mcp-expert
Expert on Model Context Protocol (MCP) — server configuration, discovery, and troubleshooting via `.mcp.json` and `claude mcp add`. Use PROACTIVELY when the…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
596 agents across 643 plugins.
Expert on Model Context Protocol (MCP) — server configuration, discovery, and troubleshooting via `.mcp.json` and `claude mcp add`. Use PROACTIVELY when the…
Deep requirement analysis agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase ANALYZE — starting a new loop session, when the user…
Evolution agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase EVOLVE — after experience-extractor produces learning.json, when…
Fills Nyquist validation gaps by generating tests and verifying coverage for phase requirements.
Verifies plans will achieve phase goals before execution. Goal-backward analysis of plan quality across 10 dimensions.
Creates executable phase plans with task breakdown, dependency analysis, wave assignment, and goal-backward verification. Also creates roadmaps.
Intelligent agent coordination and dynamic spawning specialist
Autonomous task completion coordinator using /loop and autopilot MCP tools
Backtesting specialist using npx neural-trader Rust/NAPI engine — walk-forward validation, Monte Carlo simulation, parameter optimization. Orthogonal research…
Intelligent agent coordination and dynamic spawning specialist
Autonomous task completion coordinator using /loop and autopilot MCP tools
Backtesting specialist using npx neural-trader Rust/NAPI engine — walk-forward validation, Monte Carlo simulation, parameter optimization. Orthogonal research…
Use this agent when reviewing local code changes or pull requests to understand the historical context of modified code, including past issues, patterns, and…
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist…
Use this agent when generating evaluation rubrics, checklists, criteria, metrics, and weights for a user prompt BEFORE implementation begins. Produces…
安全工程师,负责漏洞检测、安全审计、OWASP Top 10防护、依赖扫描和安全最佳实践执行,守护代码库和基础设施的安全底线
系统架构设计师,负责整体架构规划、ADR决策记录、技术选型与trade-off分析、模块职责划分、系统边界定义,确保架构支撑业务增长且保持技术债务可控
Dynamic skill generator for the Self-Evolving Loop. Use when executing /evolving-loop Phase GENERATE — after requirement-analyzer completes, when skills need…
Expert on creating, editing, and debugging Claude Code skills and slash commands. Use when the user mentions creating a skill or slash command, wants a…
Unified research agent for project domains, phase implementation approaches, and synthesis. Follows source-hierarchy methodology with confidence levels.
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation.
Fast synthesis of multiple research outputs into coherent recommendations. Resolves contradictions between sources.
Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This…
Comprehensive performance benchmarking, regression detection and performance validation
Browser automation agent — drives Playwright via 23 MCP tools, captures every session as an RVF container with a ruvector trajectory, and gates content through…
Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This…
Comprehensive performance benchmarking, regression detection and performance validation
Browser automation agent — drives Playwright via 23 MCP tools, captures every session as an RVF container with a ruvector trajectory, and gates content through…
Use this agent when adding LLM-as-Judge verification sections to implementation steps in task files. Produces structured per-step evaluation specifications…
Use this agent when researching unknown technologies, libraries, frameworks, and dependencies to gather relevant resources and documentation for implementation…
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively…
负责任务分解、进度追踪、范围控制的项目经理,将大需求拆解为可执行的开发任务并严控项目边界
Validates UI implementation against UI-SPEC.md design contracts across 6 dimensions with visual verification via Claude in Chrome.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic