red-green-refactor
Use to implement one slice test-first with disciplined double-loop TDD — an outer failing end-to-end or integration test wrapping inner unit-test red, green,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Testing & quality
12,766 results
code-review
Use this skill when the user requests "review code", "code check", "check for bugs", "code quality check", "find problems", "refactoring suggestions", or mentions "code review", "code review", "review", or "check". Used for feedback on code quality, potential bugs, performance issues, security vulnerabilities, or improvement opportunities.
error-handling-debugging
Use this skill when the user asks to "handle errors," "error handling," "catch exceptions," or "error recovery," or mentions "错误处理," "error handling," or "异常." It is used to handle errors in Rust or TypeScript, debug issues, troubleshoot Tauri command failures, fix database errors, or implement error recovery strategies.
tdd-workflow
Use when the user requests TDD, test-driven development, writing tests first, or mentions red-green-refactor.
quality-guardian
Use when running and interpreting quality gates such as lint, type checking, and tests. It is not just about executing commands; it also requires selecting the minimal sufficient checks based on the scope of changes, analyzing the causes of failures, and giving a judgment on whether to allow continued commits or releases. It should be triggered whenever the user mentions lint, typecheck, tests, quality gate, or verifying changes.
test-engineer
Use when writing, completing, running, and optimizing tests, prioritizing Vitest scenarios, and also applicable to test design for component logic, utility functions, state management, and the service layer. It should be triggered when the user mentions test, unit test, integration test, coverage, mock, Vitest, or adding tests.
quality-retrospective
Use after completing a phase to extract lessons, patterns, and improvement opportunities
quality-test
Use when implementation needs user acceptance testing with interactive verification and gap closure
team-review
Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review.
team-testing
Unified team skill for testing team. Progressive test coverage through Generator-Critic loops, shared memory, and dynamic layer selection. Triggers on "team…
find-your-margin
Help a knowledge worker find where their attention earns the fattest margin when combined with AI. Maps their skill stack against AI capabilities to identify…
building-tests
Builds and runs an app's committed tests, written from the user's expectations rather than per platform — segments (one actor's intent on one surface, from a…
skill-audit
Use when packaged skills must be checked against the repository's skill contract before a merge or release, including "check the skill rules", "inspect the skill package", "sync the skill catalog…
playwright-browser
Playwright CLI and MCP tools for headless browser automation, E2E testing, screenshots, and web scraping. Use for CI-safe browser operations.
designing-tests
Guides test strategy, TDD/BDD approaches, test coverage planning, and testing best practices. Use when designing test suites, improving coverage, or choosing…
wpt-update
Updates and triages the Web Platform Tests dependency in workerd. Use when asked to bump, update, or triage WPT.
ab-test-plan
Generate structured A/B test plans for DTC funnels — hypothesis, control vs variant, primary metric, sample size estimate, test duration, and success criteria…
media-buying-brief
Generate strategic media buying briefs — audience targeting, budget allocation, KPI targets, creative rotation, and testing frameworks for paid media campaigns.
eval-build
Build or resume trustworthy evals for an AI application, from existing evidence through reviewed cases, validated graders, and a runnable baseline. Use for…
eval-descent
Improve an AI application through bounded, evidence-linked experiments against validated evals. Use for quality, latency, cost, or model migration; requires a…
eval-discover
Find realistic AI application examples and conduct human-led trace review to discover failure modes. Use before inventing quality metrics; supports managed…
test
Generate tests for Convex functions with convex-test (queries/mutations/auth/scheduling, in-memory). TRIGGER when the user wants tests / a test suite for their…
evidence-based-debugging
Reproduce and diagnose reported software or system failures using experiments and captured evidence. When a repair is requested, demonstrate the cause, make a…
doc-coauthoring
Guides users through structured three-stage collaborative documentation workflow including context gathering, iterative refinement, and reader testing. Use…