Write tests
with agent skills.
Choose a testing skill around the behavior you need to prove. A unit test, a browser journey and a final verification pass answer different questions, even when they all end with a green check.
Filter these skills by stack and access
Choose a skill
For new behavior, look for a test-driven workflow. For a user journey, look for browser or integration testing that matches your stack. For an existing change, use verification guidance that checks the requirement as well as the code.
Before you install
Provide the acceptance criteria, the repository test commands and any fixtures already available. Keep tests away from production data. Say whether the agent may add test dependencies or start services; neither follows automatically from writing a test.
Open a listing to read its source, access labels and review evidence before copying its install command. The automated scan covers SKILL.md, not referenced files or runtime behavior. Read the review limits.
Skills for this task
13 available skills, listed A to Z. Task labels help narrow the choice; they do not establish fit for your project.
AI regression testing
Adds targeted regression tests for recurring blind spots in AI-assisted code changes.
What it can touch: Edits code · Runs commands
Last good scan retained · evidence and limits
- Automated scan: Latest fetch failed. Last successful scan: 8 Nov 2026. Current upstream content is unverified.
- Source revision: No repository commit recorded. Install command is unpinned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Installs the upstream repository’s current version, not a pinned reviewed revision. The source may have changed since the check. What the review covers.
—not counted yet
npx skills@latest add affaan-m/everything-claude-code --skill ai-regression-testingAPI test suite builder
Scans API routes and generates contract-focused tests for auth, validation, and failure paths.
What it can touch: Edits code · Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 4680893d91f2 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
686installs0 today
npx skills@latest add https://github.com/alirezarezvani/claude-skills/tree/4680893d91f2aee6f77ca1519fd1b86b7a104c87 --skill api-test-suite-builderEnd-to-end testing
Structures Playwright end-to-end suites with page objects, CI artifacts, and flake controls.
What it can touch: Edits code · Runs commands · Browser
Last good scan retained · evidence and limits
- Automated scan: Latest fetch failed. Last successful scan: 8 Nov 2026. Current upstream content is unverified.
- Source revision: No repository commit recorded. Install command is unpinned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Installs the upstream repository’s current version, not a pinned reviewed revision. The source may have changed since the check. What the review covers.
—not counted yet
npx skills@latest add affaan-m/everything-claude-code --skill e2e-testingMutation testing
Configures mewt or muton campaigns and interprets surviving mutations as test gaps or equivalents.
What it can touch: Edits code · Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 149d7b21f406 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
4.9Kinstalls+30 today
npx skills@latest add https://github.com/trailofbits/skills/tree/149d7b21f4067765b82e67029730b42d228ef4b4 --skill mutation-testingPlaywright
Drives real browser flows from the terminal with snapshot-based Playwright CLI commands.
What it can touch: Runs commands · Browser · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 49f948faa925 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
9.6Kinstalls+44 today
npx skills@latest add https://github.com/openai/skills/tree/49f948faa9258a0c61caceaf225e179651397431 --skill playwrightPost-patch validation
Validates a security patch with pinned baseline, exploit, variant, behavior, and regression evidence.
What it can touch: Edits code · Writes docs · Runs commands · Uses git · Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 149d7b21f406 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
1.3Kinstalls+25 today
npx skills@latest add https://github.com/trailofbits/skills/tree/149d7b21f4067765b82e67029730b42d228ef4b4 --skill post-patch-validationRuby test frameworks
Distinguishes Minitest and test-unit assertions, hooks, filters, skips, and Rails behavior.
What it can touch: Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: b1ea8b59bbd1 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
8installs0 today
npx skills@latest add https://github.com/st0012/ruby-skills/tree/b1ea8b59bbd15bf808c46e66f08c04a8620b7470 --skill ruby-test-frameworksSpec-driven workflow
Turns requirements into an approved, traceable spec, tests, and scope-controlled implementation.
What it can touch: Edits code · Writes docs · Runs commands · Uses git
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 4680893d91f2 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
614installs0 today
npx skills@latest add https://github.com/alirezarezvani/claude-skills/tree/4680893d91f2aee6f77ca1519fd1b86b7a104c87 --skill spec-driven-workflowTDD
A red-green loop with firm rules on what makes a test worth keeping.
What it can touch: Edits code · Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 5863806dd4e1 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
1.24Minstalls+2.5K today
npx skills@latest add https://github.com/mattpocock/skills/tree/5863806dd4e15c63174bee4e7515a4256792ecfa --skill tddTDD workflow
Runs a test-first development loop across unit, integration, and browser coverage.
What it can touch: Edits code · Runs commands · Browser
Last good scan retained · evidence and limits
- Automated scan: Latest fetch failed. Last successful scan: 8 Nov 2026. Current upstream content is unverified.
- Source revision: No repository commit recorded. Install command is unpinned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Installs the upstream repository’s current version, not a pinned reviewed revision. The source may have changed since the check. What the review covers.
—not counted yet
npx skills@latest add affaan-m/everything-claude-code --skill tdd-workflowTest-driven development
Strict test-first discipline: watch it fail, make it pass, then refactor.
What it can touch: Edits code · Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 22f0b463e7a5 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
282Kinstalls+1.3K today
npx skills@latest add https://github.com/obra/superpowers/tree/22f0b463e7a5e579904dd6211a520321035526f7 --skill test-driven-developmentVerification loop
Runs build, type, lint, test, security, and diff gates before a change is called complete.
What it can touch: Edits code · Runs commands · Uses git
Last good scan retained · evidence and limits
- Automated scan: Latest fetch failed. Last successful scan: 8 Nov 2026. Current upstream content is unverified.
- Source revision: No repository commit recorded. Install command is unpinned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Installs the upstream repository’s current version, not a pinned reviewed revision. The source may have changed since the check. What the review covers.
—not counted yet
npx skills@latest add affaan-m/everything-claude-code --skill verification-loopWeb app testing
Tests local web apps with Playwright scripts: screenshots, logs and UI checks.
What it can touch: Browser · Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 1780c5e5a552 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
206Kinstalls+741 today
npx skills@latest add https://github.com/anthropics/skills/tree/1780c5e5a552fd4d1c9d6a7b0cab26b0c2bef064 --skill webapp-testing
Check the result
- 01
Show that a new regression test fails for the intended reason before applying the fix.
- 02
Cover a meaningful boundary or failure path as well as the happy path, using the public behavior where practical.
- 03
Run the affected suite again after the final edit. Separate passed checks from skipped or blocked checks.