Testing Qa AI Skills

Analyze assertion quality, depth, variety, and false confidence in existing tests. ALWAYS USE when asked about weak, shallow, trivial, always-true, self-referential, assertion-free,…

QuantMind 平台运营操作技能 — 覆盖模型训练、模型管理、后台数据更新、字段信息查询、RSS 新闻对接与分析。在 QuantBot / Claude Code 中处理模型训练、数据同步、新闻分析等任务时使用。触发词：模型管理、数据更新、字段信息、RSS、新闻分析、查看数据、同步数据

AI DevKit · Testing phase guidance for adding and validating feature test coverage. Use when the user wants to write tests, update testing docs, run coverage, close coverage gaps, or run dev-lifecycle…

Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests,…

Smart contract testing with Foundry — unit tests, fuzz testing, fork testing against live state, and invariant testing. What to test, what to skip, and what LLMs commonly get wrong.

SaaS pricing design and optimization covering value metric selection, tier architecture, price point research, pricing page design, price increase execution, and competitive pricing analysis.

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe…

Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and tournament…

Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning.

Score a claim against the evidence behind it. Use this skill whenever the user wants to know whether something is actually supported — "is that true", "what's the source", "that sounds made up", "can…

UI checks in the 1C thin client through QA MCP (`1c-qa`, `qa_*` / `ui_*`): session, observe → act → assert, platform behaviour, unknown outcomes, journal and verdicts. Main UI route when connected and…

Use when you want to prevent coverage regressions during development. Activate with /coverage-guard to warn when coverage drops below threshold after code changes.

Internal helper: cross-page patterns, severity scoring, scorecards.

Enforce evidence bar, coverage gates, and regression guards. Use when adding tests or claiming done. Do not use to run suites; use night-market-operations.

Automatically generates executable tests that reproduce reported bugs from issue reports and code repositories. Use when users need to: (1) Create a test that reproduces a bug described in an issue…

Format CVs for academic positions with publications, grants, and teaching

大项目模块间联动回归——一份 REGRESSION.md 回归台账登记"每个模块的下游消费者 + 可执行的回归验收命令"，每次改动后照台账跑回归审计，防"改一个模块悄悄弄坏其他模块"。判决靠退出码，不靠 AI 看着没问题。中文触发：模块回归、回归台账、回归审计、改A坏B、模块联动检查、影响面检查、模块牵连、下游验证、大项目改动检查。English triggers: module…

Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.

Build Cypress test suites in TypeScript: E2E tests, component tests, custom commands, cy.intercept network control, cy.session login, Cypress Cloud, and CI integration. Covers retry-ability, the…

Manages testing lifecycle including unit tests, integration tests, validation, and quality assurance.

Frontend-implementation dedicated review framework. Called by FrontendReviewer to professionally analyze FrontendDev's output (UI/API-contract fit/component quality/unit-test sufficiency/acceptance…

Test-driven development workflow with test generation, coverage analysis, and multi-framework support

When the user wants to know what queries drive traffic to their site, which pages are indexed, click-through rates, organic search performance, or technical indexing issues. Trigger on "Search…

개발 완료 후 브라우저 자동화가 필요 없는 API/CLI 레벨 E2E 테스트 작성 및 실행. /verify 이후 실제 사용자 플로우를 검증합니다. 브라우저 자동화가 필요하면 e2e-agent-browser 스킬 사용. Triggers on: e2e 검증, e2e-verify, E2E 테스트. NOT for: 유닛 테스트, 타입체크, 빌드 검증, 브라우저…

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

Use when the user wants to interact with Hacker News (news.ycombinator.com) — read top stories from the frontpage, extract a post's data and comments, or search stories via the Algolia HN search API.…

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive…

Review TypeScript and Node code. Use for SvelteKit types, tsconfig, ESM, Zod boundaries, testing, or npm package builds. Read README.md for the guide map.

Audit pages and user journeys against a declared WCAG scope. Use when identifying keyboard, screen-reader, focus or contrast barriers and planning verified remediation.

Use when adversarial brainstorming is needed after reconnaissance — the Proposer, Devils-Advocate, and Synthesizer each run ONE pass (no rounds); the Don is grilled on the IDEA first, one question at…

Use to review a dispatch before handoff, requirements and plans before implementation, or code after implementation. Runs a fresh reviewer, then a separate context-aware adjudicator; returns…

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

Generate thorough, interactive HTML testing checklists — a real test plan organized into end-to-end flows, with pass/fail/blocked step states, a progress bar, filter and search, and copyable,…

Generates unit and regression test files for existing code. Creates "Happy Path", "Edge Case", and "Error" test stubs.

Design, optimize, and validate parallel execution across CPU threads/workers with measurable scaling evidence. Use when selecting parallelization strategy, diagnosing contention and load imbalance,…

Write and edit consulting analysis, recommendations, reports, decks, and client communications with direct language, proportional detail, and explicit evidence. Use to adapt a consulting deliverable…

基于真实生产应用程序的项目特定技能（Skill）模板示例。

Establish who the caller is — session cookies, bearer tokens, refresh, and OAuth/OIDC flows — and put each where it belongs. Use when adding or changing login, logout, signup, session handling, token…

Converts vision and market opportunity into traceable business models, product portfolios, and strategic plans. Use when defining business strategy, product direction, competitive positioning, or…

Monitor Android app stability and performance from the Play Developer Reporting API via gplay vitals. Use to query crash/ANR rates, detect release regressions with anomaly detection, filter error…

Use when a website needs rendered screenshot review, Playwright visual regression, multi-viewport checks, horizontal overflow detection, console-error checks, focus/state inspection, or a repeatable…

Design and build cinematic, award-level web pages.

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.

This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens",…

Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.

End-to-end feature testing — browser QA, API verification, eval tests, or any combination. Covers browser interactions (via agent-browser CLI), Google Workspace operations (gws CLI), API calls, and…

Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.

ALWAYS USE whenever asked to write, add, or generate unit tests for existing code in xUnit, MSTest, NUnit, pytest, Vitest/Jest, Go, or another framework, including "tests only for" one helper,…

Make minimal prompt edits to reduce false-positive refusals from Fable. Use only when the user explicitly invokes /fable-safe-prompt.