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
673720 · page 15 / 36
geminiCross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge.…majiayu000geminiOffload tasks to Google Gemini CLI to preserve Claude credits. Gemini has internet access and strong code analysis. Use for code…majiayu000writesgemini-visionGuide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object…majiayu000gemini-visionGuide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object…majiayu000writesagent-template-generatorGenerates new agent profiles with consistent structure, automatic validation pattern injection, and test-driven protocolsmajiayu000geo-researchPerform comprehensive geopolitical research using GDELT data sources and specialized analysis agents. Routes queries to…majiayu000go-playwrightExpert capability for robust, stealthy, and efficient browser automation using Playwright Go.sickn33golden-dataset-curationUse when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent…majiayu000golden-dataset-managementUse when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for AI/ML…majiayu000writesgolden-dataset-validationUse when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure dataset…majiayu000google-cloud-visionUse this skill when an agent needs Google Cloud Vision API for still-image understanding: labels, object localization, OCR…calesthiogoogle-lyriaUse Google Lyria music generation models through Google Cloud / Vertex AI / Gemini Enterprise Agent Platform for production music…calesthiogoogle-veoDirect production with Google DeepMind's Veo video-generation family across the Gemini Developer API and Google Cloud Gemini…calesthiogoose-graphics-create-styleEnd-to-end skill that turns a single reference image into a published Gooseworks style — analyzes the image, drafts the slim…gooseworks-aigrill-ai-masteryHybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability…majiayu000grill-meAdversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree…majiayu000gtarsHigh-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED…majiayu000gtarsHigh-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED…majiayu000gtarsHigh-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED…majiayu000haystack-pipelineHaystack NLP pipeline configuration for document processing and QAa5c-aiwriteshaystack-pipelineHaystack NLP pipeline configuration for document processing and QAmajiayu000writeshelpChoose Phoenix review, plan, debug, or test command. Use when user asks which /phx: command or plugin skill handles a task; do…oliver-kriskaheygen-avatar-videoProduce HeyGen avatar videos with Direct Video, Video Agent, Digital Twin, Avatar Realtime, and related avatar/voice/asset APIs.…calesthiohtml-wireframeDirect-invocation specialist for low-fidelity, self-contained HTML wireframes that test information hierarchy, content…plannotatorhume-eviBuild production realtime voice agents with Hume's Empathic Voice Interface (EVI): speech-to-speech sessions, empathic/prosodic…calesthiohume-octaveUse Hume Octave for emotionally expressive speech and voice production: text-to-speech, voice design, voice cloning, voice…calesthiohypothesis-generationStructured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate…majiayu000writeshypothesis_generationBilimsel hipotez oluşturma, deney tasarımı ve test metodolojisi rehberi.majiayu000ideogram-imageGenerate, remix, edit, inpaint, reframe, background-process, describe, layerize, and upscale images with the Ideogram Developer…calesthioimmersive-spatial-video-productionUse this skill to plan, direct, finish, and QA provider-independent mono or stereo 180-degree, 360-degree, spherical, spatial…calesthioin4-contra-logicApply IN4 Contra-Logic to argue the opposite position to stress-test assumptions and expose weak reasoning.majiayu000insurance-policy-decoderDecode a home, renters, or auto insurance policy into what's actually covered, what's excluded, and what the payout math really…mohitagw15856integration-e2e-testingIntegration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing…shinprinterviewYou are a thinking partner conducting an in-depth interview. Your goal is to help the user clarify, stress-test, and articulate…majiayu000interview-problem-bankCurated bank of interview problems organized by company, pattern, and difficulty. Provides problem recommendations, coverage…a5c-aiwritesinvestigateSystematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through…majiayu000iv-estimationEconometrics skill for instrumental variables and treatment effect estimation. Activates when the user asks about: "instrumental…brycewang-stanfordjavascript-testing-patternsImplement comprehensive testing strategies using Jest, Vitest, and Testing Library for unit tests, integration tests, and…wshobsonjestJest configuration, mocking strategies, snapshot testing, and coverage.a5c-aiwritesJest TestingExpert Jest testing framework for JavaScript/TypeScript unit and integration testinga5c-aiwritesjsdoc-tsdocJavaScript and TypeScript documentation generation using JSDoc and TSDoc. Parse source code, generate API documentation, validate…a5c-aiwriteskling-advanced-lip-syncProduction guidance for Kling AI Open Platform Advanced Lip-Sync. Use for identifying/selecting one face in an existing video…calesthioknowledge-gapAnalyze help center for coverage gaps by comparing support tickets to existing articlesmajiayu000langfuse-dashboardAutomates Langfuse Cloud dashboard interactions using Playwright MCP. Captures screenshots for documentation, extracts metrics…majiayu000writeslangfuse-integrationReplaces Phoenix observability with Langfuse Cloud (EU) traceability for pharmaceutical test generation. Adds @observe decorators…majiayu000writeslegacy-code-summarizerProduces comprehensive summaries and insights about legacy codebases to help understand unfamiliar code. Use when onboarding to a…majiayu000lens-reconAnalytics reconnaissance for takeover — find all analytics tools, inventory what's tracked and dashboarded, assess data freshness…jeremylongshorewriteslighting-directionProvider-independent lighting direction for AI-generated images, video clips, ads, film scenes, avatars, product shots…calesthio
← Prev15 / 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