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
721768 · page 16 / 36
lindy-local-dev-loopSet up local development workflow for testing Lindy AI agent integrations. Use when building webhook receivers, testing agent…jeremylongshorewritesllm-debuggerDiagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Provides root…majiayu000LLM Token OptimizationSee the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.majiayu000ln-511-test-researcherResearches real-world problems, competitor solutions, and customer complaints before test planning. Posts findings as Linear…majiayu000ln-521-test-researcherResearches real-world problems, competitor solutions, and customer complaints before test planning. Posts findings as Linear…majiayu000load-test-generatorGenerate load test scripts for k6, Locust, and Gatling from OpenAPI specsa5c-aiwriteslocalization-dubbing-productionProvider-independent localization and dubbing production direction for AI agents producing translated videos, dubbed ads, social…calesthiologic-locateLocate the root cause of a CONFIRMED failure via backward-then-forward semi-formal tracing. Trigger when the user provides a…sickn33longbridge-correlationMulti-asset correlation and cointegration analysis via Longbridge Securities — computes Pearson / Spearman return correlation…majiayu000longbridge-dividend-screenHigh-dividend stock screen via Longbridge — analyse high-dividend-yield strategies for A-shares / HK / US, filter for sustainable…majiayu000longbridge-earningsPost-earnings analysis skill — generates institutional-grade earnings update reports (8–12 page DOCX) and structured conversation…majiayu000longbridge-graham-screenerGraham cigar-butt batch screener — runs Benjamin Graham's NCAV / net-net / defensive-investor hard filters across an index or…majiayu000longbridge-pairs-tradingPairs trading / statistical-arbitrage strategy via Longbridge Securities — tests cointegration between two correlated assets…majiayu000longbridge-quant-statsQuantitative statistics framework for time-series analysis using Longbridge price data — ADF unit root test (stationarity)…majiayu000longbridge-risk-analysisRisk measurement and stress testing via Longbridge — computes VaR (historical simulation / parametric), CVaR (expected…majiayu000lottie-animation-deliveryProduction guidance for assessing, exporting, packaging, integrating, capturing, validating, and handing off Lottie vector…calesthiolp-coverage-scanCoverage gap scanner for startup loop. Reads a business coverage manifest, scans the repo and known integrations for actual…majiayu000luma-ray-videoDirect and operate Luma Ray video generation through the current Luma Agents API and distinguish it from the consumer Luma App…calesthiolumen-abtestA/B test design — produce an experiment spec with hypothesis, primary metric, MDE, sample size, run time, and decision rule. Also…jeremylongshorewritesmake-git-escrowCreate a new git escrow bounty for a test suite. Use when the user wants to submit a challenge with escrowed token rewards for…internet-courtwritesmanim-explainer-animationProvider-independent production workflow for creating Manim-based explainer animations. Use when an agent must plan, code…calesthiomanual-test-planningProduce a plain-language manual test plan from the context supplied to it — an executive summary, a high-level list of named…testdoublewritesmatlab-assess-toolboxAssess toolbox readiness and suggest improvements — validates help text, tests, coverage, code issues, dependencies, and function…matlabmatlab-transmit-capture-usrpTransmit and capture RF waveforms using Wireless Testbench with NI USRP radios (X410, X310, N310, N320, N321, N300, X300, E320).…matlabmedia-provenance-rightsProvider-independent provenance, rights, consent, disclosure, and release governance for AI-generated media. Use when producing…calesthiomethylation-aggregationBuild comprehensive DNA methylation maps by aggregating WGBS (Whole Genome Bisulfite Sequencing) data across multiple ENCODE…majiayu000bio-methylation-methylkitDNA methylation analysis with methylKit in R. Import Bismark coverage files, filter by coverage, normalize samples, and perform…majiayu000metric-calculatorCompute well-defined metrics from existing formulas, datasets, or test outputs. Use as an explicit/manual helper when the metric…majiayu000writesmidjourney-videoPlan and direct Midjourney Video V1 image-to-video work through the official website or Discord, with human operator handoff…calesthiomigrate-xunit-to-mstestConvert .NET test projects from xUnit.net v2 or v3 to MSTest v4. Use for replacing xunit packages, [Fact]/[Theory], xUnit…dotnetminimax-musicProduce music with MiniMax Music 2.6 and MiniMax cover/lyrics APIs for songs, instrumentals, AI-generated lyrics, reference-audio…calesthiominimax-speechUse this skill when producing speech, narration, dubbing, localization, advertising voice, voice-clone previews, or interactive…calesthioml-deployment-helperPrepares ML models for production deployment with containerization, API creation, monitoring setup, and A/B testing. Activates…majiayu000model-ab-testUse when validating model downgrades for skills or agents. Runs A/B comparison between current and proposed model, scores outputs…majiayu000writesExplainabilitySee the main Model Explainability skill for comprehensive XAI coverage.majiayu000Model ManagerTest, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing…majiayu000mutation-testingEXPERIMENTAL — mutation testing with muter to measure whether tests actually assert anything: mutants that survive reveal…rshankraswritesnavan-multi-env-setupSet up dev/staging/prod environment separation for Navan integrations without a sandbox API. Use when configuring multiple…jeremylongshorewritesneural-reality-captureUse this skill for provider-independent reality capture that turns photographed or video-derived real places, objects, aerial…calesthionews-monitorSet up news monitoring strategies, analyze news coverage, and synthesize current events. Create news digests and media analysis…majiayu000nvidia-speech-nimUse NVIDIA Speech NIM microservices for speech production and voice workflows, including self-hosted ASR/STT, TTS, text…calesthioobsidian-local-dev-loopSet up a fast Obsidian plugin development loop with hot reload. Covers cloning the sample plugin, esbuild watch mode, symlinking…jeremylongshorewritesonenote-ci-integrationSet up CI/CD pipelines for OneNote integrations with Graph API testing and mock strategies. Use when configuring GitHub Actions…jeremylongshorewritespaid-creative-aiWhen the user wants to create AI-generated ad creative, test performance creative, manage creative fatigue, or optimize paid…tech-leads-clubpanel-dataEconometrics skill for panel data models. Activates when the user asks about: "panel data", "fixed effects", "random effects"…brycewang-stanfordpanel-design-selectionPanel structure design, firm selection criteria, right-sourcing analysis, and coverage gap assessment for in-house legal teams.…lawve-aipanel-review-rationalisationPanel health assessment, firm exit management, coverage gap analysis, and panel refresh brief for in-house legal ops teams.…lawve-aipathology-koan-generatorGenerate diagnostic koans to test reasoning boundaries and edge cases.majiayu000
← Prev16 / 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