AI-assisted pipeline that turns product specs into human-reviewed test plans and executable Playwright automation
Skill Claude CodeCodex
Part of verefi
Statically scan the target codebase for stable selectors (data-testid, testID, aria-label, semantic roles) and grade its testability into audit.md — no running app needed. Use when the user wants to know how testable an app is, before generating tests, or as the zero-setup entry point to the Verefi pipeline.
Skill Claude CodeCodex
Part of verefi
Explore a running app with agent-browser and record verified selectors (test-id attribute, role, text) into discovery.md — including identifying which test-id attribute the app actually uses. Use when the user wants to verify a test plan's assumed selectors actually exist before writing test code, or continue the…
Skill Claude CodeCodex
Part of verefi
Run the generated Playwright tests and summarize pass/fail results. Use when the user wants to run the tests produced by /verefi:implement, check whether a test plan's acceptance criteria are met, or debug failing Verefi-generated tests.
Skill Claude CodeCodex
Part of verefi
Generate Playwright TypeScript test code from a test-plan.md (and discovery.md/audit.md if present). Use when the user wants to turn an approved test plan into runnable Playwright tests, or continue the Verefi pipeline after /verefi:testplan, /verefi:audit, or /verefi:discover.
Skill Claude CodeCodex
Part of verefi
Generate a reviewable test-plan.md (test cases + acceptance criteria) from a feature description or test-detail file. Use when the user wants to start the Verefi pipeline, kick off spec-driven test generation, or turn a PRD/user story/feature description into a test plan before writing any test code.
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: