.
Command
Part of adong-vibecoding
Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.
Command
Part of adong-vibecoding
Enforce test-driven development workflow. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage.
Command
Part of greycat
Comprehensive GreyCat frontend review — correctness, the prescribed VitePlus + Lit + Web Awesome (or similar) + @greycat/web stack, performance, Lighthouse/SEO, type safety, and testing.
marcoemrich/agentic_coding_lab
Command Claude Code
You are now in the Red Phase of TDD. Follow these instructions to activate ONE test and make it fail.
marcoemrich/agentic_coding_lab
Command Claude Code
You are now in the Refactor Phase of TDD. Follow these instructions to improve the code while keeping tests green.
marcoemrich/agentic_coding_lab
Command Claude Code
You are now in the Test List Phase of TDD. Follow these instructions to create a comprehensive test list.
Command
Implement the next task incrementally — build, test, verify, commit.
Command Claude Code
Part of cortex
Structured experiment runner — define hypothesis, metric, and variations, then run automated eval loops with brainiac tracking.
bkrabach/ai-code-project-template
Command Claude Code
Command "test-webapp-ui" from bkrabach/ai-code-project-template, covering usage, context, process, output format and notes.
hzeng-otterai/ai-course-example
Command Claude Code
You are implementing or refining a feature for the GreatNotes app (Django REST Framework backend + React 19 frontend). Work through the steps below in order, pausing for explicit approval before editing any code.
Command Claude Code
Test RTK command routing without execution (dry-run) - verifies which commands have filters.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: