cad-verifier-medium
The `medium` rung of `cad-verifier`; `bin/route.mjs` picks it, not the user.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
1,669 agents across 245 plugins.
The `medium` rung of `cad-verifier`; `bin/route.mjs` picks it, not the user.
Stage 2 reviewer focused on server logic, request handling, error paths, and idempotency.
Stage 2 cross-functional reviewer focused on data quality, training correctness, reproducibility, and evaluation soundness.
Stage 2 reviewer focused on schema design, query plans, migration strategy, and indexing.
Use for day-to-day product execution below the CPO — clarifying ticket acceptance criteria, grooming docs/11-backlog.md, deciding small in-sprint scope…
Use for independent evidence-gathering on new-product work — user evidence, competitor observation, and the market facts a PRD assumes. Conditional role,…
Use before scope-lock, and again whenever the PRD or the backlog changes materially, to check the derived product documents against the founder's own recorded…
Quality & Regulatory agent for ISO 13485 QMS, MDR compliance, FDA submissions, GDPR/DSGVO, and ISMS audits. Orchestrates ra-qm-team skills. Spawn when users…
Senior Engineer agent for architecture decisions, code review, DevOps, and API design. Orchestrates engineering and engineering-team skills for technical…
UX research agent for research planning, persona generation, journey mapping, and usability test analysis. Use when product decisions need user evidence —…
Create implementation plans using research, best practices, and codebase analysis
Executes React implementation completely self-contained from an explicit prompt or frontend task file. Use when frontend task files exist, or when "frontend…
Creates a scoped ADR batch or one backend/general Design Doc from confirmed requirements and decision-relevant repository evidence. Use when technical choices…
Creates a scoped frontend ADR batch or one Design Doc from confirmed UI requirements and decision-relevant repository evidence. Use when frontend technical…
Scaffold & Boilerplate Intelligence Agent - Pattern scanning, consistent code generation, template engine
Chaos experiments, failure injection, blast radius control, gameday planning, and resilience validation specialist.
Clean/Hexagonal/Onion architecture specialist for maintainable systems
**Scope**: Detection commands for common failure modes across languages. Load during any perspective review on a real codebase. **Generated**: 2026-04-13
Zero-dependency combat visual upgrades: CSS particle replacement, Framer Motion combat juice, CSS 3D card transforms.
Custom GLSL filters for hit effects, glow chaining, DisplacementFilter shockwaves, Spine integration, particle emitter combat patterns, z-ordering, and alpha…
Usar para revisión de experiencia de usuario, auditoría de accesibilidad, análisis de flujos de usuario y evaluación de heurísticas de usabilidad. Se activa…
Unified QA agent covering both strategy and execution. Use for test plan creation, bug severity assessment, regression planning, release readiness evaluation…
Owns the release pipeline: certification checklists, store submissions, platform requirements, version numbering, and release-day coordination. Use for release…
The Security Engineer protects software systems and user data from threats. They review code for vulnerabilities, design secure authentication and…
Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks…
Cross-branch synthesizer for /craft:research. Reads all branch files in a research topic folder (produced by haiku researcher agents) and writes _plan.md…
Factual extraction agent for /craft:research. Investigates ONE sub-question, extracts findings with verbatim quotes and sources, writes them to a branch file,…
SPEC 작성 전문가. EARS 형식 요구사항 + Given/When/Then 인수 기준 작성. Use for /aura spec:new to create structured requirements.
테스트 스캐폴드 전문가. Phase 1.5에서 실패하는 테스트를 먼저 작성. Behavioral assertions required — not just NoError checks.
UX/접근성 검증 전문가. Phase 3.5에서 프론트엔드 파일 변경 시 자동 실행. WCAG 접근성 + 로딩/에러 상태 + 반응형 체크.
You are the Amplification Visionary. You read a completed plan draft and ask ONE question: **could this be 10x better in outcome with comparable effort?**
You are the Reframing Visionary. You read the ORIGINAL USER REQUEST — **NOT the plan draft** — and ask: **what is the user really trying to achieve, and does…
You are the Simplicity Visionary. You read a completed plan draft and ask ONE question: **is there a simpler approach that achieves the same outcome?**
Use when: package.json has React but NO next.config.*, Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use…
Use when: library docs lookup, API verification, best practices research. Do NOT use for: codebase exploration (use explore-codebase), code fixes (use sniper).
Use when: Cargo.toml present. Do NOT use for: JS/TS (typescript-expert), frontend apps (framework experts), other languages.
Use when dispatching work and unsure which model tier to use — returns a recommended model and effort level based on task characteristics
CSS animation and motion designer. Implements View Transitions API, scroll-driven animations, CSS keyframes, FLIP, staggered reveals, and reduced-motion…
Runs Lighthouse audits, analyzes Core Web Vitals, suggests specific fixes with file:line references. Targets LCP<=2.5s, CLS<=0.1, INP<=200ms.
Software implementation planning specialist that decomposes complex problems into sequential, testable sub-tasks
Ansible automation and infrastructure-as-code subject matter expert
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic