agentsclimarketplace

Test

10,621 rows, by stacks then stars

1,559 of these skill files have been read, by 1,201 distinct authors, and what they tell an agent counted. What Test authors agree on, and what they forbid

  • Agentic test update

    jpbaking/agentic-tests/skills/shared/agentic-test-update Skill

    1★ repo

    Reconcile agent tests after the user INTENTIONALLY changed main-code behavior — show each failing agent test as old-locked vs new-actual behavior, and update tests only with per-diff user confirmation. Use when agent tests fail after a deliberate behavior change.

  • Agentic unit test

    jpbaking/agentic-tests/skills/shared/agentic-unit-test Skill

    1★ repo

    Generate agent-authored unit tests ("agent tests") to reach a user-defined coverage goal for one target file/class or the whole project, without ever modifying main code or user-made tests. Use when asked to write unit tests, raise coverage, or lock down existing behavior before refactoring/optimization.

  • Vue testing best practices

    JunfengRan/dev-env/skills/vue-testing-best-practices Skill

    1★ repo

    Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.

    The same file is in 6 other repositories

  • Nestjs testing

    dkmqflx/nestjs-best-practices-plugin/plugins/nestjs-best-practices/skills/nestjs-testing Skill

    1★ repo

    NestJS testing best practices (unit and e2e). Use when writing or reviewing NestJS tests — Test.createTestingModule, mocking providers, controller/service unit tests, or e2e with supertest. Triggers on TestingModule, createTestingModule, overrideProvider, or supertest.

    The same file is in 1 other repository

  • Add sample data

    LeonardSEO/power-platform-skills-codex/plugins/power-pages/skills/add-sample-data Skill

    1★ repo

    Populates Dataverse tables with sample records for testing and demoing a Power Pages site. Use when the user wants to add sample data, seed data, generate test records, or insert demo data into their tables.

    The same file is in 1 other repository

  • Test site

    LeonardSEO/power-platform-skills-codex/plugins/power-pages/skills/test-site Skill

    1★ repo

    Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

    The same file is in 1 other repository

  • Skill

    mohamedzhioua/proofguard/deferred/test-quality-guard/skill Skill

    1★ repo

    Kills fake, low-value, or bug-locking tests — tests that assert nothing meaningful, tests that mock the very unit under test, and tests that assert CURRENT (possibly buggy) behavior instead of correct behavior. Best used reactively after tests are written, generated, or changed. Use when the user says "add tests", "write unit tests", "increase coverage", "is this tested?", or after a coding agent produced or modified test code. DO NOT USE for production (non-test) code review (use clean-diff-guard) or for verifying a task is done (use evidence-before-done); this guard reviews TEST code quality specifically.

  • Docs drift guard

    mohamedzhioua/proofguard/skills/docs-drift-guard Skill

    1★ repo

    Blocks calling a code change "done" when it renamed, added, removed, or changed a public name, flag, command, default value, count, config key, or behavior but left the docs (README, CHANGELOG, docs/, examples, --help text, code comments/docstrings) still referencing the old surface. Best used reactively after code changes a public name, flag, command, default value, count, config key, or behavior. Use when the user says "rename", "change the flag", "update the API", "add a command", "bump the version", or after any change to a user-facing surface. DO NOT USE for pure internal refactors with no public surface, or for verifying tests (test-code quality is out of proofguard's scope; a test-quality-guard is in `deferred/`, not yet shipped); this guard checks that DOCS match the code after a change.

  • Cheapest discriminating test

    ralfyishere/piensalo/micro-skills/cheapest-discriminating-test Skill

    1★ repo

    With multiple live hypotheses and a limited test budget, design the cheapest single test whose possible outcomes separate the hypotheses — with a results-to-verdict table committed before running anything. Activate when two or more competing hypotheses are on the table and the next step is choosing what test, experiment, or probe to run.

  • Analytics

    cskwork/supermarketer-skill/vendor/marketingskills/skills/analytics Skill

    1★ repo

    When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this," "track conversions," "attribution," "Mixpanel," "Segment," "are my events firing," or "analytics isn't working." Use this whenever someone asks how to know if something is working or wants to measure marketing results. For A/B test measurement, see ab-testing.

    The same file is in 3 other repositories

  • Laravel testing

    noppu-labs/ai-toolkit/laravel/skills/laravel-testing Skill

    1★ repo

    Laravel 13 testing with Pest PHP 4 or PHPUnit 12. Use when writing feature tests, unit tests, or any test code in a Laravel application. Triggers on tasks involving HTTP tests, model factories, database assertions, mocking facades, authentication testing, or test organisation patterns.

    The same file is in 7 other repositories

  • Laravel validation

    noppu-labs/ai-toolkit/laravel/skills/laravel-validation Skill

    1★ repo

    Form request validation and comprehensive validation testing. Use when creating or modifying form requests, validation rules, or validation tests.

    The same file is in 2 other repositories

  • Code reviewer

    yinyoudexing/skill-compass/examples/demo-skills/code-reviewer Skill

    1★ repo

    Use when reviewing changes for correctness, maintainability, regressions, and test coverage

  • Fastapi testing

    dkmqflx/fastapi-best-practices-plugin/plugins/fastapi-best-practices/skills/fastapi-testing Skill

    1★ repo

    FastAPI testing best practices. Use when writing or reviewing tests for a FastAPI app — TestClient, dependency_overrides, async httpx clients. Triggers on TestClient, AsyncClient, ASGITransport, dependency_overrides, or pytest test files for FastAPI endpoints.

    The same file is in 1 other repository

  • Skillproof

    Dafenxz0/skillproof/skills/skillproof Skill

    1★ repo

    Design, run, audit, and interpret evidence-based benchmarks for Agent Skills. Use when proving whether a SKILL.md improves outcomes, comparing baseline/automatic/forced use, testing activation or false activation, measuring quality/tokens/cost/latency, detecting regressions, or producing a reproducible SkillProof report. Also use to repair weak skill benchmarks or scope unsupported benchmark claims. Do not use for ordinary coding, writing, or analysis merely because it mentions tests, metrics, models, or benchmarks.

  • 507 tdd

    ssdiwu/507-skills/code/507-tdd Skill

    1★ repo

    测试驱动开发:仅在用户明确要求 test-first、TDD、先写测试或红绿重构时,以垂直切片完成行为测试、最小实现和全绿重构。Use when user says tdd, test-first, 先写测试, 测试驱动, 红绿重构, test driven development.

  • 507 test

    ssdiwu/507-skills/code/507-test Skill

    1★ repo

    测试任务:测试本身是主要任务时,用现有框架补行为测试、运行测试、修正过时测试或缩小失败范围;真实生产 bug 转根因修复。Use when user says test, testing, 写测试, 加测试, 补测试, 跑测试, 运行测试, 测试挂了, 测试失败, 修失败测试, 缩小失败范围, coverage.

  • Implement

    eduardkumskyi/octo/skills/implement Skill

    no license1★ repo

    Supervised execution of a plan task-by-task: implementer writes code, test-engineer adds tests, targeted tests run, user checkpoint between batches. File-disjoint tasks run in parallel.

  • Test

    eduardkumskyi/octo/skills/test Skill

    no license1★ repo

    Run only the tests affected by the current diff, printing which tests were selected and why. Full suite with --all. Reads the project's test command and subset syntax from CLAUDE.md.

  • Mutation testing

    andr-ca/agentharness/.claude/skills/mutation-testing Skill

    1★ repo

    Use when writing tests for critical business logic, auditing test suite quality beyond line coverage, or interpreting surviving mutants — covers mutation operators, mutation score thresholds, and tooling (mutmut, Stryker, gremlins) for Python, TypeScript/JS, and Go.

  • Testing

    andr-ca/agentharness/.claude/skills/testing Skill

    1★ repo

    Use when writing tests, deciding on test coverage, choosing between unit/integration/E2E tests, applying TDD, or reviewing test quality — covers rigor tiers, the Red-Green-Refactor cycle, coverage requirements, and Playwright for UI testing.

  • Conversion cro

    whatsuppiyush/god-of-skills/marketing/conversion-cro Skill

    1★ repo

    Conversion rate optimization for landing pages, product pages, and checkout flows. Use whenever the user wants more signups, purchases, or leads from the same traffic; is writing or auditing a hero section, landing page, or PDP; mentions above-the-fold, headline, value prop, CTA, social proof, reviews, cart abandonment, checkout friction, popups, A/B tests, or funnel drop-off; says "my page gets traffic but no conversions," "why do people bounce," "fix my landing page," "improve checkout completion," or "which version should I test." Also use to diagnose a leaky multi-step funnel or to decide what to test next.

  • Analytics data

    whatsuppiyush/god-of-skills/research/analytics-data Skill

    1★ repo

    The discipline of measuring growth honestly: finding the metric that matters, proving a change actually caused a result, and prioritizing what to test next. Use whenever the user is choosing KPIs or dashboard metrics, mentions activation threshold / magic number / aha metric, wants to run or audit A/B experiments, asks "did this actually work / was it causal", is confused why platform ROAS doesn't match real growth, needs attribution or incrementality or holdout tests, wants to measure PMF, is designing surveys (Sean Ellis 40% test, churn, post-purchase NPS), needs to prioritize a backlog (RICE / DRICE), or is stalling on growth and debating tactics. Trigger phrases: "which metric should I track", "is this a vanity metric", "how do I prove incrementality", "why is my reported ROAS so high", "how do I measure PMF", "what should I test next", "how do I prioritize experiments", "growth is stalling, where's the problem".

  • Node testing

    Paldom/node-skills/skills/node-testing Skill

    1★ repo

    Builds unit and integration test infrastructure for Node/TS/React - Vitest or node:test selection with explicit config, v8 coverage gates that fail CI, React Testing Library, mocking discipline, flaky-test triage. Use when the user asks to set up tests, add coverage thresholds, pick a test runner, or fix a flaky test setup. Not for E2E browser suites, lint rules, or CI workflow authoring.

  • Mobile verification

    jeremyinthebay/relay-skills/skills/mobile-verification Skill

    1★ repo

    Test what a page actually DOES on a phone — real taps, real scrolling, real animations — using Playwright instead of a browser-automation tab that is structurally blind to motion. Use whenever verifying mobile behaviour, testing touch interactions, checking horizontal overflow or touch-target sizes, before merging any front-end change, or when a scroll/animation/click test reports "nothing happened" and you need to know whether the page is broken or your harness is.

  • Implement spec

    dineshrevunuru/SuperSkills/implement-spec Skill

    1★ repo

    Drive a spec or set of tickets to shipped, committed code — the conductor of the SHIP-wing rigor path. Agrees the test seams up front, builds in vertical slices (red→green via `test-shipped-code` at each seam), runs `review-shipped-code` as an AND-gate before commit, and routes surprise breakage to `diagnose-bugs`. Use when asked to 'implement this spec', 'build this ticket', 'build out the feature', 'work through the tickets', 'implement what the spec says', 'build the booking flow', or before committing a shipped Next/React/TypeScript feature. Solo-first: the 'tickets' are a workpack BUILD-SPEC / tasks.json / a plain checklist, NOT an assumed Jira board — mode-switches UP to a tracker only when Dinesh actually has one. NOT for prototypes (build-coded-prototypes owns those — no tests, no review gate).

  • Plan usability test

    dineshrevunuru/SuperSkills/plan-usability-test Skill

    1★ repo

    Plans a usability test end-to-end the NN/g way: study goals → qual/quant fork → sample size (5-user rule and exactly when it fails) → moderated/unmoderated × remote/in-person mode choice → recruiting numbers → mandatory pilot with fix-then-freeze. Use when asked to 'plan a usability test', 'set up user testing', 'test this prototype/app/flow', 'how many users do I need', 'is 5 users enough', 'moderated or unmoderated?', 'remote or in-person?', or when a stakeholder wants metrics from a small study. Produces a complete test plan document.

  • Run contextual research

    dineshrevunuru/SuperSkills/run-contextual-research Skill

    1★ repo

    Plans and runs research in the user's real environment or real timeline: contextual inquiry (master-apprentice, in-context interview), field studies (observation-first site visits), and diary studies (longitudinal self-logging plus elicitation interview). Use when someone says 'watch users where they actually work', 'contextual inquiry', 'field study', 'site visit', 'shadow users', 'ethnographic', 'diary study', 'log their experience over time', or when a behavior can't be reproduced in a lab or a single session — workarounds, interruptions, expert workflows, multi-day journeys. NOT for lab/task-based testing (plan-usability-test) or single-room interviews (conduct-user-interview).

  • Run heuristic evaluation

    dineshrevunuru/SuperSkills/run-heuristic-evaluation Skill

    1★ repo

    Runs an expert usability inspection without users: Nielsen's 10 heuristics operationalized with per-heuristic violation questions, a multi-evaluator two-pass protocol with aggregation, and a cognitive walkthrough for learnability. Produces a prioritized expert-review deliverable. Use when someone says 'run a heuristic evaluation', 'expert review this UI', 'inspect this against the heuristics', 'cognitive walkthrough', 'find usability problems without testing users', or when there is no time/budget/access for a usability test. NOT for severity rating (analyze-usability-data owns the 0–4 scale), WCAG audits (audit-accessibility), or testing with real users (plan-usability-test).

  • Structure information architecture

    dineshrevunuru/SuperSkills/structure-information-architecture Skill

    1★ repo

    Designs and validates information architecture — organization schemes, hierarchy, labels, polyhierarchy — then proves it with card sorts and tree tests as one generate→evaluate loop. Use when organizing content or features into categories, naming navigation labels, building a sitemap, planning or analyzing a card sort or tree test, reading a dendrogram or similarity matrix, or when users 'can't find' things ('users can't find X', 'how should we organize the nav', 'run a card sort', 'is this hierarchy right', 'interpret these tree test results', 'fix our IA').

  • Test shipped code

    dineshrevunuru/SuperSkills/test-shipped-code Skill

    1★ repo

    Test-first discipline for the PRODUCTION client code Dinesh ships — a live salon booking app, Next/React/TypeScript surfaces real users touch. Red before green: write the failing behavior test, then only enough code to pass it. Use when building or changing a shipped feature test-first, or when someone says 'write a test for this', 'add test coverage', 'red-green-refactor', 'TDD this', 'test the booking logic', 'is this test actually testing anything', or 'this passes but I don't trust it' — and before merging any logic/state/data change to a live app. Hard-scoped to shipped code: NEVER for prototypes (build-coded-prototypes says skip tests there). Mode-switches — full TDD for logic/state/data; a screenshot via verify-ui-quality for pure-visual work. Wired to Vitest / Jest / Playwright.

  • Use quantitative evidence

    dineshrevunuru/SuperSkills/use-quantitative-evidence Skill

    1★ repo

    Designs and reads quantitative UX evidence honestly: hypothesis-first A/B tests with a traffic/duration feasibility gate, a decision tree for when A/B is the WRONG tool (why-questions, low traffic, strategic redesigns), statistical vs practical significance, the analytics what-not-why limit with a mandatory follow-up qual spec, and the firewall against reporting metrics from 5-user studies. Use when someone says 'should we A/B test this', 'which version won', 'is this statistically significant', 'run an experiment', 'the analytics show a drop-off', 'what percent of users…', or tries to quote percentages from a small qualitative study. NOT for choosing metrics or instruments (define-ux-success-metrics) or for analyzing qual usability sessions (analyze-usability-data).

  • Test data gen

    NSBen/skillfoundry/src/skillfoundry/data/starter_skills/test-data-gen Skill

    1★ repo

    Use when tests need realistic fixtures or mock data and you want to generate them deterministically instead of copying production data.

  • Write tests

    NSBen/skillfoundry/src/skillfoundry/data/starter_skills/write-tests Skill

    1★ repo

    Use when a module or function lacks tests and you need to generate meaningful unit or integration tests that cover the real behaviour.

  • Test skill

    scullxbones/armature/internal/skillsembed/skills/test-skill Skill

    no license1★ repo

    Agent harness task DAG tracker; git-based, zero-dependency agentic context seeding with spec citation and audit tracking

  • Playwright

    mblauberg/provenant/skills/playwright Skill

    1★ repo

    Use for terminal-driven browser navigation, interaction, snapshots, screenshots, extraction, or UI-flow debugging. Not for authoring Playwright test suites or frontend design; use tdd or ui-ux-design.

  • Tdd

    mblauberg/provenant/skills/tdd Skill

    1★ repo

    Use for writing the first right-reason failing test for new or changed observable behaviour, then red-green-refactor. Not for behaviour-preserving structure, diagnosis-only, or delivery; use refactor, diagnose, or implement.

  • Test driven development

    furkangonel/cowrangler/bundled_skills/software-development/test-driven-development Skill

    1★ repo

    TDD workflow — Red, Green, Refactor cycle with practical examples.

  • Testing

    furkangonel/cowrangler/bundled_skills/testing Skill

    1★ repo

    Test writing SOP for unit, integration, and e2e tests (TDD) plus exploratory QA for web apps — find bugs, gather evidence, write reports.

  • Skip skill listing in test environment

    vishuwa2004/cskill-agents/agents/claude-code/skills/skip-skill-listing-in-test-environment Skill

    1★ repo

    Suppress skill-listing attachments in test mode so discoverability noise does not interfere with deterministic test behavior.

    The same file is in 1 other repository

  • Skip skill listing in test environment

    vishuwa2004/cskill-agents/agents/codex/skills/skip-skill-listing-in-test-environment Skill

    1★ repo

    Suppress skill-listing attachments in test mode so discoverability noise does not interfere with deterministic test behavior.

    The same file is in 1 other repository

  • Skip skill listing in test environment

    vishuwa2004/cskill-agents/skills/skip-skill-listing-in-test-environment Skill

    1★ repo

    Suppress skill-listing attachments in test mode so discoverability noise does not interfere with deterministic test behavior.

    The same file is in 1 other repository

  • Test argument

    OC-NeuralSense/reader-first-writing-skills/skills/test-argument Skill

    1★ repo

    Evaluative. Activate to check whether a set of claims actually supports its conclusion and to find anything unsupported. Common phrasings: "Do these points actually support my conclusion?", "Find any claims here that aren't actually supported", "Is this parent a real summary of its children?". Expected inputs: an argument-blueprint, or a bare conclusion plus its claims. Reports defects on the soundness layer; it NEVER rewrites, re-groups, or drafts. Do NOT activate when the user wants a full layered draft diagnosis across structure and prose (use diagnose-draft), wants the structure built from scratch (use build-argument), or wants defects actually fixed (use revise-structure). This skill only judges soundness and produces a report.

  • Test writer

    claudifytech/claude-code-skills-starter/skills/test-writer Skill

    0★ repo

    Generate tests that match the project's existing test patterns and framework

  • Test scope definition

    thinkyou0714/claude-lab-skills/lab-implementation-flow/skills/test-scope-definition Skill

    0★ repo

    実装・変更に対して何をどこまでテストすべきかを定義する。テスト種別・対象・優先度・合否基準を整理し、テスト不足による手戻りを防ぐ。テスト計画を立てるときに使う。

  • Test driven development

    zjy1020/claude-code-skills/skills/test-driven-development Skill

    0★ repo

    Use when implementing any feature or bugfix, before writing implementation code

  • Design experiment plan

    alexe-ev/product-plugins/experimentation/skills/design-experiment-plan Skill

    0★ repo

    Build a complete product experiment plan from a validated hypothesis, metrics, and testing assumptions. Use this skill when the user is ready to prepare an A/B test or structured product experiment for execution.

  • Recommend post test decision

    alexe-ev/product-plugins/experimentation/skills/recommend-post-test-decision Skill

    0★ repo

    Recommend what to do after an experiment based on the result quality, effect size, and business context. Use this skill when the user has a completed experiment and needs a practical product decision such as roll out, rerun, iterate, segment-rollout, or reject.

  • Validate hypothesis quality

    alexe-ev/product-plugins/experimentation/skills/validate-hypothesis-quality Skill

    0★ repo

    Evaluate whether a product experiment hypothesis is specific, measurable, and suitable for testing. Use this skill when the user already has a draft hypothesis and wants to know if it is strong enough for an A/B test or other product experiment.

  • Run usability testing

    alexe-ev/product-plugins/ux-research/skills/run-usability-testing Skill

    0★ repo

    Structure and synthesize usability testing sessions and feedback loops. Use this skill when a team needs to evaluate a design or flow by observing real users attempting to use it.

  • Finishing a development branch

    deokjinlog/intent-locked-workflow/skills/finishing-a-development-branch Skill

    0★ repo

    Use when implementation is complete and tests pass. Runs the test gate one final time and emits a single termination message; user manually decides merge / PR / keep / discard. (v1.1.14 슬림화 — AskUserQuestion 게이트 + boilerplate 제거)

  • Test driven development

    deokjinlog/intent-locked-workflow/skills/test-driven-development Skill

    0★ repo

    Use when implementing any feature or bugfix, before writing implementation code

    The same file is in 33 other repositories

  • Test

    azadmotala/claude-code-team-builder/examples/saas-dashboard/.claude/skills/test Skill

    0★ repo

    Run the TenantFlow test suite. Vitest unit tests and Playwright e2e tests.

  • Feature test

    telefrek/vallorcine/skills/feature-test Skill

    0★ repo

    Write failing tests from work-plan contracts and acceptance criteria

  • Nextauth local e2e session

    bokuwalily/claude-code-skills/skills/nextauth-local-e2e-session Skill

    0★ repo

    next-auth(v5/JWT)+Google OAuthのみのNext.jsアプリを、本番DBに触れずローカルdevでログイン済みE2E検証したいとき。セッションCookieを自作mintし、TURSO等のDB env をfile DBに差し替えて Playwright で通す手順。

  • 10x tester

    arhuman/claude-plugins/plugins/10x/skills/10x-tester Skill

    no license0★ repo

    Comprehensive testing specialist for all levels and types. Use when writing unit, integration, E2E, performance, or security tests; creating test strategies and plans; analyzing test coverage; building automation frameworks; managing defects; debugging test failures; manual testing (exploratory, usability, accessibility); scaling CI/CD test pipelines.

  • Specdd test

    specdd/plugin-claude/skills/specdd-test Skill

    0★ repo

    Use when Claude Code needs to derive, add, update, or assess tests from active SpecDD specs.

  • Specdd trace

    specdd/plugin-claude/skills/specdd-trace Skill

    0★ repo

    Use when Claude Code needs to trace SpecDD specs to code, tests, docs, changed files, or coverage gaps.

  • Contribute

    opendatadiscovery/odd-team/.claude/skills/contribute Skill

    0★ repo

    Resolve a GitHub issue on opendatadiscovery/odd-platform end-to-end as a virtual contributor — scope, reproduce, root-cause, plan (GATE 1), change code, add unit + integration tests, update docs + ontology, open a DRAFT PR (GATE 2). Composes the ontology / test / doc / adr machinery; posts clarifying + root-cause comments via a scoped-token GitHub App; never merges.

  • Coverage

    opendatadiscovery/odd-team/.claude/skills/coverage Skill

    0★ repo

    Show scan coverage across all scanners — what's been analyzed, what remains, what changed since last scan.