测试
单元测试、集成测试与测试自动化
interface-design
Dammyjay93
This skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for marketing design (landing pages, marketing sites, campaigns).
ab-split-test-engineering
dmend3z
A comprehensive skill for A/B split test engineering, following Neil Patel's methodology. It covers test prioritization (ICE scoring), statistical significance, sample size, hypothesis formation, variable isolation, multivariate vs. A/B decisions, test documentation, and conversion lift calculation. Use this skill to optimize web pages, ads, and emails for higher conversion rates.
solana-dev
solana-foundation
End-to-end Solana development playbook (Jan 2026). Prefer Solana Foundation framework-kit (@solana/client + @solana/react-hooks) for React/Next.js UI. Prefer @solana/kit for all new client/RPC/transaction code. When legacy dependencies require web3.js, isolate it behind @solana/web3-compat (or @solana/web3.js as a true legacy fallback). Covers wallet-standard-first connection (incl. ConnectorKit), Anchor/Pinocchio programs, Codama-based client generation, LiteSVM/Mollusk/Surfpool testing, and security checklists.
debug
udecode
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
creating-openlineage-extractors
astronomer
Create custom OpenLineage extractors for Airflow operators. Use when the user needs lineage from unsupported or third-party operators, wants column-level lineage, or needs complex extraction logic beyond what inlets/outlets provide.
review-pr
alpinejs
Review an open PR like a maintainer — checkout, fix issues, push changes, post a structured verdict comment. You just merge or close.
e2e-testing
cosmix
End-to-end testing patterns and best practices for web applications using Playwright, Cypress, Selenium, and Puppeteer. Covers Page Object Model, test fixtures, selector strategies, async handling, visual regression testing, and flaky test prevention. Includes QA expertise for acceptance testing, smoke testing, cross-browser testing, and test reliability. Use when setting up E2E tests, debugging test failures, improving test reliability, or implementing browser automation. Trigger keywords: e2e, e2e testing, end-to-end, end-to-end tests, Playwright, Cypress, Selenium, Puppeteer, Page Object Model, page object, test fixtures, selectors, locator, locators, data-testid, async tests, visual regression, visual testing, screenshot, flaky tests, flakiness, browser testing, browser automation, UI test, UI testing, acceptance test, acceptance testing, smoke test, smoke testing, integration test, wait, waits, assertion, assertions, test data, test isolation.
debugging
cosmix
Systematically diagnoses and resolves software bugs, test failures, data quality issues, and performance problems using various debugging techniques and tools. Trigger keywords: debug, bug, error, exception, crash, issue, troubleshoot, fix, stack trace, diagnosis, diagnose, investigate, root cause, why, failing, broken, not working, unexpected, flaky, intermittent, regression, performance degradation.
fluxcd
cosmix
GitOps continuous delivery toolkit for Kubernetes with Flux CD. Use when implementing GitOps workflows, declarative deployments, Helm chart automation, Kustomize overlays, image update automation, multi-tenancy, or Git-based continuous delivery. Triggers: flux, fluxcd, gitops, kustomization, helmrelease, gitrepository, helmrepository, imagerepository, imagepolicy, image automation, source controller, continuous delivery, kubernetes deployment automation, helm automation, kustomize automation, git sync, declarative deployment.
xcsift
ldomaradzki
Use xcsift for Swift and Xcode build output. Activate when running swift build, swift test, or xcodebuild commands. Pipe output through xcsift for structured TOON format optimized for LLM consumption.
pyproject-toml
vamseeachanta
Configure Python projects with pyproject.toml for modern packaging, tools, and dependency management
interview-me
mycelium-hq
Use when an ask is underspecified ("build me X" without who it's for, why now, or what success looks like), when a request is conventional rather than specific ("a dashboard", "make it faster" with no number), when Claude catches itself silently filling in ambiguous requirements before any plan, spec, or code exists, or when the user says "interview me", "grill me", "are we sure?", or "stress-test my thinking". Needs a live user; not for CI, scheduled runs, or autonomous loops.
istio
cosmix
Service mesh implementation with Istio for microservices traffic management, security, and observability. Use when implementing service mesh, mTLS, traffic routing, load balancing, circuit breakers, retries, timeouts, canary deployments, A/B testing, or service-to-service communication. Triggers: istio, service mesh, envoy, sidecar, virtualservice, destinationrule, gateway, mtls, peerauthentication, authorizationpolicy, serviceentry, traffic management, traffic splitting, canary, blue-green, circuit breaker, retry, timeout, load balancing, ingress, egress, observability, tracing, telemetry.
doubt-driven-development
mycelium-hq
'Use when correctness matters more than speed: about to commit non-trivial code, make an architectural call under uncertainty, work in unfamiliar code, or assert what the compiler cannot check (''this is safe'', ''thread-safe'', ''this scales'', ''matches the spec''). Strongest on high-stakes surfaces (production deploys, security-sensitive logic, data migrations, irreversible operations) and when the user asks to sanity-check, red-team, double-check, or get a second opinion on a decision.'
backend-tester
olehsvyrydov
Senior QA Engineer with 10+ years Java testing experience. Use when writing unit tests with JUnit, creating integration tests with Testcontainers, implementing API tests, following TDD methodology, or testing reactive code with StepVerifier.
test-driven-development
lv416e
"Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first 機能やバグ修正を実装する際、実装コードを書く前に使用 - まずテストを書き、失敗を確認し、最小限のコードで通す。最初に失敗を求めることで、テストが実際に動作を検証することを保証"
add-package
remix-run
Create or align a package in the Remix monorepo to match existing package conventions. Use when adding a brand new package under packages/, or when fixing an existing package's structure, test setup, TypeScript/build config, code style, and README layout to match the rest of Remix 3.
nx-run-tasks
nrwl
Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.
nx-run-tasks
nrwl
Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.
nx-generate
nrwl
Generate code using nx generators. INVOKE IMMEDIATELY when user mentions scaffolding, setup, structure, creating apps/libs, or setting up project structure. Trigger words - scaffold, setup, create a ... app, create a ... lib, project structure, generate, add a new project. ALWAYS use this BEFORE calling nx_docs or exploring - this skill handles discovery internally.
kaizen:plan-do-check-act
NeoLabHQ
Iterative PDCA cycle for systematic experimentation and continuous improvement
cuda-kernels
huggingface
"Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations."
customaize-agent:test-prompt
NeoLabHQ
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
customaize-agent:agent-evaluation
NeoLabHQ
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.