Testing
quality-playbook
Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol with regression test…
Testing
skills-lint
Validate Agent Skills against Anthropic open standard specifications, checking YAML frontmatter, file naming, description quality, version consistency, and content constraints. Use…
Testing
write-lookahead-test
Generate rigorous look-ahead bias tests for any module that touches market data, features, or signals. Use this skill whenever the user adds or modifies code in data/feature_engine…
Testing
go
Opens the running app in a browser and verifies recent UI changes actually work. Use whenever the user wants a quick smoke test or sanity check of recent work, or says "go", "open …
Testing
react18-enzyme-to-rtl
Provides exact Enzyme → React Testing Library migration patterns for React 18 upgrades. Use this skill whenever Enzyme tests need to be rewritten - shallow, mount, wrapper.find(), …
Testing
moviemonk-ai
Full build and safety test workflow for MovieMonk UX/Component changes. Validates that UI modifications maintain type safety, component consistency, responsive behavior, and test c…
Testing
dual-agent-harness
Build or run a soulbis ⚔️ ⊥ soulbae 🧙 dual-agent harness — a proposer and a prover held apart by a Fiat-Shamir Gap, so no result survives that the proposer could have tuned to. Use…
Testing
pulser
Diagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (gotchas, description, allowed-tools, file-size, structure, frontmatter,…
Testing
browser-probe
Exploratory browser testing for real web apps. Use when the user wants a smoke test, scoped verification, exploratory QA, or a balanced read on what works, what feels off, and what…
Testing
qa
QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a si…
Testing
flake-axis-bisection
Isolates the trigger behind a known-flaky test by varying one axis at a time—order, isolation, workers, viewport, latency, repetition—while tracking pass/fail counts and checking w…
Testing
test-playwright
Drive a live localhost app through browser automation like a real user, exercising every page, flow, and component touched in the session. Hunt for issues across UI, backend, and D…
Testing
qa-pr
Runs an agent-driven QA pass on a PR preview URL using the kmikeym v0.01m SOP: cold sign-up, first prompt, in-app exploration, edit/theme change, publish, live URL test, and remix.…
Testing
jcb-skill-flowRecorder
Use when you need to record a website's menu navigation flow, capture screenshots, save rendered HTML, download page resources, and summarize network/API calls during a semi-automa…
Testing
case
Import a TypR bug into cases/ and drive it from repro to fix. Use when the user hits a bug in a TypR project and wants it turned into a reproducible case (from a `typr case snapsho…
Testing
monitor-test-run
Monitors Kobiton test executions in real time: polls until all runs reach a terminal state, surfaces live-remediation URLs on blockers, and delivers accurate post-mortems that dist…
Testing
block-testing
Automated testing guidance for custom AEM Edge Delivery Services blocks. Analyzes block JavaScript and CSS for common issues including missing null checks, unscoped CSS selectors, …
Testing
catalog-audit
Validate product data integration between Adobe Commerce and an AEM Edge Delivery Services storefront. Checks Catalog Service API connectivity, product data rendering accuracy, pri…
Testing
debugging-code
Interactively debug source code by setting breakpoints, stepping through execution line by line, inspecting live variable state, evaluating expressions, and navigating the call sta…
Testing
qa-agent
Autonomous QA agent using playwright-cli. Reads the codebase, explores a running local app, attempts to reproduce a bug described in plain language, then creates a structured GitHu…
Testing
check-subagent
Audits custom subagent definitions against deterministic checks for location, frontmatter, naming, tools, prompt size, and structure, plus judgment dimensions covering scope, routi…
Testing
sap-sac-test-automation
Designs capability-gated browser discovery and deterministic Playwright test suites for SAP Analytics Cloud stories, dashboards, planning workflows, comments, permissions, and visu…
Testing
test-convert
Gera testes robustos e comportamentais para o Convert (React + Redux + Axios) seguindo BDD e as diretrizes do knowledge base. Analisa componentes, serviços, validações e cálculos e…
Testing
audit-accessibility
Automated WCAG 2.2 accessibility audit that crawls every page, runs axe-core checks, validates keyboard navigation, color contrast, ARIA labels, heading hierarchy, form labels, and…
Testing
loop-evals
Designs the evaluation harness for agent loops, establishing trustworthy verification through a 7-layer suite with false-completion-rate and repair-productivity as core metrics. En…
Testing
playwright-e2e-builder
Plans and builds comprehensive Playwright E2E test suites using Page Object Model, authentication state persistence, custom fixtures, visual regression, and CI integration. Conduct…
Testing
forge-qa-warfare-v2
Delivers exhaustive actor-based QA coverage for FitnessMealPlanner across all roles, endpoints, states, inputs, and assertions. Executes a 9-phase pipeline integrating six speciali…
Testing
chaos-tdd-fault-injection
Design deterministic fault-injection tests that declare guarded behavior first, then implement minimal guards at protocol seams for LLM and external I/O failures. Use to harden pip…
Testing
playwright-e2e-execution-run
Executes an existing Playwright end-to-end suite against a confirmed non-production target and returns a structured run report including pass/fail counts, flaky tests, durations, a…
Testing
shape-test-plan
Orchestrates stateful phased test rollouts for existing products by writing a durable plan at context/foundation/test-plan.md then sequencing through research, planning, and implem…
Testing
schoolos-migration-guard
Checks Django 5.2 + PostgreSQL 16 migrations for unsafe operations on live data: exclusive locks, data loss, backward-incompatible changes, NOT NULL without defaults, irreversible …
Testing
agenttrace
Local-first TUI/CLI for post-run agent session audits — cost/token spikes, tool failures, retry loops, latency gaps, health scores, anomalies, session-to-session diffs. No upload, …
Testing
organizing-test-source-sets
Organizes Android test source sets including src/test/, src/androidTest/, sharedTest conventions, and KMP-style splits. Covers testImplementation, androidTestImplementation, and de…
Testing
unit-test-bean-validation
Provides patterns for unit testing Jakarta Bean Validation (JSR-380) constraints including @Valid, @NotNull, @Min, @Max, and @Email with Hibernate Validator. Generates custom valid…
Testing
antigravity-native-e2e-dev
Launch and exercise the native Antigravity (agy) TUI harness end-to-end with a live local Omnigent server, driving CLI turns through the web UI for smoke tests and debugging. Load …
Testing
pev-test-design
Analyzes Acceptance Criteria using six classical QA techniques: equivalence partitioning, boundary value analysis, decision tables, state transitions, error guessing, and checklist…
Testing
pre-generation-check
Validates all pre-generation gates before sending tracks to Suno. Checks sources verified, lyrics reviewed, pronunciation resolved, explicit flag set, style prompt complete, and ar…
Testing
designing-distributed-system-tests
Designs claim-driven test plans for distributed or stateful systems involving persistence, replication, consensus, or partial failure. Investigates product guarantees then creates …
Testing
qa-testing-routing
Routes QA and testing tasks across visual QA, certification, performance, API, accessibility, tools, and workflow optimization. Handles evidence-based bug reporting with screenshot…
Testing
os-eval-runner
Stateless evaluation engine that scores and gates skill improvement iterations using headless Python scripts. Use for "evaluate this skill", "run autoresearch loop", "optimize this…
Testing
qa-tester
Ensures 100% scenario coverage for any project feature. Builds a mandatory scenario matrix before writing tests, covering success paths, errors, missing fields, partial combination…
Testing
grpc-mock
Provides in-memory gRPC server mocking for client tests across languages: Go bufconn + mockgen, Python pytest-grpc with stub patching, JVM in-process servers, and Node fake servers…
Testing
police
Triple Gate quality enforcement system. Triggers on non-trivial builds. Runs three self-drafts plus six specialized validators across four phases with task isolation, compaction sa…
Testing
forge-clarify
Clarify and validate issues before planning. Reproduces bugs via browser, verifies UX expectations, and captures evidence screenshots. Moves issues from confirmed to clarified stat…
Testing
kafka-shadowtraffic-java
Generates a Java TestContainers test class that runs ShadowTraffic in-process to populate Kafka topics with synthetic data. Builds the ShadowTraffic config, adapts it for container…
Testing
unit-test-service-layer
Provides patterns for unit testing service layers with Mockito. Creates isolated tests that mock repository calls, verify method invocations, test exception scenarios, and stub ext…
Testing
ontology-validator
Validate material sample annotations against ontology constraints by checking class and property existence, verifying domain and range consistency for object properties, assessing …
Testing
qa-docs
Generates SIAE-compliant Master Test Plan (.docx) and Product Risk Analysis (.xlsx) via a 6-phase interactive workflow. Accepts scope from JIRA, chat or docs; analyzes requirements…
Testing
aoa-eval
Routes evaluation work by surfacing session readiness packets, checking local and central eval surfaces, then selecting apply, local intake, design, or mining paths while respectin…
Testing
persona-test
Exploratory browser testing driven by user personas. Uses a Plan-Act-Reflect loop with screenshots to identify UX and functional issues, then outputs structured P0-P3 reports plus …
Testing
rspec-testing-pyramid
Provides RSpec testing guidance for Ruby on Rails following a pyramid strategy—model and request specs over system specs. Includes FactoryBot patterns, shared examples, VCR for HTT…
Testing
accessibility-test
Automated WCAG 2.1 AA accessibility testing with axe-core and Lighthouse CI. Auto-detects frameworks, discovers routes, installs Playwright for page scanning and jest-axe for compo…
Testing
regle-advanced
Advanced Regle form validation: collection rules with $each, async/$pending handling, server/externalErrors, $reset options, global config via defineRegleConfig, discriminated unio…
Testing
auditing-compose-performance
Runs an end-to-end Jetpack Compose performance audit for broad symptoms like sluggishness or rough scrolling. Sequences Measure → Diagnose → Fix → Verify phases across 25 focused s…
Testing
quality-peer-review-niche
Peer-reviews new work on niche or feature branches against the matching general baseline, detects backend and shared-library leaks to origin/general, cherry-picks clean backend com…
Testing
midnight-verify:verify-wallet-sdk
Determines wallet SDK claim type and routes verification: pre-flight type checks, source investigation, or devnet E2E fallback. Handles @midnight-ntwrk/wallet-sdk claims, WalletFac…
Testing
post-review-pickup
Authoritative protocol for next-lane pickup after any PR-lifecycle boundary and for pre-review intake discovery from fresh boot or watchdog wake. Requires the next lane, a review-f…
Testing
shadow-mode-runner
Coordinates SHADOW mode operation where the agent runs parallel to human input without delivering output or incurring billing. Measures agreement rates and generates promotion repo…
Testing
qa-vendor-evaluator
Produces side-by-side commercial QA vendor matrices comparing test-management, no-code automation, visual regression, and AI copilot tools across capability, cost, integration dept…
Testing
shape-tdd
Executes approved plans phase-by-phase using TDD (red→green→refactor) only on unimplemented phases. Reads plan.md and Progress, writes failing tests first, implements minimal passi…
Showing the top 60 of 6,049. See the full list →