Agent skills

Testing & QA skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
1,723 found
577624 · page 13 / 36
Change Impact MapA practical framework to map change dependencies and blast radius, including who/what is affected, what to test, rollout/rollback…majiayu000character-design-continuityProvider-independent character design and continuity direction for generated media. Use when an agent must create, preserve…calesthiocharacterization-test-generatorGenerate characterization tests to capture and verify existing behavior before migrationa5c-aiwritescinematic-shot-directionDirect cinematic shots and coverage for AI-assisted content production. Use when an agent must translate story intent into…calesthiocinematic-trailer-productionProvider-independent cinematic trailer production for AI agents creating movie-style trailers, teaser trailers, launch trailers…calesthioclade-ci-integrationTest and validate Claude integrations in CI/CD pipelines \u2014\nUse\ \ when working with ci-integration patterns.\nGitHub…jeremylongshorewritesclade-local-dev-loopSet up a fast local development loop for building with the Anthropic\ \ API \u2014\nUse when working with local-dev-loop…jeremylongshorewritesclaude-superpowersForce Claude Code to work like a senior developer: plan before coding, work in isolation, write tests first, and review its own…majiayu000cli-e2e-test-harnessSet up E2E test harness for CLI applications with process spawning and assertions.a5c-aiwritesCode Coverage AnalysisMulti-language code coverage analysis, reporting, and quality gate enforcementa5c-aiwritescode-review-gateArchitect code review with DRY, YAGNI, abstraction, and test coverage principle enforcementa5c-aiwritescode-sample-validatorExtract, validate, and test code samples in documentation. Verify syntax, execute samples, check outputs, validate imports, and…a5c-aiwritescode-testing-agentMANDATORY ENTRY POINT for generating or writing tests. Invoke this skill before editing files whenever the user asks to generate…dotnetcodebase-assumption-captureCapture wrong assumptions you made about the codebase. TRIGGER when reality differs from expectation (e.g., "assumed Jest but…majiayu000codebase-mappingAutomatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies…a5c-aiwritescodebase-mappingAutomatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies…majiayu000writescoding-agentIncremental development agent with TDD workflow. Use when implementing features one at a time, following test-driven development…majiayu000cognitive-baseline-evalExecute the Joseph Cognitive Baseline v2.1 (JC B-v2.1) 5-Scenario Test Suite to quantify AI alignment, friction maintenance, and…majiayu000compatibility-test-matrixMulti-version, multi-platform SDK compatibility testinga5c-aiwritescompositional-acset-comparisonCompare data structures (DuckDB, LanceDB) via ACSets with persistent homology coverage analysis and geometric morphism…majiayu000comprehensive-review-pr-enhanceGenerate structured PR descriptions from diffs, add review checklists, risk assessments, and test coverage summaries. Use when…sickn33compute-env-setupSet up and validate a reproducible Python or R environment on a Wisp execution context. Use for a selected local, WSL, or direct…xuzhougengConfidence ScoringSee the main Model Explainability skill for comprehensive coverage of confidence scoring and calibration.majiayu000content-experimentation-best-practicesA/B testing and content experimentation methodology for data-driven optimization. Use when setting up A/B tests, multivariate…majiayu000evaluationThis skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality"…majiayu000contract-test-frameworkConsumer-driven contract testing for SDK-API compatibility. Generate Pact consumer tests, verify provider contracts, configure…a5c-aiwritescontract-test-generatorGenerate contract tests for API migrations with consumer-driven contracts and provider verificationa5c-aiwritescoo-analyticsCOO 产品运营数据分析技能,使用 Playwright MCP 从 App Store Connect、小程序后台、小红书创作者中心等平台获取运营数据majiayu000corpus-analysisGap detection and knowledge mapping techniques for comparing BRD requirements against corpus coverage. Includes SurrealQL queries…majiayu000counterexample-explainerExplain why counterexamples violate specifications by analyzing formal specifications (temporal logic, invariants…majiayu000create-businessGuided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase…wondelaicreative-learningsDocument learnings from creative tests including patterns of what worked and what didn't, updating the angle/hook performance…majiayu000critical-readingAnalytical evaluation of texts for argument quality, author purpose, bias, credibility, and rhetorical strategy. Covers the…majiayu000critiqueAdversarial stress test of an idea. Find fatal flaws, hidden assumptions, dependencies, and failure modes. Use after evaluate to…majiayu000cross-artifact-analysisPerform cross-artifact consistency and coverage analysis across constitution, specification, plan, and task artifacts to detect…a5c-aiwritescross-platform-test-matrixGenerate CI test matrix for Windows, macOS, and Linux combinationsa5c-aiwritescultural-researchUse this to autonomously populate Martinique_DB. Takes a cultural topic from the 6 CoT circles, runs a deep research loop using…majiayu000curl-httpAPI testing with curl and httpie for HTTP requests. Use when user asks to "test API", "make HTTP request", "curl POST", "send…majiayu000customerio-ci-integrationConfigure Customer.io CI/CD integration with automated testing. Use when setting up GitHub Actions, integration test suites, or…jeremylongshorewritescustomerio-hello-worldCreate a minimal working Customer.io example. Use when learning Customer.io basics, testing SDK setup, or creating your first…jeremylongshorewritescustomerio-load-scaleImplement Customer.io load testing and horizontal scaling. Use when preparing for high traffic, running load tests, or designing…jeremylongshorewritescypressCypress testing patterns, custom commands, component testing, and CI integration.a5c-aiwritesCypress E2E TestingExpert Cypress testing framework integration for browser-based end-to-end testinga5c-aiwritesd-id-avatar-videoUse D-ID to plan, generate, stream, localize, and QA avatar/talking-head videos, including V2 Photo Avatar Talks, V3 Pro/Instant…calesthiod3-animated-data-visualizationProduction guidance for converting sourced data and approved claims into truthful, accessible, deterministic animated…calesthiodata-analysisUse when the user wants an iterative, self-checking exploratory analysis of a dataset — surfacing findings that are each verified…gaasherdata-scienceUse this skill when performing exploratory data analysis, statistical testing, data visualization, or building predictive models.…majiayu000data-validationQA an analysis before sharing with stakeholders — methodology checks, accuracy verification, and bias detection. Use when…majiayu000
← Prev13 / 36Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going