Навыки: Тестирование

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for...

GraphQL API app (apps/graphql): Strawberry schema, query modules, services, SQLAlchemy and Alembic, reports/transform in...

Use when safely merge GitHub pull requests that are ready

Land a feature branch on main. Use when asked how to merge or finish a branch; not for syncing a branch with main.

Use when creating, rewriting, OR reviewing a GitLab Merge Request in the Gramax product repo (`gramax/` → `gitlab.ics-it...

Automatically validate mermaid diagrams after creating or editing them in markdown files

Review MERN code for compliance with standards, NFRs, and security policy.

Manage Playwright E2E tests for critical user journeys.

Non-functional requirements checklist for MERN features

Run MERN unit tests, report results, and optionally fix failures.

Manage Meta Ads (Facebook + Instagram) — performance, ROAS, CPM, frequency, audience overlap, learning phase, creative f...

Diagnose Meta Ads campaign performance and account gaps using Meta's actual system mechanics — including customer-journe...

30-day comprehensive Meta Ads health audit. Checks pixel/CAPI integrity, scans creative fatigue across the account, prof...

Read before any Meta audit, pause, scale or optimization-event change on a sales campaign that optimizes for COMPLETE_RE...

CLI code review patterns. Use when reviewing CLI applications built with Commander.js, @clack/prompts, picocolors. Cover...

Code review patterns, feedback principles. Use when reviewing PRs, implementations, or making approval/rejection decisio...

Run a structured, repeatable audit for a live website and produce actionable artifacts.

Валидация объекта метаданных 1С. Используй после создания или модификации объекта конфигурации для проверки корректности

Metabolomics-specific analysis strategies and domain knowledge

METAINFORMANT rules for directory config/quality. Use when editing, adding tests, or reviewing code under this path. Rea...

METAINFORMANT rules for directory docs/quality. Use when editing, adding tests, or reviewing code under this path. Read...

METAINFORMANT rules for directory examples/quality. Use when editing, adding tests, or reviewing code under this path. R...

METAINFORMANT rules for directory scripts/quality. Use when editing, adding tests, or reviewing code under this path. Re...

METAINFORMANT rules for directory scripts/validate. Use when editing, adding tests, or reviewing code under this path. R...

Toph's metalbending for a strict code quality review. Everyone said metal could not be bent, until Toph felt the specks...

🧪 Orchestrateur Audit & QA Test — route vers les skills de vérification qualité, tests API, audit de données et tests E...

Write reviewed KPI and metric narratives from supplied data, definitions, and assumptions. Use when Codex is asked to ex...

Collect and analyze on-device performance metrics and crash diagnostics using MetricKit. Use when setting up MXMetricMan...

System metrics, telemetry, and performance monitoring

Use this skill whenever asked to prepare, review, or classify transactions for a Mexico IVA (Impuesto al Valor Agregado)...

Enterprise middleware testing patterns for message routing, transformation, DLQ, protocol mediation, ESB error handling,...

Migrate from Cypress or Selenium to Playwright. Use when user mentions "cypress", "selenium", "migrate tests", "convert...

Migrate an MSTest v3 test project to MSTest v4 (latest). Use when user says "upgrade to MSTest v4", "migrate to MSTest v...

Migrates Cypress, Selenium, WebdriverIO, or Protractor suites to Playwright in staged slices, each with a parity gate be...

Step-by-step migration guides for moving to Playwright from Cypress or Selenium/WebDriver — command mappings, architectu...

Keep docs/migration/TRACEABILITY.md (the Flutter→React Native master matrix) accurate and check it against the code with...

Knowledge base from MIL-HDBK-338B (Electronic Reliability Design Handbook). Use for electronic reliability engineering:...

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training larg...

Iterative review-fix loop for accumulated milestone/branch changes. Runs parallel reviewers, fixes findings autonomously...

从自然语言制作 Minecraft 黑洞、白洞双极喷流与外扩光壳、旋转盘面、螺旋粒子与可调渐变光晕，含原创 GLSL、黑洞工作台和 Forge 1.20.1 世界透镜及物品示例。用于近距离天体主体、盘面、粒子与背景畸变；不替代普通星空或科学...

保留 Minecraft 原世界几何与位置，在球形、路径或其他世界空间区域内替换环境表面材质，制作扩散、侵蚀、收缩与边缘效果。处理深度位置重建、对象筛选、区域叠加、透明层、生命周期及 Forge 1.20.1 接入；不用于跨维度门户、单纯全...

将 Unity Stylised Energy Shield Shader Graph 转换为 Minecraft Forge 1.20.1 的客户端护盾网格特效，附带共享 recipe.json、可自定义 HTML 工作台、六边形/扫描线...

Use when the agent needs recursive reasoning, episodic memory retrieval, internet learning, or world-model prediction. M...

Test and debug the Dashboard “Edit with AI” mini-app editor flow (start edit session, build, history, close session) and...

MinIO high-performance S3-compatible object storage: erasure coding, mc client, KES encryption, site replication, ILM, I...

Write, review, and improve Minitest tests for Ruby on Rails applications. Covers model tests, controller tests, system t...

QA 시나리오 수집·현장 생성 → Playwright 코드 생성 → 실행·수정 반복을 수행한다. /minos, 미노스, /qpassenger, 큐패신저, QA 통과할 때까지, 테스트 통과까지, playwright t...

Onboard a consumer web app to mirroir's .mirroir/ dotfile by EXPLORING the running app (chrome-devtools-mcp) — derive re...