An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
8,249 agents across 643 plugins.
Comprehensive testing specialist that creates and executes test suites. Writes unit tests, integration tests, and E2E tests. Performs security testing,…
Final quality validation specialist that ensures requirements compliance and production readiness. Verifies all requirements are met, architecture is properly…
Expert UI/UX design agent with 10+ years of experience creating award-winning user experiences. Specializes in AI-collaborative design workflows that produce…
AWS + Kubernetes + Terraform infrastructure expert agent. Designs microservices architecture, cloud infrastructure, and CI/CD pipelines. Use proactively when…
Evaluator-Optimizer pattern agent for automatic iteration cycles. Orchestrates the Generator-Evaluator loop in the PDCA Check-Act phase until quality criteria…
Agent that guides users through the 9-phase Development Pipeline. Provides step-by-step guidance based on project level (Starter/Dynamic/Enterprise). Use…
AWS services architecture (Lambda, ECS, S3, RDS, SQS, CloudFront), IaC patterns, and cost optimization specialist.
Microsoft Azure infrastructure, services, and best practices specialist
Use this agent for git operations — atomic commits, rebase, history cleanup, and style detection. Flow detects the project's commit style from git log and…
Use this agent when the user needs help with financial management, cash flow analysis, expense tracking, revenue monitoring, financial reports, monthly…
Use this agent for test strategy, TDD workflows, integration/e2e coverage, and flaky test hardening. Grid follows the testing pyramid (70/20/10) and refuses to…
CONTRIBUTOR TOOL - Orchestrates plugin validation against latest Claude Code documentation. Spawns parallel validation subagents per component type, compresses…
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
Expert Elixir/Phoenix code reviewer - idioms, patterns, performance, conventions. Use proactively after writing Elixir code.
Evaluates technical topics, proposals, or decisions across multiple dimensions with evidence-based scoring and recommendations.
Analyzes existing codebase from a specific focus area, spawned in parallel
Collaborative planner working within pre-allocated task ID ranges
Learn how to use the Microsoft Agent Framework with Anthropic's Claude models.
Learn how to use Microsoft Agent Framework with Azure OpenAI ChatCompletion service.
Learn how to use Microsoft Agent Framework with Azure OpenAI Responses service.
Use this agent when you need to verify that a UI implementation matches its Figma design specifications. This agent should be called after code has been…
Use this agent PROACTIVELY when design work isn't coming together on the first attempt. If you've made 1-2 design changes and the result still feels off,…
Use this agent when you need a brutally honest Rails code review from the perspective of David Heinemeier Hansson. This agent excels at identifying…
COBOL engineering specialist for mainframe program development, maintenance, and modernization on z/OS. Use when the task requires writing or reviewing COBOL…
COBOL engineering specialist for mainframe program development, maintenance, and modernization on z/OS. Use when the task requires writing or reviewing COBOL…
Code review specialist for identifying bugs, security vulnerabilities, and code quality issues. Use when reviewing pull requests, auditing code changes, or…
This agent should be used to "review artifact", "validate spec output", "check quality", "review research output", "review requirements", "review design",…
Expert task planner for breaking plans into executable tasks. Masters POC-first workflow, task sequencing, quality gates, and constitution alignment.
This agent should be used to "decompose a large feature", "triage a big task", "break down into multiple specs", "create epic decomposition", or needs guidance…
Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and…
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow…
<!-- Loaded by performance-optimization-engineer when task involves DOM, CSS, requestIdleCallback, localStorage, RegExp, or batch reads/writes -->
Bundle analysis and optimization strategies for JavaScript applications.
Domain correctness review: requirements coverage, edge cases, state machines, data validation, failure modes.
前端 UI 开发、组件实现和 API 对接。例如:实现 UI 组件、修复样式问题、对接后端 API、搭建项目框架。**主动调用 when** 任务涉及 React/Vue 组件、CSS 样式、前端路由或 API 对接。(关键词:React、Vite、TanStack…
指标拆解、A/B 实验设计、漏斗分析与北极星指标管理。例如:定义 OMTM、设计 A/B 实验、分析转化漏斗、给出实验结论与推广建议。**主动调用 when** 需要指标定义、实验设计或数据驱动的产品决策。(关键词:北极星指标、OMTM、A/B test、漏斗分析、留存、置信区间、统计显著、Counter…
微信小程序代码审查、审核合规与包体积评估。例如:审查 wx.* API 调用、检查审核红线、评估主包/分包体积、识别 setData 性能问题。**主动调用 when** 小程序提审前需审查 wx.*…
Use this agent when setting up connections, configuring replication, working with remote tables, or integrating data from external systems into SAP Datasphere.…
Use this agent when designing SAP Datasphere data models, creating views (graphical or SQL), building analytic models, or working with the Data Builder.…
Use this agent when designing, generating, reviewing, previewing, or preparing deployment for SAP Fiori apps created with Fiori tools, UI5 tooling, or Fiori…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic