This runs your full test suite in a smart sequence: diagnostics for type errors first (catches root causes in ~1 second), then unit and integration tests in parallel, then E2E tests only if the fast ones pass. The pre-flight diagnostics step is clever because you get "expected int, got str" instead of mysterious test failures downstream. It uses arbiter agents for the parallel phase and atlas for the slower end-to-end stuff. You can scope it to specific features or run quick checks with just unit tests. The workflow stops early if anything fails, so you're not waiting on slow browser tests when you have a basic type error. Good for pre-commit checks or verifying changes before a merge.

skills.sh installs
503
GitHub stars
3.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill test --agent claude-code

Installs into .claude/skills of the current project.

Files

/test - Testing Workflow

Run comprehensive test suite with parallel execution.

When to Use

  • "Run all tests"
  • "Test the feature"
  • "Verify everything works"
  • "Full test suite"
  • Before releases or merges
  • After major changes

Workflow Overview

┌─────────────┐      ┌───────────┐
│ diagnostics │ ──▶  │ arbiter  │ ─┐
│ (type check)│      │ (unit)    │  │
└─────────────┘      └───────────┘  │
                                    ├──▶ ┌─────────┐
                     ┌───────────┐  │    │  atlas  │
                     │  arbiter  │ ─┘    │ (e2e)   │
                     │ (integ)   │       └─────────┘
                     └───────────┘

  Pre-flight         Parallel              Sequential
  (~1 second)        fast tests            slow tests

Agent Sequence

#AgentRoleExecution
1arbiterUnit tests, type checks, lintingParallel
1arbiterIntegration testsParallel
2atlasE2E/acceptance testsAfter 1 passes

Why This Order?

Sponsors

Details

Repository
github.com/parcadei/continuous-claude-v3
Categories
Testing & QA, Automation & Workflows
First seen
Jun 3, 2026

More from parcadei/continuous-claude-v3

All 108
1rshankras avatartestingrshankras/claude-code-apple-skillsTDD and testing skills for iOS/macOS apps. Covers characterization tests, TDD workflows, test contracts, snapshot tests, test infrastructure, and deterministic 481skills.sh installs
2secondsky avatarmobile-app-testingsecondsky/claude-skillsMobile app testing with unit tests, UI automation, performance testing. Use for test infrastructure, E2E tests, testing standards, or encountering test framewor480skills.sh installs
3oakoss avatarplaywrightoakoss/agent-skillsPlaywright browser automation API, web scraping, and tooling. Covers locator strategies, assertions, API testing, stealth mode, anti-bot bypass, authenticated s466skills.sh installs
4secondsky avatarmutation-testingsecondsky/claude-skillsValidate test effectiveness with mutation testing using Stryker (TypeScript/JavaScript with Vitest or bun test via @hughescr/stryker-bun-runner) and mutmut (Pyt456skills.sh installs
5mrgoonie avatarweb-testingmrgoonie/claudekit-skillsWeb testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile ges448skills.sh installs
6manutej avatarshell-testing-frameworkmanutej/luxor-claude-marketplaceShell script testing expertise using bash test framework patterns from unix-goto, covering test structure (arrange-act-assert), 4 test categories, assertion pat440skills.sh installs