deployment-verificatio…
Use this agent when a PR touches production data, migrations, or any behavior that could silently discard or duplicate records. Produces a concrete…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
8,242 agents across 643 plugins.
Use this agent when a PR touches production data, migrations, or any behavior that could silently discard or duplicate records. Produces a concrete…
System design specialist for architecture decisions, technology selection, and high-level component design. Use when the task requires evaluating architectural…
Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task…
Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task…
This agent should be used to "research a feature", "analyze feasibility", "explore codebase", "find existing patterns", "gather context before requirements".…
Expert specification analyst for creating feature specs aligned with project constitution. Generates user stories, acceptance criteria, and scope definitions.
Autonomous task executor for spec-kit development. Executes a single task from tasks.md, verifies, commits, and signals completion.
Use proactively to retrieve and extract relevant information from Output SDK project documentation files. Checks if content is already in context before…
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze…
Design new workflows for the Output SDK system, plan complex workflow orchestrations, or create comprehensive implementation blueprints. Use at the beginning…
Detect breaking changes, backward compatibility violations, schema inconsistencies, and HTTP status code misuse.
JWT, OAuth, session management, and token refresh implementations with security-correct patterns
Universal operational rules injected by /do at agent dispatch. Domain-specific rules live in each agent's .md file.
代码审查、安全审计和质量评估。例如:审查 PR 变更、审计安全漏洞、检查最佳实践。**主动调用 when** 收到 PR 审查请求、安全审计请求或发现可疑代码模式。(关键词:OWASP、SQL 注入、XSS、CSRF、密钥泄漏、依赖漏洞、PR review、code smell)
面向用户的内容产出——发布说明、产品博客、文档化访谈与案例研究。例如:写 release notes、产品上线博客、用户案例、内部知识沉淀。**主动调用 when** 需要面向用户 / 社区 / 媒体的非技术内容。(关键词:release…
部署工程师 —— UAT 环境部署、容器编排、冒烟自检。例如:merge 后拉取合并代码、用独立 compose project 起隔离 UAT 栈、端口偏移避开 dev worktree、冒烟校验后交接 QA。**主动调用 when** code review(含 SIT Audit)通过 + 合并到 main…
Bugfix diagnosis and pre-fix evidence specialist on Opus at high effort. Use to prove a concrete root cause, reproduce it, add a candidate regression guard,…
Use this agent when implementing CAP service handlers, CRUD operations, custom actions, and OData logic. This agent specializes in Node.js, TypeScript, and…
Use this agent when troubleshooting data actions, multi actions, or allocation issues. Helps with tracing, debugging, and optimizing planning calculations.…
Use this agent when managing SAP Datasphere administration tasks including spaces, users, roles, security, monitoring, and system configuration. Examples:…
Release Train Engineer - PR creation, CI/CD validation, release coordination
Security Engineer - RLS validation, security audits, vulnerability scanning
System Architect - Pattern validation, architectural decisions, conflict prevention
Your GitHub analytics command center -- team velocity, review turnaround, issue resolution metrics, contribution activity, bottleneck detection, and code churn…
ARIA implementation specialist for web applications. Use when building or reviewing any interactive web component including modals, tabs, accordions,…
CI/CD accessibility agent. Conversational agent for setting up, managing, and troubleshooting accessibility CI pipelines. Supports baseline management (fail…
PROACTIVELY optimize performance when any layer shows degradation. MUST BE USED for slow page loads, API latency, query performance, memory leaks, or bundle…
PROACTIVELY research product direction by combining market evidence and requirement clarification. MUST BE USED when teams need competitive context,…
PROACTIVELY conduct user research before designing major features or when conversion metrics drop. MUST BE USED when building user personas, validating new…
Verifies implementation quality by dispatching specialized evaluators. Evaluate-Loop Step 4.
Implements tasks from the plan sequentially. Evaluate-Loop Step 3.
Fixes issues found by evaluation. Evaluate-Loop Step 5.
[Subagent] 末端 HTML 导出器。 接收导演已经确认的 HTML 版式,调用脚本生成 `.html` 文件。
[Subagent] 文本去AI味专家。 基于 WikiProject AI Cleanup 综合指南,深度去除"AI腔",注入人类灵魂。 由工作流导演调度;完整流程中的推进方式以工作流 JSON 为准,也可作为独立工具使用。
[Subagent] 记忆装载器。 扫描历史写作复盘(99_episode.md),提炼跨项目的稳定写作偏好规则, 生成当前项目的 00_memory_packet.md 供下游 Agent 读取。 由工作流导演调度;具体阶段顺序以工作流 JSON 为准,本代理不自行定义顺序。
Marketing strategist covering SNS, ads, content, and campaigns. Orchestrates creative production with image/video generation skills.
Plan implementation strategies and break down complex tasks. Use when designing solutions.
Use this agent when you need a thorough review of TypeScript type definitions, type usage patterns, and type architecture in recently written or modified code.…
DevOps自动化工程师,负责CI/CD流水线设计、Docker容器化部署、基础设施即代码(IaC)、监控告警配置,确保项目从构建到部署的全链路自动化
专注React/Vue/现代Web前端开发的工程师,负责组件开发、页面构建、响应式布局、Core Web Vitals性能优化、可访问性合规,交付高质量用户界面代码
Git工作流专家,负责分支策略设计、合并冲突解决、代码历史维护、CI集成和团队Git规范制定
Binary analysis agent — disassembly, decompilation, vulnerability discovery in compiled code, firmware analysis, protocol reverse engineering
Deep security audit agent — performs comprehensive security review of code, configs, and architecture against OWASP, MITRE ATT&CK, and CWE frameworks
Run simple commands, collect and summarize results to protect parent context. Lightweight subagent.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic