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
1,4891,536 · page 32 / 36
proofQA and testing engineer — test strategy, E2E suites, API tests, flaky test triage, coverage.jeremylongshorewritesproperty-based-test-helperAssist with property based test helper operations. Auto-activating skill for Test Automation. Triggers on: property based test…jeremylongshorewritesproperty-based-testingProperty-based testing with fast-check (TypeScript/JavaScript) and Hypothesis (Python). Generate test cases automatically, find…foryourhealth111-pixelwritespropulsion-test-analysisSkill for propulsion system ground test data acquisition and analysisa5c-aiwritespsychrev-theory-constructionUse when building the actual theory or formal/computational model for a Psychological Review manuscript — turning a framed…brycewang-stanfordpubar-topic-selectionUse when deciding whether a public-administration project fits Public Administration Review (PAR) and which article type to…brycewang-stanfordpublic-ma-qa-informationWenn es um Public M&A und Kapitalmarkt / MAR in Corporate-Kanzlei geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und…Klotzkettepublic-relationsWhen the user wants to plan PR, write a press release, or manage media relations. Also use when the user mentions "public…kostja94pydeseq2-differential-expressionBulk RNA-seq DE with PyDESeq2: load counts, normalize, fit negative binomial models, Wald test (BH-FDR), LFC shrinkage…BioTender-maxpytest-coverageRun pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%.githubpytest-test-generatorGenerate pytest test generator operations. Auto-activating skill for Test Automation. Triggers on: pytest test generator, pytest…jeremylongshorewritespython-testingPython testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.mturacpython-testingPython testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.vibeevalPyTorch CSV Image Data Loading and VGG TrainingLoad flattened image data from a CSV file with specific schema (label + pixel columns), create train/validation/test data…ECNU-ICALKqa-handoff-packageTurn a story and its change into a clean 'ready for QA' package — test scenarios, edge cases, the data and environment setup, and…mohitagw15856qa-informationWenn es um Q&A und Information Requests in Großkanzlei Corporate/M&A geht: ordnet Akteninhalt, Belege, Lücken und…Klotzketteqa-information-requestsWenn es um Qa Information Requests in Großkanzlei Corporate/M&A geht: ordnet Akteninhalt, Belege, Lücken und Nachforderungen…Klotzketteqa-kanzleiweit-templating-praxis-verwalterWenn es um Skill-QA kanzleiweit in Kanzlei-Builder-Hub geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen…Klotzketteqa-quartoAdversarial Quarto vs Beamer QA. Critic finds issues, fixer applies fixes, loops until APPROVED (max 5 rounds).brycewang-stanfordwritesqa-release-signoffProduce a QA release sign-off / go-no-go readiness report. Use when asked for a release sign-off, a go/no-go QA report, release…mohitagw15856qaInteractive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the…stevesolunqe-tables-figuresUse when building or auditing tables and figures for a Quantitative Economics (QE) manuscript so exhibits follow QE house rules —…brycewang-stanfordqe-writing-styleUse when polishing prose, abstract, and introduction for a Quantitative Economics (QE) manuscript so a quantitative method and…brycewang-stanfordqualitaetspruefung-builder-daten-red-team-korrekturWenn es um Skills-QA in Kanzlei-Builder-Hub geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert…Klotzkettequarkus-tddTest-driven development for Quarkus 3.x LTS using JUnit 5, Mockito, REST Assured, Camel testing, and JaCoCo. Use when adding…mturacquinnProves the system works by writing and executing comprehensive test suites.sickn33quiz-generatorGenerate a quiz or test on any topic with a balanced mix of question types and difficulty, plus a complete answer key with…mohitagw15856react19-test-patternsProvides before/after patterns for migrating test files to React 19 compatibility, including act() imports, Simulate removal, and…githubreactive-commentTriage inbound journalist source queries and draft a response only when the user's expertise is a real fit. Runs each query…elvisunrealistic-prompt-generationGenerate natural, controlled prompt variants from a target-blind design brief and prompt architecture while preserving approved…elvisunrebuttalWorkflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only…brycewang-stanfordwritesrecipe-add-integration-testsAdd integration/E2E tests to existing codebase using Design Docsshinprrecsys-related-workUse when positioning an ACM RecSys submission against recommender-systems literature and its neighbors (SIGIR, KDD, WSDM…brycewang-stanfordred-green-refactorGuides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor…rohitg00red-team-reviewStress-test a plan, strategy, PRD, or launch by simulating hostile expert personas who attack it from every angle. Use when asked…mohitagw15856refactorThe behavior-preserving restructure gate. Routed to by /refactor for a rename, extract, inline, move, dedup, or…arbiterForgeregex-builderBuild a regular expression from a plain-English description, or explain an existing one. Use when asked to write a regex…mohitagw15856regression-test-planDesign and prioritize a regression test suite so changes don't break what worked. Use when asked to plan regression testing…mohitagw15856relay-80-100-workflowUse when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern…AgentWorkforcereplit-load-scaleLoad test and scale Replit deployments with Autoscale tuning, Reserved VM sizing, and capacity planning. Use when load testing…jeremylongshorewritesrepo-stats-autoupdateKeeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted…stevesolunrequirement-gap-finder需求補洞助手(探路模式)— 專用於「白紙一張、還沒有 PRD」的場合:站在 PM、UIUX、 Backend、Frontend、QA 五個角色,掃描需求的缺漏、容易誤解的敘述、沒考慮到的 Edge Case,…skinnerlee1225research_and_write_comprehensive_chapterResearches a specific topic across multiple domains and writes a cohesive, exhaustive non-fiction chapter with an educational…ECNU-ICALKresearch-companionStrategic research companion — brainstorm, evaluate, and decide on research directions. TRIGGER when the user wants to brainstorm…brycewang-stanfordopen-knowledge-pack-knowledge-base-researchInvestigate a topic against preserved sources and write a provisional research article under `research/` in a Knowledge Base…inkeepresearch-ops-skillsUse when planning, funding, scoping, or synthesizing enterprise research across workstreams — clinical study design, R&D program…alirezarezvaniresponse-complianceOpenResponses API compliance testing. Use for Response API endpoint tests, compliance runs, schema debugging, response api test…lobehubopen-knowledge-pack-software-lifecycle-review-a-designReviews whether a design is SOUND — solving the right problem, derived from its stated goals and constraints — and emits ranked…inkeep
← Prev32 / 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