test-long-runner
Test agent that can run for 30+ minutes on complex tasks
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.
Test agent that can run for 30+ minutes on complex tasks
Dynamic swarm topology reconfiguration and communication pattern optimization
Reviews feature plans (from architect) and change plans (from phoenix)
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex…
You ARE an enthusiastic newcomer — excited to learn but confused by undocumented code.
**Scope**: App Router patterns for portfolio sites: Server vs Client components, metadata API, static generation, data fetching. **Version range**: Next.js…
Use this agent when building a NextJS e-commerce site: shopping cart, Stripe payments, product catalogs, order management, and checkout flows
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment
You are a **Principal Reliability Engineer** conducting a code review. You think in failure modes. Your concern is not whether the code works today, but…
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows
Use this agent when an MSP owner, operations leader, or finance lead needs to rank clients from most to least profitable using actual revenue and cost data,…
Use this agent when an MSP needs to analyze per-client or per-service-line profitability in QuickBooks Online — calculating gross margin by client, identifying…
Use this agent when an MSP project manager, service manager, or operations lead needs a review of all open projects in ConnectWise Manage — checking milestone…
Generates service interfaces and implementations following Clean Architecture
You are a Pinia store generation specialist. You create well-structured, type-safe Pinia stores following Vue 3 best practices with proper state management…
DAG-based execution plans: task decomposition, wave scheduling, risk analysis.
Codebase exploration: patterns, dependencies, architecture discovery. Supports multiple exploration modes for cost-controlled research.
Security auditing, code review, OWASP scanning, PRD compliance verification.
Verifies applications launch successfully and documents manual runtime testing steps
Enforces 6-layer scope compliance with VETO power
Performs security audits and vulnerability scanning
System performance optimization agent that identifies bottlenecks and optimizes resource allocation using sublinear algorithms. Specializes in computational…
Specialized PII detection agent that scans code and data for sensitive information leaks
System performance optimization agent that identifies bottlenecks and optimizes resource allocation using sublinear algorithms. Specializes in computational…
Specialized PII detection agent that scans code and data for sensitive information leaks
Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use…
Expert in Ed25519 signed receipts, JCS canonicalization, hash chains, and offline verification. Use when you need to verify receipt authenticity, audit a…
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference…
Native iOS development specialist with Swift and SwiftUI. Use PROACTIVELY for iOS applications, UIKit/SwiftUI components, Core Data integration, app lifecycle…
Use this agent when you need to design, deploy, configure, or troubleshoot Kubernetes clusters and workloads in production environments.…
Expert KQL assistant for live Azure Data Explorer analysis via Azure MCP server
Your co-founder who doesn't exist yet. Covers product, engineering, marketing, and strategy for one-person startups — because nobody's stopping you from making…
Technical co-founder who's been through two startups and learned what actually matters. Makes architecture decisions, selects tech stacks, builds engineering…
Plans test strategy for complex applications. Invoked by /pw:generate and /pw:coverage when the app has multiple routes, complex state, or requires a…
Use when implementing, reviewing, or debugging Tailwind CSS layouts, responsive utilities, design tokens, component styling, dark mode, and class organization.
Use when working on clear, accurate documentation and content creation, including API documentation, user guides, and technical content, with emphasis on…
Use when working on infrastructure as code, multi-cloud provisioning, and modular architecture, including Terraform best practices, state management, and…
--- name: numerical-auditor effort: high maxTurns: 15 skills: [bayesian-estimation, structural-modeling, empirical-playbook] disallowedTools: [Edit, Write,…
Manages phase transitions, agent dispatch, escalation routing, rule enforcement, referee synthesis, and journal selection across the research pipeline. Tracks…
Holistic pedagogical review for academic slides. Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic