starwards-tdd
Test-driven development for Starwards - write the test first, watch it fail, write minimal code to pass; includes Jest unit tests, Playwright E2E tests,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-25 00:14
Testing & quality
12,687 results
skill-review
Evaluate Agent Skill directories against the Agent Skills Specification and quality criteria. This skill should be used when the user asks to "review a skill",…
prune
Prune one area's verification surface: delete, consolidate, or repair the tests and checks that no longer earn their cost, remove the test-only production code…
bugfix-pr
Treats bug-fix pull requests as invasive and untrusted. The agent must security-scan the PR first, must not run any command supplied by the author or issue,…
cloudbase-code-review
Code review and validation for CloudBase projects. After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill to check for…
test-reviewer
Review test design and readiness, Test review. Use when: After the Test Spec/Test Case Package is complete, it is necessary to review the coverage, traceability, execution evidence, and residual risks within the independent test scope, as a test gate before release preparation.
test-spec-writer
Write test spec, test specification/test case package authoring. Use when: after the LLD is complete and the test strategy has been confirmed, a complete test case package, traceability matrix, and execution notes within the independent test scope need to be produced.
test-strategy-writer
Write test strategy, test strategy writing. Use when: after the PRD, API Contract, and HLD baselines are clear, it is necessary to define independent test scope, independent test levels, phased execution rules, environment strategy, and entry/exit criteria.
testing-flow
Orchestrate the complete test case lifecycle from requirements to uploading to TMS (Test Management System). Generate test cases, improve existing ones,…
debugging-patterns
Debug .NET/ABP and React applications with systematic root cause analysis. Use when: (1) investigating bugs or errors, (2) analyzing stack traces, (3)…
e2e-testing-patterns
Master end-to-end testing with Playwright to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing…
chrome-devtools
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance,…
marketing-ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B…
performance_engineering
When validating system performance under load, identifying bottlenecks through profiling, or optimizing application responsiveness. Covers load testing (k6,…
contract-testing
Consumer-driven contract testing with Pact for API compatibility. Use when testing microservice integrations, verifying API contracts, preventing breaking…
llm-testing
Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured…
run-tests
Comprehensive test execution with parallel analysis and coverage reporting. Use when running test suites or troubleshooting failures with the run-tests…
LDAP Injection Testing
This skill should be used when the user asks to "test for LDAP injection vulnerabilities", "exploit LDAP queries", "perform blind LDAP injection attacks",…
verify
How to verify changes to the a1-yandex-kit-setup helper CLI at its real surface (setup.mjs), including the no-network sandbox scenario.
YunxiaoQA
Tester Yunxiao (Projex) automation: Receive and start [Testing] tasks, advance requirements from Pending Test to In Testing, perform retesting, re-read the latest prototype PRD before judging expected results or submitting defects, and confirm again before submission that the requirement has not changed. Monitor 01_ONEOS newly delivered tasks daily and automatically create test plans for delivery tasks whose titles contain both [Delivery] and [New] and that already have a selected iteration, ...
agent-testing-patterns
Test AI agent systems including tool use, multi-turn conversations, error recovery, and non-deterministic outputs. Covers mock strategies, evaluation metrics,…
adversarially-validating-game-repairs
Stress-tests an already-written game bug fix with adversarial cases selected from the state, timing, identity, lifecycle, persistence, and input surfaces the…
stress-testing-game-concepts
Audits one or more game concepts, rule specs, or early prototypes adversarially for unreachable goals, dominant simple policies, agency collapse, irrelevant…
debugging
Systematically debug code issues using proven methodologies. Use when encountering errors, unexpected behavior, or performance problems. Handles error…