review-quality-gate
Self-check quality gate for review findings. Validates that each finding is actionable, evidence-backed, correctly located, not duplicating linter output, and…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Testing & quality
13,007 results
create-walkthrough
Generate a walkthrough artifact (walkthrough.md) summarizing completed work for PR delivery. Gathers information from plan.md, git history, and test results to…
wayfinder-pipeline
The wayfinder pipeline: the long route from a loose idea to merged code, stage by stage, and the test that picks it or /quick-change. Use when sizing a change,…
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
running-tests
Use when running tests in the Nango monorepo - knows unit vs integration configs, vitest commands, Docker setup, and common test patterns
ajiang_adversarial_review
Conduct independent, evidence-driven regression review of software changes, divide work by requirements and impact chains, and verify findings one by one. Suitable when the user requests adversarial review or for high-impact changes; when tools are insufficient, state the review coverage.
ajiang_contract_audit
Check the producer and consumer contracts of connectors, model providers, plugins, cross-process bridges, synchronization, and migration; locate silent failures, ineffective configuration, misjudged state, and environment differences.
ajiang_debugging
Troubleshoot software faults: distinguish symptoms from attribution, establish pre-fix failure evidence and hypothesis experiments, and after a minimal fix verify via the original user flow. Suitable for bugs with unknown causes, environment-related bugs, or bugs that still reproduce after a fix.
tdd-quality-workflow
Use this skill when guiding or reviewing test-driven development with evidence for Red, Green, Refactor and test effectiveness; triggers include TDD quality…
apply-tdd
Use when implementing a non-trivial, observable behavior change with TDD under explicit ecosystem production-path and test-isolation boundaries. Do not apply…
review-code
Review diffs, pull requests, commits, patches, or source files for correctness, baseline security, performance, maintainability, tests, and integration risk.…
stress-testing-plans
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants…
test-refactor
Use this skill when improving the maintainability, readability, organization, and architecture of existing automated tests without changing their behaviour.
test-unit-guidelines
Use this skill when writing, reviewing, refactoring, or maintaining unit tests in any framework — the isolated, in-process tests of a single function, class,…
scaffold-agent-tests
Generate an LLM agent test suite (golden cases, mock-LLM unit tests, evaluator harness) from an agent implementation and its agent-test contract. Use when an…
oro-behat-debugging
Use when debugging or troubleshooting Behat tests in Oro Commerce 6.1 — failing scenarios, intermittent/flaky runs (passes 4 of 5, fails 3 of 20), missing…
oro-functional-testing
Use when writing, debugging, or configuring PHPUnit functional tests for Oro Commerce 6.1 — anything extending WebTestCase: controllers, REST API, console…
oro-k6-testing
Use when setting up or running k6 performance tests for Oro Commerce 6.1 — load testing, storefront benchmarking, checkout flow performance, cache warm-up, or…
ads-linkedin
LinkedIn Ads deep analysis for B2B advertising. Evaluates 25 checks across technical setup, audience targeting, creative quality, lead gen forms, and bidding…
api-testing
Use this skill when testing REST or GraphQL APIs, implementing contract tests, setting up mock servers, or validating API behavior. Triggers on API testing,…
mcp-chrome-devtools
Use the Chrome DevTools MCP server (io.github.ChromeDevTools/chrome-devtools-mcp) for browser automation, navigation, form interaction, and UI flow validation…
mcp-playwright
Use the Playwright MCP server (@playwright/mcp) for browser-driven verification, screenshots, console logs, and UI flow validation; use when debugging or…
skill-tester
Test Claude Code skills in real-world scenarios to validate functionality, usability, and effectiveness. Task-based testing operations for scenario testing,…
testgen
Generate tests with expert routing, framework detection, and auto-TaskCreate. Triggers on: generate tests, write tests, testgen, create test file, add test…