platform-checks
This skill should be used when the user wants to create, modify, or debug a platform check. Trigger when the user mentions "platform check", "platform-checks",…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Testing & quality
13,071 results
five-phase-pass
Use when asked to propagate a dean-stack monorepo change through the five-phase pass: P1 apps/web, P2 generator template, P3 regenerated test-project plus…
kill-servers
Use when asked to kill stale dean-stack dev, preview, or Storybook server processes and free ports before `bun run check`, Playwright, or the five-phase-pass…
playwright
Router skill for Playwright in dean-stack — pins `@playwright/test` 1.59+, dispatches to the story-tests, app-tests, PWA-offline, or conventions sub-skill, and…
production-readiness-review
Use this skill when a running preview, prototype, or vibe-coded slice might be treated as a real product. Scores demo vs pilot vs production, lists UI-owned…
android-emulator-skill
Production-ready scripts for Android app testing, building, and automation. Provides semantic UI navigation, build automation, log monitoring, and emulator…
android-testing
Comprehensive testing strategy involving Unit, Integration, Hilt, and Screenshot tests.
claude-code-reviewer
Code review skill that explains AI-made session changes as a cohesive story. Generates a self-contained HTML report with cross-file connection…
create-mcp-eval
Generate comprehensive eval tests for any MCP server using @mcpjam/sdk. Supports Jest and Vitest with deterministic and LLM-driven test patterns.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user…
playwright-expert
Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke to write test scripts, create page…
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the…
fixing-bugs
Fixes bugs in the Medusa monorepo from a Linear ticket or a described issue. Validates the report against the code, writes a regression test and confirms it…
analyze-automation-roi
Analyze automation ROI for test cases and recommend which tests to automate based on value and effort. Use for prioritizing test automation investments.
analyze-pyramid
Analyze test pyramid health by examining test distribution across unit, integration, and E2E levels. Use for test portfolio assessment and rebalancing…
resolve-failed-e2e-test
Analyze a failed E2E test, fix the underlying issue, and verify the fix. Use after /test-e2e reports failures.
resolve-failed-test
Analyze a failed test, fix the underlying issue, and verify the fix. Use after /test reports failures.
test
Run project test suite and report results in structured JSON format. Use to validate implementation before commit or review.
test-e2e
Execute end-to-end test specification and report results. Use after implementation to validate user journeys before review.
validate
Validate specification against schema and quality rules.
write-acceptance
Write acceptance criteria in Given-When-Then format for user stories following BDD best practices. Use for creating testable, clear acceptance criteria.
kf-g-git-pr-red-green-stacked-pr
Use when a bug fix or regression test must leave CI evidence that the test failed on the code before the fix (Red-Green Stacked PR: bottom PR with…
browserhub
Browserhub integration. Manage data, records, and automate workflows. Use when the user wants to interact with Browserhub data.
looplia-e2e
End-to-end testing for looplia CLI from local source. Builds the CLI, initializes workspace, runs the writing-kit workflow, and verifies outputs. Use when…