Каталог навыков агентов

Exercise the delivered customer journey using real runtime or browser evidence. Use for functional acceptance testing af...

Reproduce a pull request locally and collect merge-decision evidence. Use when asked to QA a PR; applies no fixes.

Automated QA agent that starts the app, walks through every screen and API endpoint, verifies functionality, evaluates m...

Ejecutar la puerta de calidad en modo fast o full e interpretar el resultado; no para escribir tests (test-write) ni pro...

Systematically QA test a web application with browser-based bug fixing. Four modes: diff-aware (automatic on feature bra...

Systematically QA test a web application. Use when asked to "qa", "QA", "test this site", "find bugs", "dogfood", or rev...

QA subagent — writes tests, reviews test coverage, and files bugs for missing or failing tests

Run QA validation on a pull request — boots the local environment, tests acceptance criteria, and optionally posts the r...

系统化 QA 测试并修复发现的问题。先测试，再按 bug 逐个修、逐个重新验证， 并为每个修复补回归测试。 (gstack)

Meticulous QA subagent for test planning, bug hunting, edge-case analysis, and implementation verification.

QA workflow for software projects. Use for tasks like writing test plans, deriving test cases from PRDs, risk-based test...

Turn Claude Code into an autonomous QA agent — an explore, generate, run, heal, report loop that maps the app, writes te...

Pre-ship audit checklist for Ethereum dApps. Ship-blocking checks and should-fix checks covering wallet connection, butt...

Hands-on QA testing of running applications via browser automation. Use whenever the user asks to test a running app, pe...

Especialista em testes E2E e auditoria de interface para Electron e Next.js usando Playwright, Vitest e Chrome DevTools.

The complete QA skill for Claude Code — turn Claude into an expert QA engineer that picks the right test type, writes re...

Automated geometry repair using RasFixit and quality validation using RasCheck. Handles blocked obstructions, generates...

Launch four independent AI code reviewers (Opus, Gemini, Codex, Kimi K2.5) to QA/QC code or notebooks. Each reviewer wri...

Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states...

Evaluate pipeline runs against ACCEPTANCE_MATRIX.md. Use after feature releases to verify acceptance criteria.

The analyst that watches your other analysts. It reads the trail your reports and workflows leave behind, then surfaces...

Builds QA harnesses for LLM agents. Use when evaluating tool, trace, red-team, regression, multi-agent, or carried-works...

Analyze a GitHub pull request for risk level and generate concrete QA recommendations. Accepts a PR URL or "owner/repo#n...

QA Analyst Agent. 성능 분석, 부하 테스트, 품질 메트릭 분석을 담당합니다. 성능, 부하(load), 분석, 메트릭 관련 요청 시 사용됩니다.

Autonomous API testing with hurl (declarative HTTP), xh (fast calls), k6 (load), grpcurl (gRPC). Use for REST contracts,...

API interface testing and automation. Send HTTP requests, validate responses, chain API calls, generate test scripts (Py...

API testing and contract validation across REST (OpenAPI 3.1), GraphQL (SDL), and gRPC (proto). Use when you need schema...

Argus QA readiness wizard; safe alias for qa-ready that avoids old qa-agent command collisions

Argus QA first-run setup wizard; configures MCP, app settings, and Azure DevOps credentials

Run a combined assessment of test strategy, CI coverage, and commit hooks, then consolidate actionable findings.

QA 审计 — 跑全量文档质量检查,按 P0/P1/P2 严重度分级输出审计报告。设计完成、代码交接前调用本 skill,作为进入实施的最后一道硬门控,确保 P0=0 才放行。

Quality auditor for Source Library. Prioritizes verifying original language texts (not modern translations), auditing me...

App-specific QA audit skill for the Claude Code Cloud web app. Contains flow map, test cases, known issues, and mobile-s...

COMPREHENSIVE UI/UX audit combining code analysis AND visual screenshot analysis. Detects design system violations, visu...

Writing and running automated tests: unit and integration design, fixtures, mocks vs real dependencies, coverage, flake...

Write E2E tests using Playwright with Cucumber/Gherkin for this project. Use when creating tests, writing test cases, te...

Use this skill for test strategy, E2E automation, visual regression, flaky test control, QA evidence. Trigger when the t...

当需要制定测试策略、发布前质量检查、Bug 分析和分类、质量风险评估时使用。James Bach 思维模型。

Executes behavioral API tests by spinning up the service and making real HTTP requests. Validates status codes, response...

Autonomous browser testing with playwright-cli (token-efficient CLI) and Playwright MCP. Use for E2E tests, browser auto...

E2E test creation and execution for QA. Validates implementations using Playwright API tests that become persistent arti...

Record a reproducible defect, independent triage, immutable attempts, and evidence-backed retest state.

Deduplicates issues.jsonl and files Azure DevOps Bug work items with annotated screenshots attached

Write a bug report a developer can reproduce and fix without asking a single follow-up question.

Parallel cell-execution subagent. Receives a chunk of audit cells, opens its own browser tab, runs them sequentially wit...

Understand and suggest QA test cases based on code changes

PR作成前の品質保証チェックを実行します。Lint、テスト、ビルド、カバレッジ確認を自動で行い、合格/不合格を判定します。フロントエンドのみ、バックエンドのみ、または両方のチェックが可能です。

QAチェックリストに対して現在のコードの修正状況を自動検証し、レポートを出力する

Formal Quality Assurance Checklist before every Merge/Deploy. 6-phase validation with Build Verification, Test Suite, No...

Generate a QA checklist from the current branch's change and write it into the current PR's body as a `## QA Checklist`...

Run comprehensive quality verification including build, types, lint, tests, and security scans.

Code quality review before validation. Checks for @ts-ignore, any types, anti-patterns, and potential issues. Use proact...

Verify implementation against QA Contract (G#N, AC#N), auto-invoke debug on RED

Validates API contracts by discovering consumers and ensuring responses match their expectations. Detects breaking chang...

actor: qa | mandate: Validate API/event contracts | bounds: No performance testing

Specialist QA subagent for test coverage analysis. Use when: identifying untested code paths, checking whether spec acce...

Reads issues.jsonl after the audit, writes coverage-report.json, and prints a terminal summary. Does NOT write a markdow...

Review test suites for coverage gaps, flaky tests, assertion quality, and real-world failure detection.

Generate focused QA test plans (300 lines max) for customer CSS deployments

Whole-app QA loop run by an orchestrator — map every feature, plan small test units, fan out one tester agent per unit,...

QA + bugfix cycle until it passes

Build and visualize QA dashboards and reports with Allure Report, Grafana, and ReportPortal. Covers test execution visua...

Generate and manage Q&A database for Topical Authority content. Use when user wants to create structured answers for clu...

Systematic debugging methodologies, troubleshooting workflows, logging strategies, error tracking, performance profiling...

Use when about to verify UI in a browser — screenshot sweeps, click-throughs, exploratory or E2E visual QA.

Detects unnamed buttons, missing lang attribute, absent skip-to-content link, and missing/disabled viewport meta.

Simulates adaptive media states (prefers-color-scheme: dark, prefers-reduced-motion: reduce, forced-colors: active, pref...

Detects layout breakage at common CSS breakpoint boundaries (767px, 1023px, 1279px) — widths bugs typically hide between...

Detects layout bugs at exact CSS breakpoint boundaries by extracting the page's actual @media values and probing at (bou...

Captures and CLASSIFIES runtime errors during load AND interaction: uncaught exceptions (TypeError/ReferenceError/…), un...

Scans CSS stylesheets for properties with known cross-browser compatibility gaps: missing vendor prefixes, Safari-specif...

Detects whether the site respects prefers-color-scheme. No dark-mode handling = jarring white flash for dark-mode users

Tests dropdown / tooltip / autocomplete menus: open each, verify the popup is not clipped at the right or bottom edge of...

Resize-sweeps the page across a range of widths (incl. in-between 600/900/1100 and extremes 320/1920) to catch fluid-lay...

WCAG 1.4.11 — detects elements that rely solely on background color or images for distinction. Fail Windows High Contras...

Detects desktop-only elements that are CSS-hidden on mobile but still download heavy resources (images, iframes, videos)...

Detects :hover CSS rules that aren't wrapped in @media (hover: hover) — on touch devices these styles get 'stuck' after...

Detects missing alt text, broken images, oversized images, aspect-ratio distortion (stretched), and hero/banner images w...

Detects fixed/sticky overflow, narrow content, CTA below fold, dropdown cutoff, content bleed-through, critical-element-...

Detects loading spinners stuck 3s after networkidle, blank pages, and 404/error content even when HTTP returned 200 (SPA...

Tests loading-state behavior under simulated slow network. Detects stuck skeletons, loading spinners overlapping content...

Detects layout that breaks when the on-screen keyboard appears AND inputs with wrong type/inputmode that show the wrong...

Tests open modals / dialogs: verify they fit within the viewport height, action buttons (Submit/Cancel) are reachable, a...

Captures HTTP 4xx/5xx responses and failed requests during page load

Detects layout breakage in landscape orientation on mobile/tablet — swaps viewport dimensions and scans for overflow, cu...

Tests TRUE orientation rotation via browser_resize (swap width/height). Detects layout bugs that appear in landscape, st...

Detects horizontal content overflow on any element

Detects tab strips, segmented controls, and button groups whose children overflow horizontally without a visible scroll...

WCAG 2.3.3 — detects animations/transitions that are not gated by @media (prefers-reduced-motion: reduce). Vestibular-di...

WCAG 1.4.10 — detects content that requires horizontal scroll at 320px, fixed-width elements, non-shrinking tables, and...

Detects images served without srcset, missing max-width:100%, missing loading='lazy' below the fold, and oversized natur...

Switches the document to RTL (dir='rtl') and detects layout breakage — overflow, mirrored asymmetry, and non-logical CSS...

Detects fixed/sticky elements at the top or bottom of the viewport that don't use env(safe-area-inset-*) — content gets...

Tests sticky elements during scroll: they remain pinned, do not overlap content, and do not detach. Scrolls the page, ca...

Detects tap targets that are too small for accurate touch input, using WCAG 2.2 spacing-aware rules: <24×24 always flagg...