Навыки: Тестирование

Build a complete vertical slice for a new feature — Prisma model + API route + react-query hook + UI page + sidebar entr...

Add a second game to the monorepo (apps/<game>) from the seed game, wired to the gate. Load when asked to create a new g...

Use when adding global mode support for one existing agentsmesh target from a target-structure/global-path doc. Covers c...

Scaffold and write Aspire integration tests for NovaTune API endpoints

Use this when adding evaluation to an LLM/agent app - measuring output quality (correctness, faithfulness, relevance, sa...

Add a screen, tab or component to the Expo app (apps/mobile). Use when the user wants something new in the mobile app, o...

Adds a new application module to this Spring Modulith project with the package layout the ModuleBoundariesTests gate exp...

Builds and governs a buy-and-build programme -- consolidation thesis, target criteria, arbitrage arithmetic, integration...

Add unit tests to a Datagrok package

Add or extend a driven port and its adapter in agent-office's hexagonal core — storage/persistence, OS integration, cloc...

Use when posting validated code review findings as GitHub PR line-level comments or a GitHub PR review after completing...

为已有 PageObject 增量添加回归测试点。触发：新增测试点、添加回归点、add test point、增加覆盖、扩展页面方法。

Add unit tests for a component or function

This skill covers patterns for creating and managing test scorer endpoints. Trigger: Load this skill when working with t...

Add or update a logical hardware test stand in inventory/stands.yaml. Use when asked to create a stand, assign existing...

Add Selenium-based UI tests for NovaTune player and admin Vue SPAs against Aspire backend

Add focused Bun unit tests for mission-critical behavior and edge cases — not blanket coverage.

Write failing unit tests for feature requirements (TDD style)

Add a new quality tier or use-case tier that reuses an existing image model, covering QualityTier types, tier config, sc...

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge...

Address and implement review feedback on a pull request.

One-shot pass to address PR review comments: fetch threads, apply validated fixes, lint/test affected files, commit, pus...

Load this skill when acting on review feedback left on your change: verify each comment, fix what holds, push back with...

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to au...

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another age...

Detect and classify ADinsights API/data/integration contract risk for planning and review. Use when prompts or file chan...

Synthesize ADinsights release readiness from router, scope, contract, docs, and optional validation checks. Use when dec...

Evaluate ADinsights scope risk for AI coding sessions. Use when requests may span multiple top-level folders, require Ra...

Pattern of rule lists. Load when assembling or editing an admin list screen — the ready-made order of blocks, the <prefi...

Distribute reviewed work items to team members for testing

Fix PR review comments, simplify code, and self-review

Use when reviewing code changes for an Azure DevOps ticket. Fetches ticket context, finds the linked PR, and performs a...

Review a resolved ADO work item to verify the fix is complete and correct

Use when testing and verifying a bug fix or feature for an ADO ticket. Triggers on /ado-test, "test ticket", or requests...

Write Architecture Decision Records that capture context, options, decision, consequences, and follow-up.

Run a source-grounded paid-advertising audit for one or more of Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, Appl...

Ad Performance Auditor — analyze existing ad campaigns and identify optimization opportunities

Audit paid-ad copy, images, video, hooks, concepts, format coverage, platform-native fit, message match, creative fatigu...

Generate paid-ad image assets from a validated creative brief and brand profile using an explicitly configured image pro...

Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creat...

Meta Ads deep analysis covering Facebook and Instagram advertising. Evaluates 46 checks across Pixel/CAPI health, creati...

Monitor paid-ad account pacing, delivery, performance, creative fatigue, tracking, policy, and data quality across suppo...

Generate rights-cleared paid-ad product photography variants from an authorized source image and validated brand profile...

Use when performing thorough multi-phase code review with historical context tracking and verification. Triggers: 'thoro...

Audit one Ergopti driver adversarially with reproducible evidence, without implementing fixes. Use for robustness audits...

JP's signature red-team pass — "how would I break this?" Argue against your own approach before proceeding. Trigger on a...

Exploratory, adversarial QA: exercise a feature through whichever surface(s) it exposes — UI, API, or both — and surface...

Decide whether an article deserves publication through hard checks and skeptical comparison.