Testing automation · commands · 18 picks

Claude Code testing automation

Commands, hooks, and skills for generating tests, running checks, enforcing TDD loops, and keeping Claude Code changes verifiable.

Curated by @heyclaude-editors Updated 2026-07-18

Commands, hooks, and skills for generating tests, running checks, enforcing TDD loops, and keeping Claude Code changes verifiable.

Compared at a glance

The top 5 picks side by side on trust, install, platform support, and disclosed notes — full rationale for each below.

3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).

Next steps differ across picks — use the actions in the table below to copy install commands and source links per resource.

Field	TDD Workflow Custom Command for Claude Code A user-created custom slash command that runs a red-green-refactor TDD loop in Claude Code: write failing tests first, implement until they pass, then refactor. Built with the documented custom-command frontmatter and $ARGUMENTS substitution, not a built-in feature. Open dossier	/targeted-test-generation - Targeted Test Generation Runbook Community slash command runbook for adding minimal automated tests around a changed module: inspect the git diff, mirror repository test conventions, and draft focused unit or integration tests using Anthropic develop-tests guidance. Open dossier	Playwright E2E Testing Automation Skill Write and maintain reliable end-to-end tests with Playwright — Microsoft's browser automation library that auto-waits for actionable elements and runs the same suite against Chromium, Firefox, and WebKit. Open dossier	Generate Tests Custom Command A user-created custom slash command for Claude Code that turns a file or function into a test suite. You create .claude/commands/generate-tests.md and invoke it with /generate-tests; it is a prompt recipe, not a built-in command, and uses no CLI flags. Open dossier	GitHub Actions AI-Powered CI/CD Automation Skill Build intelligent CI/CD pipelines with GitHub Actions, AI-assisted workflow generation, automated testing, and deployment orchestration. Open dossier
Next stepsDiffers	Open dossier API JSON Open LLM Open source Newsletter Claim listing	Open dossier API JSON Open LLM Open source Newsletter Claim listing	Open dossier API JSON Open LLM Open source Newsletter Claim listing	Open dossier API JSON Open LLM Open source Newsletter Claim listing	Open dossier API JSON Open LLM Open source Newsletter Claim listing
Trust
Review status	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed	ReviewedMaintainer reviewed
Package trustDiffers	Package not verified	Package not verified	Package verified2025-10-16	Package not verified	Package verified2025-10-16
Source provenanceDiffers	Source-backed	Submission linkedSource submission	No submission link	Source-backed	No submission link
SubmitterDiffers	—	kiannidev	—	—	—
Install risk	Review first	Review first	Low risk	Review first	Low risk
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Brand	—	—	—	—	GitHub
Category	commands	commands	skills	commands	skills
Source	Source-backed	Source-backed	First-party	Source-backed	First-party
Author	JSONbored	kiannidev	JSONbored	JSONbored	JSONbored
Added	2025-10-25	2026-06-16	2025-10-16	2025-09-16	2025-10-16
Platforms	Claude Code	Claude Code	Claude Code Codex Windsurf Gemini Cursor CLI	Claude Code	Claude Code Codex Windsurf Gemini Cursor CLI
Harness	Claude Code	Claude Code	Claude Code Codex Windsurf Gemini Cursor CLI	Claude Code	Claude Code Codex Windsurf Gemini Cursor CLI
Source repo	—	—	—	—	—
Safety notes	✓The base recipe does not pre-approve Bash commands. Review the project's test scripts first, then approve the exact test command when Claude Code prompts or add a narrowly scoped command only after you trust it. Claude may create and edit test and source files as part of the loop (Read/Edit/Write). Run it in version control so changes are reviewable and reversible. If you extend the prompt with auto-commit or deploy steps, add explicit safety review; the base recipe does not commit or push.	✓Generated tests are drafts; run the project's test command locally before committing. Do not add network calls, production credentials, or destructive setup to proposed tests.	✓`npx playwright install --with-deps` downloads browser binaries (~500 MB for Chromium, Firefox, and WebKit) from Playwright's CDN and on Linux installs system-level packages. Review your network and environment policies before running in restricted infrastructure. Generated tests have full browser-level access to any URL they target. Review test scripts before running them against authenticated sessions or production environments — Playwright can submit forms, click buttons, and make network requests as a real user.	✓The recipe asks Claude to run the test suite, which executes project code and test commands locally; review the source and tests before running, especially in an unfamiliar repository. If you add an allowed-tools field (e.g. Bash(npm test:*)), Claude can run those tool calls without a per-use permission prompt while the command is active. Scope it narrowly. Project-level .claude/commands files are shared via git and run for anyone who trusts the workspace; treat a checked-in command as executable content and review it before trusting the repo.	✓Setup downloads and unzips a package, and generated workflows run build/test/deploy commands in CI with repository permissions; review workflow YAML and least-privilege the GITHUB_TOKEN before merging.
Privacy notes	✓The command body can read project files via @ references and !`command` injection if you add them; only reference files you are comfortable sending to the model as prompt context. The base recipe asks you to inspect project test scripts instead of injecting package.json automatically.	✓Use synthetic fixtures only; do not copy production logs or customer records into tests.	✓Playwright runs entirely on your local machine. Traces, screenshots, and HTML test reports are written to local disk only and are not uploaded to Microsoft or any external service. Trace files and failure screenshots may capture sensitive content from the application under test (form data, rendered PII, session tokens visible in URLs). Store and rotate these files appropriately.	✓Dynamic-injection lines (!`...`) and @file references send the output of shell commands and the contents of referenced files into the model context; avoid pointing them at files containing secrets, credentials, or other sensitive data.	✓CI workflows read repository code and use secrets (API keys, deploy credentials, model keys); store them in GitHub Actions secrets, never in workflow files or logs, and review what third-party actions can access.
Prerequisites	— none listed	Git repository with an existing test runner configured in package scripts or docs. A concrete code change or diff hunk to cover with new or updated tests.	Node.js 18+ Playwright 1.40+ with the @playwright/test package Browser binaries installed via `npx playwright install` (Chromium, Firefox, WebKit) A web application accessible for testing (local dev server, staging, or production URL)	— none listed	GitHub repository with Actions enabled Test suite (Vitest, Jest, Playwright) Deployment target (Vercel, AWS, GCP, etc.) GitHub account with repository access and Actions enabled (free tier includes 2,000 minutes/month)
Install	—	`/targeted-test-generation <file-or-symbol>`	`npx playwright install --with-deps`	—	`curl -L https://heyclau.de/downloads/skills/github-actions-ai-cicd.zip -o github-actions-ai-cicd.zip && unzip -o github-actions-ai-cicd.zip -d ./github-actions-ai-cicd`
Config	—	—	—	—	—
Citations	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationcode.claude.com Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationplatform.claude.com Submitted by kiannidev2026-06-16 Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationplaywright.dev Package (SHA-256 pinned)/downloads/skills/playwright-e2e-testing.zip Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationcode.claude.com Source methodology →	Source repositorygithub.com 2026-07-18T19:14:44+00:00 Documentationdocs.github.com Package (SHA-256 pinned)/downloads/skills/github-actions-ai-cicd.zip Source methodology →
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed	Unclaimed