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

  • Qa loop

    pedroberaldo87/pedro-plugins/plugins/qa-loop/skills/qa-loop Skill

    no license0★ repo

    Use quando o usuário quer revisar código num loop disciplinado que para por retornos decrescentes (qualidade vs vale a pena), não por zero erros. Ancora no plano de implementação — toda rodada checa fidelidade ao plano e classifica cada finding em implementação, plan-drift ou plano-falho; conserta só implementação com regression gate por conserto; materializa accepted-limits; e entrega relatório humano (HTML) + journal agêntico pra avaliar o nº ideal de loops com o tempo. A skill tem duas fases — uma assintótica de review (severidade variável; e2e/Playwright vira actionable, não bloqueia) e uma Fase Gate absoluta (lint, type, unit e integração 100% verdes no repo inteiro, pré-existentes incluídos, ou gate-red). O motor roda como um Workflow determinístico all-Opus (Opus revisa, Opus planeja, Opus conserta). Substitui /qa, /rev6 e /iterate. Trigger em "/qa-loop", "/qa", "/rev6", "audita o plano", "tá 100%", "revisa isso", "review multi-ângulo", "loopa o review", "revisa até valer a pena".

  • Test and oracle builder

    alainlebret/claude-agents/higher-ed-teaching-agents/skills/test-and-oracle-builder Skill

    0★ repo

    Builds tests, evaluation oracles, case matrices, and validation scripts for assignments, labs, exams, and projects in computing. Use when a pedagogical artifact must be corrected reliably and reproducibly.

  • Playwright login session

    baronguyen001/ai-automation-skills/skills/playwright-login-session Skill

    0★ repo

    Log in once in a real browser, save the Playwright storage_state, then start every later run already signed in - no re-login, no committed cookies. Use for reuse a logged-in session, skip login on each run, save browser cookies, storage_state, or keep a scraper authenticated.

  • Playwright pdf snapshot

    baronguyen001/ai-automation-skills/skills/playwright-pdf-snapshot Skill

    0★ repo

    Render any URL to a headless PDF or PNG snapshot with Playwright and no committed cookies. Use when the user asks to archive a page, capture a dashboard/report, make a PDF snapshot, or save a page screenshot for downstream review.

  • Labrodev testing

    labrodev/laravel-playbook/skills/labrodev-testing Skill

    0★ repo

    Use when writing or reviewing Pest tests in a Labrodev Laravel project: testing Actions, Rules, Services, or Data validation, adding route-level Feature tests, creating domain-state helpers in tests/Pest.php, or adding/maintaining the Pest architecture test suite that mechanically enforces the playbook.

  • Testing

    Shankulkarni/react-native-ai-plugin/plugins/rn-ai/skills/testing Skill

    0★ repo

    Use when writing tests for a React Native app -- Jest + jest-expo preset, React Native Testing Library, Reanimated mocks, React Query test setup, what to test and what not to.

  • Nebo testing qa

    lifenewjob/nebo-claude-skills-public/skills/nebo-testing-qa Skill

    0★ repo

    TESTING-QA. Triggers: TDD, тесты, pytest, coverage, code review QA, BDD, mutation testing

  • Bedrock

    kennykankush/skillpack/plugins/workbench/skills/bedrock Skill

    no license0★ repo

    Foundation audit mode. Walk a codebase as an adversarial building inspector - stress-test load-bearing logic to bank-grade, limit-test feature flows by actually running them, and file a fragility report backed by runnable repros. Maintains an AUDIT.md ledger at repo root across runs. Use when the user asks to audit the foundations, check whether things are foundationally strong or flaky, run a bank-logic check, limit-test or stress-test features after a heavy build sprint, question the codebase from first principles, or harden what the audit found ("report and fix"). Two modes - report (default) and report-then-fix.

  • Gauntlet

    kennykankush/skillpack/plugins/workbench/skills/gauntlet Skill

    no license0★ repo

    Run a system through its trials. Drive a realistic, goal-driven user journey end-to-end as the spine, and at every action the user takes, sweep-test the REAL subsystem behind it — a surface pass (breadth across the whole journey that also triages each touchpoint into a risk-ranked hit-list) funnelling into a deep pass (depth on the risky stations: a varied + adversarial population, breadth × volume, independent verification). It proves both that the user's experience held AND that the machinery is sound. Skeptical flaw-hunting stance, safe and reversible. Use when the user says "gauntlet this flow/journey", "sweep-test the whole pipeline end to end", "simulate a user and stress the machinery behind each step", "is X sound front to back", "god+user sweep", or "run the gauntlet on payments/scoring/onboarding". A fusion of deterministic simulation testing, agent playtesting, synthetic user journeys, and the test-oracle problem — bedrock's bigger sibling.

  • Aria skill test

    iansteitz1-eng/aria-skills/aria-skill-test Skill

    no license0★ repo

    Regression harness for the aria-skills repo. Runs every shipped skill in dry-run mode + asserts clean output (no traceback, no credential leaks, valid SKILL.md frontmatter, README.md present). Text report by default; --junit-xml flag for CI integration. Use when the user says "test the skills", "regression check", "before push", "run the test harness", or any time before opening a PR or pushing to main.

  • Test perspective

    kompiro/hane/skills/test-perspective Skill

    0★ repo

    Reusable Claude Code skills for branch/worktree-based PR workflow, design docs, acceptance tests, and doc maintenance.

  • Done prover

    dhruba-datta/claude-papercuts/skills/done-prover Skill

    0★ repo

    Verify Claude's claim that tests are passing. Use this skill when the user wants to know whether a recent "all tests pass" or "feature complete" statement was honest, or when the user mentions Claude lied about completion. Reads the most recent test output from the conversation transcript and surfaces any discrepancy between what Claude claimed and what the test runner actually reported. Auto-triggered by a Stop hook whenever Claude makes a test-pass claim in its final message.

  • Hello

    jordanl17/visill/packages/visill-build/test/fixtures/hello.golden/skill/hello Skill

    0★ repo

    A minimal fixture skill for @visill/build tests.

  • Skill src

    jordanl17/visill/packages/visill-build/test/fixtures/hello/skill-src Skill

    0★ repo

    A minimal fixture skill for @visill/build tests.

  • Uat

    brandtam/skills/skills/uat Skill

    0★ repo

    Run a user acceptance testing session with collect-grill-PRD workflow. Use when user says "uat", "start uat", "acceptance testing", "let's test", or invokes /uat. Captures observations as checklist items, grills for decisions, then generates a PRD.

  • Tdd

    Viniciusmq25/skills/tdd Skill

    0★ repo

    Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

  • Test tool

    Sylad/claude-code-codex/.claude/skills/test-tool Skill

    0★ repo

    Use when the user wants to evaluate a third-party Claude Code tool (npm package, GitHub repo, plugin marketplace) before adopting it. Triggers on phrases like "/test-tool", "on teste X", "let's evaluate X", "is X any good?", or when the user shares a GitHub URL of a tool to assess. Runs the systematic test bench protocol (snapshot → install in sandbox → verify pollution → minimal usage → verdict → cleanup) and ships the verdict to the claude-code-codex Tools tested catalog.

  • Pentest ai threat testing

    bertbertov/claude-stack/skills/pentest-ai-threat-testing Skill

    0★ repo

    Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.

  • Playwright recording

    bertbertov/claude-stack/skills/playwright-recording Skill

    0★ repo

    Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.

  • Tdd workflow

    bertbertov/claude-stack/skills/tdd-workflow Skill

    0★ repo

    Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

    The same file is in 8 other repositories

  • Tob differential review

    bertbertov/claude-stack/skills/tob-differential-review Skill

    0★ repo

    Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.

    The same file is in 4 other repositories

  • Test report from issue

    hsinhan-h/hh-claude-skills/test-report-from-issue Skill

    no license0★ repo

    Generates a Word (.docx) test report from a GitHub issue's verification checklist — a summary table plus a per-item detail section with blank space to paste results. Use when the user asks to create a test report / QA report / 測試報告 / 驗證報告 for a specific GitHub issue, or wants to turn an issue's checklist ("Test Plan", "Checklist", "驗證項目", "測試項目", or a raw "- [ ]" list) into a fillable Word document.

  • Garelier scout

    aby-studio-works/garelier/skills/garelier-scout Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/scout invocation, not on generic research/investigate/inspect/report wording. Scout reads one assignment.md from Dock, does the work WITHOUT any code commits, writes an inspection draft to `__garelier/<pm_id>/control/inspections/<category>/YYYY/MM/YYYY-MM-DD-<topic>.md`, and reports back for Dock review and PM commit. Handles commit-free tasks: web research, market studies, accounting/tax review, full test-suite runs, deploy health checks, benchmarks, external API checks, metrics collection, daily reports, data整理. Activate in a `__garelier/<pm_id>/_scouts/<id>/` worktree, when assignment.md appears, when answers.md arrives after a BLOCKED state, or on Scout terms — "investigate", "research", "inspect", "report on", "check", "survey", "daily report", "日報". Requires garelier-core.

  • Garelier smith

    aby-studio-works/garelier/skills/garelier-smith Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/smith invocation, not on generic hardening/integration-test/anvil wording. Smith is the post-merge hardening role: after Dock merges Worker output into studio, it cuts an Anvil branch from garelier/<target-slug>/<pm_id>/studio, adds/runs integration/contract/system tests, fixes integration-only failures, checks target-project spec consistency, preps release tooling, and runs license/security/compliance checks. Activate in a `__garelier/<pm_id>/_smiths/<id>/` worktree, when assignment.md appears for a Smith, review.md signals Anvil rework, or merged.md arrives after Dock merges the Anvil branch. Requires garelier-core.

  • Pm pmf coach

    kalyvask/pm-evaluation-framework/.claude/skills/pm-pmf-coach Skill

    0★ repo

    Walk a founder or early-stage PM through finding product-market fit on a specific bet. Use when the user is pre-PMF (no validated value hypothesis), has a candidate insight + audience + business model, and needs help deciding what to test next, how to interpret a failed experiment, and whether to pivot (change who/how) or restart (change what). Different from pm-value-hypothesis-tester which pressure-tests a single hypothesis statement statically; this skill runs the multi-step PMF process iteratively. Built on the Lean Startup synthesis (Rachleff, Ries, Blank, Moore, Christensen, Marks, Fitzpatrick, Cook).

  • Rails clean test output

    mickzijdel/rails-toolkit/skills/rails-clean-test-output Skill

    0★ repo

    Systematically eliminate unexpected output (warnings, stray puts/p/pp, deprecation notices) from a Rails test suite, one issue at a time, with per-fix verification and commits. Works for both RSpec (`bundle exec rspec`) and Minitest (`bin/rails test`) - detect which the project uses and adapt. Use whenever the user wants to clean up, silence, fix, or investigate noisy test output, mentions warnings or stray logs during test runs, or asks to get their suite running "clean" - e.g. "my test output is noisy", "there's a bunch of warnings when I run specs/tests", "help me clean up the test output".

  • Rails core

    mickzijdel/rails-toolkit/skills/rails-core Skill

    0★ repo

    Use FIRST on any Ruby on Rails work — the project owner's hard-won Rails gotchas and non-negotiable rules (fixtures, migrations, Stimulus LSP, validation, gems, test suite). Read before writing or changing Rails code.

  • Rails testing

    mickzijdel/rails-toolkit/skills/rails-testing Skill

    0★ repo

    Agent skills for working with Ruby on Rails 8+

  • Leadup browser playwright tester

    leadupofficial/leadup-claude-skills/leadup-browser-playwright-tester Skill

    0★ repo

    Test a LeadUp app end-to-end in the browser. Runs the app locally (Docker or dev server), exercises login, forms, navigation, and admin flows, checks console errors and mobile responsiveness, and creates or updates Playwright specs. Use when the user says "test website", "run Playwright", "browser test", "check UI works", "test admin panel", or "test login".

  • Leadup qa test case generator

    leadupofficial/leadup-claude-skills/leadup-qa-test-case-generator Skill

    0★ repo

    Generate manual and automated test cases for a LeadUp website, SaaS, admin panel, API, mobile app, or deployment — including critical user flows, edge cases, Playwright test ideas, mobile/responsive checks, admin panel tests, payment/deploy tests, and clear acceptance criteria. Use when the user says "test cases", "QA plan", "manual testing", "Playwright tests", "test this app", or "create test cases".

  • Opp repl cli tools

    tabgab/opp_repl-skill/opp-repl-cli-tools Skill

    no license0★ repo

    Use the opp_repl shell wrappers (opp_build_project, opp_run_simulations, opp_run_*_tests, opp_update_*_test_results) from scripts and CI pipelines instead of the IPython REPL. Load for non-interactive workflows — covers shared flags, project auto-detection from CWD, filtering, build modes, and exit codes.

  • Opp repl coverage reports

    tabgab/opp_repl-skill/opp-repl-coverage-reports Skill

    no license0★ repo

    Generate C++ line-coverage reports from simulation runs using opp_repl's `coverage` build mode and LLVM coverage tools. open_coverage_report builds, runs, and opens the HTML report; generate_coverage_report just produces it. Load when you need to know which C++ lines are exercised by a given simulation or test.

  • Opp repl feature and release tests

    tabgab/opp_repl-skill/opp-repl-feature-and-release-tests Skill

    no license0★ repo

    Comprehensive test suites — feature tests verify builds with different optional feature combinations, release tests validate release candidates, and run_all_tests sequentially runs every configured test type. Load for release-gate CI pipelines that want one call to rule them all.

  • Opp repl fingerprint tests

    tabgab/opp_repl-skill/opp-repl-fingerprint-tests Skill

    no license0★ repo

    Detect behavioral regressions using simulation event fingerprints (hash-based). run_fingerprint_tests compares a computed hash of selected state against a stored baseline in the project's fingerprint_store JSON. update_fingerprint_test_results seeds or refreshes that baseline. Load when you need trajectory-level regression detection stronger than smoke tests.

  • Opp repl module image tests

    tabgab/opp_repl-skill/opp-repl-module-image-tests Skill

    no license0★ repo

    Detect visual regressions in OMNeT++ module rendering. capture_module_images renders one image per compound module from each filtered simulation (via Qtenv); run_module_image_tests compares fresh renders against a baseline using an RMSE metric. Distinct from chart tests (which compare analysis plots). Requires the httpx extra. Load when module display strings, icons, or layout must stay stable.

  • Opp repl sanitizer tests

    tabgab/opp_repl-skill/opp-repl-sanitizer-tests Skill

    no license0★ repo

    Run simulations built with AddressSanitizer / UBSan instrumentation to catch memory errors and undefined behavior. Uses the `sanitize` build mode. Load when hunting down flaky crashes, UAFs, leaks, or UB that normal release builds miss.

  • Opp repl smoke tests

    tabgab/opp_repl-skill/opp-repl-smoke-tests Skill

    no license0★ repo

    Run smoke tests with opp_repl — the cheapest regression check. run_smoke_tests() verifies that every (or filtered) simulation starts and terminates without crashing. Load this for baseline health checks before running heavier test suites (fingerprint, statistical, etc.).

  • Opp repl speed tests

    tabgab/opp_repl-skill/opp-repl-speed-tests Skill

    no license0★ repo

    Detect performance regressions by measuring CPU instruction counts with the `profile` build mode and comparing against a stored baseline in speed_store. run_speed_tests / update_speed_test_results use perf counters for deterministic measurement across noisy hardware. Load when you need to catch a change that makes the simulator slower.

  • Opp repl statistical tests

    tabgab/opp_repl-skill/opp-repl-statistical-tests Skill

    no license0★ repo

    Detect regressions in simulation SCALAR results by comparing against saved baselines. Complementary to fingerprint tests — coarser (numeric tolerances) but easier to interpret. update_statistical_test_results seeds or refreshes the baseline in the project's statistics_folder. Load when fingerprint churn is too noisy and you only care about headline metrics.

  • Grill docs

    wachawo/claude-skills/skills/grill-docs Skill

    0★ repo

    A "grilling" session that stress-tests your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) as decisions crystallize. Use when the user wants to stress-test a plan against the project's language and documented decisions.

  • Playwright interactive

    wachawo/claude-skills/skills/playwright-interactive Skill

    0★ repo

    Persistent browser and Electron interaction via `js_repl` for fast iterative UI debugging.

  • Playwright

    wachawo/claude-skills/skills/playwright Skill

    0★ repo

    Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, debugging user scenarios) via `playwright-cli` or the bundled wrapper script.

  • Tdd

    wachawo/claude-skills/skills/tdd Skill

    0★ repo

    Test-driven development with the red-green-refactor cycle. Use when the user wants to develop features or fix bugs via TDD, mentions "red-green-refactor", asks for integration tests, or requests a test-first approach.

  • Webapp testing

    wachawo/claude-skills/skills/webapp-testing Skill

    0★ repo

    Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and reviewing browser logs.

  • Aem unit integration testing

    prakash888kp/AEM-SKILLS/skills/tier-5-development/aem-unit-integration-testing Skill

    0★ repo

    A curated catalog of Adobe Experience Manager (AEM) skills organized into tiers, with dependency chains and contribution guidelines.

  • Tdd workflow

    ezos26/claude-skills/skills/tdd-workflow Skill

    0★ repo

    Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

  • Test generator

    kakarot-oncloud/claude-dev-skills/skills/test-generator Skill

    0★ repo

    Generates unit and integration tests for a function, class, or module — covering happy path, edge cases, error cases, and boundary conditions. Supports common frameworks (Jest, Vitest, Pytest, Go testing, JUnit, RSpec). Use this skill when the user asks to "write tests for this", "add test coverage", "what tests should I add", or pastes code that lacks tests.

  • Generate testing strategy

    eroveda/blueprint-skills/skills/generate-testing-strategy Skill

    0★ repo

    Generates TESTING_STRATEGY.md — a consolidated testing strategy document that aggregates the acceptance criteria from all executable specs into a global testing approach (unit, integration, E2E, load, security). Use this skill AFTER swebok-generate-spec has produced 03-SPECS.yaml (or the specs/ directory). ## When to invoke this skill - After all specs have been generated - When the user asks for a "testing strategy", "QA plan", "test plan", or "TESTING_STRATEGY.md" - When planning the testing phase of a project ## When NOT to invoke - Before specs exist - For projects without acceptance criteria defined

  • Payments testing

    Marcdaou/claude-qa-suite/qa-suite/skills/payments-testing Skill

    0★ repo

    Test Stripe payment flows in test mode using the Stripe API/MCP — the successful charge/checkout path that should create a booking, and the decline/failure paths (generic decline and 3DS/SCA-required) that the app must handle gracefully. Use this skill whenever the user wants to test payments, verify checkout, confirm a charge succeeds or a declined card is handled, or check Stripe integration before launch. Trigger on casual asks like "does paying actually work" or "test a declined card" too. Stripe TEST MODE only.

  • Test

    Mr-GraphnStaff/Skill-builder/skills/test Skill

    0★ repo

    we test shit

  • Skainet data dsl

    SKaiNET-developers/SKaiNET-coding-skills/skainet-consumer-skills/skills/skainet-data-dsl Skill

    0★ repo

    Use when constructing tensors, slicing them, or building transform pipelines using the SKaiNET public DSL — applies in both consumer apps and inside the SKaiNET repo. Trigger tokens include `tensor(`, `tensor {`, `data<`, `pipeline<`, `sliceView`, `segment {`, `rescale`, `normalize`, `unsqueeze` (in pipeline context), `FP32::class`, `FP16::class`, `Int8::class`, `Int32::class`, `Ternary::class`, `randn(`, `uniform(`. Do NOT fire on tensor *assertions* (in-repo tests go to the contributor `skainet-testing` skill) or on neural-network builders (`sequential` / `dag` go to `skainet-nn-dsl`).

  • Skainet testing

    SKaiNET-developers/SKaiNET-coding-skills/skainet-contributor-skills/skills/skainet-testing Skill

    0★ repo

    Use ONLY when writing or editing unit tests INSIDE the SKaiNET repository — tests under `SKaiNET/skainet-*/src/commonTest/`, `*/jvmTest/`, or `SKaiNET/skainet-test/skainet-test-java/`. Enforces the in-repo test policy: Kotest spec runner on JVM, `kotlin.test` in commonTest, `TensorAssertions.assertTensorClose` with explicit `ToleranceConfig.{STRICT/STANDARD/RELAXED/GRADIENT}`, Java JUnit 5 in `skainet-test-java`. Trigger tokens include `assertTensorClose`, `assertArrayClose`, `ToleranceConfig`, `GroundTruthTensor`. Do NOT fire on a CONSUMER project writing its own tests against SKaiNET as a dependency — those tests don't have access to `skainet-test-groundtruth` and can use any framework they like.

  • Test

    puukis/lstack/skills/test Skill

    0★ repo

    Writes tests only — reads source and existing tests first, never touches source files

  • Standards

    Endika/eskills/skills/standards Skill

    0★ repo

    Use when about to commit, write or design tests, name identifiers, write user-facing copy, choose an ID type, or push — enforces my non-negotiable conventions for commits, test design, repo hygiene, inclusive language, IDs, and pre-push checks.

  • Browser testing with devtools

    dills122/ai-central/templates/skills/imported/agent-skills/browser-testing-with-devtools Skill

    0★ repo

    Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

    The same file is in 2 other repositories

  • Test driven development

    dills122/ai-central/templates/skills/imported/agent-skills/test-driven-development Skill

    0★ repo

    Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

    The same file is in 7 other repositories

  • Qa test planner

    dills122/ai-central/templates/skills/imported/agent-toolkit/qa-test-planner Skill

    0★ repo

    Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

    The same file is in 7 other repositories

  • Vitest

    dills122/ai-central/templates/skills/imported/antfu-skills/vitest Skill

    0★ repo

    Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.

    The same file is in 2 other repositories

  • Vue testing best practices

    dills122/ai-central/templates/skills/imported/antfu-skills/vue-testing-best-practices Skill

    0★ 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

  • Review

    dills122/ai-central/templates/skills/imported/claude-skills/engineering-team/playwright-pro/skills/review Skill

    0★ repo

    Review Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".

    The same file is in 4 other repositories