ECOMANSONI

Audit the developer experience of a product, SDK, docs site, or SKILL.md by dropping multiple Claude subagents at it with only a tiny task prompt and real tools (WebFetch, Bash, Write). Agents must discover the docs themselves, install deps, ask for credentials if needed, and attempt real execution. The skill captures each agent's trace — tool calls, retries, wall time, errors — and scores on Setup Friction, Speed, Efficiency, Error Recovery, and Doc Quality, then emits an HTML report with an A–F grade and concrete fixes. Use when the user asks to audit agent experience, test a skill, audit docs for agents, check if a SDK is agent-friendly, validate a SKILL.md, measure agent DX, or benchmark how painful onboarding is for an AI agent. Triggers: 'audit agent experience', 'test this skill', 'audit docs for agents', 'is my SDK agent-friendly', 'run a DX audit', 'agent experience test', 'test my docs', 'how do agents do with my product'.

Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.

Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks, and visual explorations. Use whenever the user asks to design, mock up, prototype, wireframe, visualize, or explore an interface, product screen, user flow, content layout, visual artifact, or pitch/deck concept, even if they do not say "design". Also use for setting up, importing, or authoring reusable design systems, UI kits, brand tokens, component libraries, or loadable design-system bundles. The skill guides context gathering, clarifying questions, choosing fidelity, selecting or binding design systems, creating project folders, building one or more HTML deliverables, previewing them, and verifying they load cleanly. It is harness-agnostic for Claude Code, Cursor, Codex Agent, and similar file-capable agents; harness-specific ask, preview, screenshot, and verification tools are resolved from references/.

Use the Browserbase CLI (`browse`) for Browserbase Functions and platform API workflows. Use when the user asks to run `browse`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, search the web through the Browserbase Search API, or scaffold starter templates. Prefer the Browser skill for interactive browsing; use the top-level `browse` driver commands (`browse open`, `browse get`, etc.) only when the user explicitly wants the CLI path.

Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.

Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.

Mansoni browser agent — управляет браузером без скриншотов, видит реальный UI, тестирует проект в реальном времени. Использует Playwright для навигации, проверки состояния и интерактивного тестирования.

Graphify integration for Mansoni — создаёт knowledge graph проекта, ищет связи между компонентами, генерирует отчёты. Использует глобальный graphify.

Comprehensive accessibility testing including WCAG compliance. Use when: full a11y audit, compliance checking, or accessibility certification.

WCAG compliance and accessibility testing. Use when: auditing accessibility, fixing a11y issues, or testing screen reader compatibility.

Meta-auditing of Claude agents and their outputs. Use when: reviewing agent quality, validating agent decisions, or improving agent prompts.

Smooth 60fps animations and transitions. Use when: optimizing CSS animations, GPU acceleration, or motion rendering.

API response time improvement strategies. Use when: reducing API latency, optimizing response payloads, or improving API performance.

Zero-downtime deployment strategy with instant rollback capability. Use when: planning production deployments, implementing blue-green infrastructure, or setting up traffic switching.

Gradual traffic shifting for safe production releases. Use when: releasing features incrementally, validating changes with real users, or A/B testing infrastructure.

Intentional failure injection for system resilience testing. Use when: validating fault tolerance, testing SLOs under stress, or preparing for incidents.

API contract validation between services. Use when: testing API compatibility, validating schemas, or preventing breaking changes.

Supabase/PostgreSQL query optimization. Use when: optimizing slow queries, adding indexes, or improving database performance.

Business continuity and data recovery procedures. Use when: planning DR scenarios, creating backup strategies, or defining RTO/RPO.

Containerization best practices for Node.js/React. Use when: creating Dockerfiles, optimizing images, or managing containers.

CI/CD pipeline configuration and management. Use when: creating workflows, optimizing CI, or managing GitHub Actions.

API and service integration testing patterns. Use when: testing database interactions, API contracts, or multi-service flows.

Kubernetes deployment patterns. Use when: deploying to K8s, managing pods, or configuring services.

Playwright-based browser testing with real user flows. Use when: running E2E tests, testing authenticated flows, or verifying UI in real browser. Triggers: browser testing, E2E, Playwright, real user simulation.

Performance testing under load. Use when: validating scalability, finding bottlenecks, or setting performance baselines.

Finding and fixing memory leaks in JavaScript/TypeScript. Use when: investigating OOM errors, high memory usage, or profiling performance issues.

Observability infrastructure: metrics, logs, traces, alerts. Use when: setting up monitoring, creating dashboards, or configuring alerts.

Network performance optimization for web apps. Use when: reducing latency, optimizing API calls, or improving data transfer.

Comprehensive performance auditing across frontend, backend, and infrastructure. Use when: full performance review, bottleneck identification, or optimization planning.

React rendering optimization techniques. Use when: reducing re-renders, optimizing component trees, or improving React performance.

Coordinated release process with versioning, changelog, and deployment gates. Use when: planning releases, managing versions, or coordinating deployments.

Secure handling of API keys, tokens, and credentials. Use when: managing secrets, rotating keys, or auditing credential storage.

Expert DevOps practices: architecture, scaling, incident response. Use when: complex infrastructure decisions, scaling challenges, or architectural reviews.

Comprehensive test suite validation and coverage analysis. Use when: assessing test quality, identifying gaps, or planning test improvements.

Screenshot comparison testing for UI changes. Use when: detecting unintended UI changes, validating design consistency, or automating visual QA.

Frontend performance testing and optimization. Use when: auditing Core Web Vitals, optimizing load times, or improving UX performance.

User acceptance testing procedures for web applications. Use when: validating features with real users, conducting UAT sessions, or preparing for release.

Аудит соответствия требованиям: GDPR/ФЗ-152 (персональные данные), согласие пользователя, право на удаление, политика конфиденциальности, Supabase compliance, хранение данных. Use when: GDPR, ФЗ-152, compliance, персональные данные, согласие, право на удаление, privacy.

Calls E2EE security audit for calls-v2: ephemeral ECDH+HKDF+AES-KW key exchange, ECDSA signatures, SFrame transforms, rekey state machine. Use when: calls-v2, video calls encryption.

Quantitative assessment of code quality across multiple dimensions.