A systematic development workflow for producing high-quality, test-driven software. Integrates TDD, systematic debugging, verification gates, and agentic orchestration.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin dutchthenomad-claude-flowThis folder contains **slash commands** - user-invoked prompts that execute specific workflows. Each `.md` file defines a command accessible via `/command-name` in Claude Code.
Quick test runner - run pytest and analyze results without permission prompts
Use for ALL technical failures. 4-phase root cause analysis before ANY fix attempts.
Architect mode - ULTRATHINK planning from GitHub Issue. Use for ALL new features and significant changes.
Use after completing a task to get code review before proceeding.
Run project test suite with auto-detection of test framework.
Save/restore context across /clear commands and sessions. Use before clearing context.
Use for ALL new features, bug fixes, and refactoring. Enforces RED-GREEN-REFACTOR cycle.
Use BEFORE claiming any task is complete. Evidence before claims, always.
Use to create isolated workspace for feature development. Enables parallel work without branch switching.
This folder contains **subagent definitions** - specialized AI assistants that Claude Code can delegate tasks to. Each agent has specific expertise and tool access.
Senior Python Developer - implements features to make tests pass, TDD workflow
Figma design specialist with full MCP integration and browser automation. Use when working with Figma designs, UI/UX implementation, design systems, component libraries, design-to-code workflows, or browser-based design validation. Can create, modify, and inspect Figma documents directly, and control browsers for visual testing.
RAG-powered project specialist for claude-flow. Answers architecture questions, creates commands/agents/skills, and maintains CONTEXT.md files. Use for any questions about this repository.
GitHub Repository Master - issues, PRs, commits, branches, MCP operations
ML/RL Engineer - Gymnasium environments, Stable Baselines 3, reward shaping, model training
Use this agent when you need to clean up development artifacts, remove unused files, or organize a messy project structure. Examples: <example>Context: User has been working on multiple features and wants to clean up before a release. user: 'I've been working on several features and my project is getting messy with old scripts and unused files. Can you help clean it up?' assistant: 'I'll use the project-cleanup-agent to analyze your project structure and safely remove unused artifacts.' <commentary>The user needs project cleanup, so use the project-cleanup-agent to identify and remove superfluous files.</commentary></example> <example>Context: After completing a development phase, the user wants to remove temporary files and unused scripts. user: 'We just finished the trading bot implementation and there are lots of test scripts and temporary files lying around' assistant: 'Let me use the project-cleanup-agent to identify and clean up the development artifacts from your trading bot project.' <commentary>Post-development cleanup is needed, so use the project-cleanup-agent to organize and remove unnecessary files.</commentary></example>
QA Automation Engineer - writes tests only, pytest, TDD, test coverage
RAG-powered WebSocket protocol specialist for rugs.fun integration. Use PROACTIVELY when questions involve rugs.fun, REPLAYER, VECTRA-PLAYER, WebSocket events, gameStateUpdate, Socket.IO, or trading bot development. Provides authoritative answers about events, game mechanics, field definitions, and implementation patterns from indexed documentation.
Ubuntu Systems Architect - system packages, services, dependencies, environment setup
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Uses power tools
Uses Bash, Write, or Edit tools
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.