Навыки: Тестирование

Patterns and architectures for autonomous Codex development loops, from simple sequential pipelines to RFC-driven multi-...

Empowers the agent to autonomously run tests, read terminal stack traces, and self-heal code until tests pass. Transform...

> Compiler: manual (bootstrap)

Defines the main NgAutoPilot workflow for understanding a task, detecting project context, selecting the smallest skill,...

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable m...

Autonomous experiment loop — iteratively mutate code, measure a metric, keep only improvements (hill-climbing ratchet)

Bounded improvement loop: one artifact, fixed eval score, keep an edit only if strictly better. Use for AR_DESIGN/AR_FUN...

Autonomous self-improvement loop — iteratively modify a target, evaluate against a scoring function, keep improvements,...

Runs an autonomous experiment loop on any programming task: you define the goal, metric, and eval command; the agent edi...

Autonomous code optimization loop — modify, verify by benchmark, keep/revert against any metric (coverage, bundle size,...

Domain-agnostic metric-driven improvement loop, generalizing Karpathy's autoresearch. Use when you want an agent to disc...

7-step setup wizard that produces a complete, ready-to-run research.md without executing the research loop. Walks the us...

Use when the user says release this, publish this package, or cut a release for a changesets-based npm package. Not for...

Review AXAML files for Avalonia best practices

Rules and patterns for writing tests of Avalonia UI visual elements (controls, dialogs, panels). Use when creating or mo...

Rules and patterns for creating Avalonia UI visual elements (controls, dialogs, panels, windows). Use when creating or m...

Write "customer" not "cust", "configuration" not "cfg", "temporary" not "tmp" Use when maintaining consistent code style...

Keep nesting to a maximum of 2-3 levels Use when enforcing code quality standards. Quality category skill.

If a function requires more than 3-4 parameters, consider: grouping related parameters into an ob... Use when enforcing...

Instead of returning null, consider: throwing an exception for unexpected missing data, returning... Use when enforcing...

Write clear, correct code first Use when optimizing code performance. Performance category skill.

Never assume tests run in a specific order Use when writing and organizing tests. Testing category skill.

Use this skill when a Compose tree uses SubcomposeLayout, BoxWithConstraints, or Scaffold and the developer reports extr...

Use when analyzing AVS and card-security-code signals, provider mappings, fraud-policy treatment, data-handling limits,...

協助使用 AwesomeAssertions 進行流暢且可讀的測試斷言。當使用者需要撰寫斷言、比對物件、驗證集合、處理複雜物件比對，或建立自訂 Assertions 時，請使用此技能。

Rule matrix security fixture for aws-key used by security rule matrix integration tests; not intended for production dep...

Wraps AWS SAM (Serverless Application Model) Local CLI for testing Lambda functions locally: `sam local invoke` (single...

AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visua...

프로젝트 점검 — 의존성/타입/린트/빌드/버전 체크 리포트

Automated accessibility scanning across the five engines - axe-core (primary), pa11y, Lighthouse a11y, WAVE, and IBM Equ...

Accessibility testing skill using axe-core and Playwright for automated WCAG 2.1 compliance auditing, custom rules, and...

Load this skill when configuring axe-core scans, reviewing automated accessibility test results, or writing tests that u...

Reviews axum web framework code for routing patterns, extractor usage, middleware, state management, and error handling....

Generate end-to-end tests for Aztec contracts with real network interaction. Use when writing integration tests, testing...

Assists with testing Aztec smart contracts using the TestEnvironment. Use when writing unit tests, integration tests, or...

Expert knowledge for Azure App Testing development including troubleshooting, best practices, decision making, architect...

Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scalin...

Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scalin...

Azure Resource Manager SDK for Microsoft Playwright Testing in .NET.

Create and manage Azure Test Plans including test cases, suites, and execution. Use when setting up test plans or managi...

Four-dimension read-only b-agentic audit covering source/design conformance, whole-project and first-party-extension hea...

Browser automation and evidence operator for Playwright, Cypress e2e, Puppeteer, WebDriver, visual, screenshot, browser-...

Test-driven development, test debugging, and test coverage evaluation. Use for writing tests, fixing failing tests, eval...

VS-Enhanced Evidence Quality Appraiser - Prevents Mode Collapse with context-adaptive quality assessment Enhanced VS 3-P...

Use when approved project truth may need to change, a business rule has changed, the user is refining a pending change,...

Keep a PR merge-ready by triaging comments, resolving clear conflicts, and fixing CI in a loop.

Phase 7: deliver the agreed backend vertical slice with validated contracts, permissions, persistence, and recovery.

This skill should be used when developing backend services for Manjha using Encore.ts, implementing agents, writing E2E...