rUv

Coordinate 15 agents implementing claude-flow v3 across security, core systems, integration, testing, performance, and release work. Provides role assignments, task dependencies, GitHub tracking examples, and a four-phase schedule spanning 14 weeks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assign claude-flow v3 work across 15 agents
• Run tasks in parallel while respecting dependencies
• Track milestones and progress through GitHub issues

Improve the code that plans, reviews, and controls agent work while keeping the model fixed. Darwin Mode tests changes in isolated environments and retains variants that pass tests and show measurable improvement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing changes to planning and review logic
• Evaluating retry, tool, and memory policies
• Trying an offline dry run

Modernize the claude-flow v3 command-line interface by splitting large command files, adding interactive prompts, connecting hooks that run on execution events, and organizing multiple commands into automated workflows with progress reporting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Splitting large command files into focused modules
• Adding interactive setup prompts
• Recording command results through execution hooks

Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build answers grounded in retrieved documents
• Add meaning-based search to a knowledge base
• Find documents with similar content

Improve the MCP server that connects claude-flow v3 to tools. It guides connection reuse, faster tool lookup, request distribution, and communication changes, with monitoring to evaluate response times, errors, memory use, and cache performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Analyze slow MCP startup and tool responses
• Reuse connections and clean up idle ones
• Improve tool lookup and distribute requests

Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build agent memory that reuses past experiences
• Record and assess sequences of agent actions
• Consolidate similar experiences into reusable patterns

Connect agent tasks into a sequence where each step receives the previous output. Use custom prompts or predefined workflows to analyze code, plan refactoring, generate tests, optimize performance, or transform data through multiple stages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn code analysis into an improvement plan
• Prioritize and refactor existing code
• Find test gaps and generate unit tests

Automate browser tasks with agent-browser, using snapshots that label page elements for the agent. Handle login flows, fill and submit forms, extract page information, and capture screenshots through a repeatable navigation and interaction workflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Automating login flows
• Filling and submitting web forms
• Extracting product names, prices, and links

Coordinate changes across multiple GitHub repositories with teams of AI agents. Align package versions, synchronize documentation, standardize project structures, and organize integration tests and pull requests for updates that affect several projects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Aligning dependency versions across repositories
• Synchronizing shared documentation
• Standardizing repository structures and CI workflows

Manage code changes across multiple AI agents while recording operations and their outcomes. Use previous task histories to find similar attempts, inspect successful patterns, and obtain suggested steps for implementation, code review, deployment, or merging changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Manage code changes by multiple AI agents
• Get deployment suggestions from previous outcomes
• Inspect failed merge attempts before trying again

Coordinate specialist agents in Claude Flow under a lead agent. Distribute development or research tasks, use voting to make decisions, preserve shared knowledge, and pause or resume work through managed sessions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Splitting application development among specialist agents
• Comparing technologies through research and voting
• Coordinating code reviews across specialties

Turn a feature request into a minimal implementation plan before coding. Identify which files need changes, explain why, define the smallest required interface, and flag broader effects or expanded permissions for the implementer.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan a feature before coding
• Identify files affected by a change
• Review scope and permission changes

Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare performance before and after v3 optimization
• Evaluate vector search speed and memory use
• Track performance regressions over time

Analyze teams of agents in Claude Flow to find delays in communication, processing, memory, and network access. Generate performance reports, compare runs, and review recommendations or apply available automatic optimizations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating slow agent tasks
• Creating weekly performance reports
• Comparing performance before and after changes

Deploy teams of AI agents on Flow Nexus and automate development, research, or data processing workflows. Define step dependencies and event triggers, assign suitable agents, and monitor progress, queues, and execution history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Automating testing, builds, and deployment
• Distributing research and analysis across agents
• Scheduling data extraction, transformation, and loading

Manage Flow Nexus accounts, isolated cloud environments for running code, and application deployment. The skill also covers publishing templates, tracking credits and payments, submitting coding challenges, managing stored files, and checking execution logs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a cloud environment and run code
• Publish an app or deploy a template
• Check credit balances and configure automatic refills

Create and improve GitHub Actions workflows for automated testing and deployment. Coordinate multiple AI agents to review pull requests, investigate failed runs, scan for security issues, and manage releases across repositories.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create workflows for automated testing and deployment
• Investigate failed runs and suggest fixes
• Coordinate code reviews and security checks

Organize software releases on GitHub, from version suggestions and release notes to testing, builds, and deployment. Coordinate multiple packages or repositories, roll changes out in stages, and configure rollback to restore an earlier release when problems occur.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing version updates and release notes
• Coordinating releases across packages and repositories
• Deploying in stages with monitoring and rollback

Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train agents from historical experience
• Build decision-making for games and navigation
• Combine experience from multiple agents for training

Organize software development from requirements and architecture through testing, review, and deployment. Use specialized agent roles, shared memory, and test-driven development, where tests are written before code, to coordinate work across the project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan and implement a new feature
• Refactor legacy code with supporting tests
• Review code security and performance

Automate checks, code formatting, agent coordination, and session records around Claude Code operations. Uses hooks, actions triggered before or after work, to preserve context and connect development tasks with shared memory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Automatically format and validate edited code
• Share progress across multiple agents
• Save and restore development sessions

Work with AI as a coding partner, choosing who writes code and who guides the work. Supports role switching, test generation, ongoing code review, debugging, and step-by-step explanations for learning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Write code with ongoing AI review
• Direct AI implementation while reviewing its output
• Develop features by writing tests first

Implement agents that use recorded task outcomes to choose future approaches. ReasoningBank supports matching past patterns, comparing strategies, retaining experience in AgentDB, and tracking how strategy success and learning change over time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose task strategies using past outcomes
• Compare approaches to code review or bug fixing
• Match current situations to learned patterns

Build custom Claude Code skills with clear instructions, reusable templates, and organized supporting files. The skill guides you through YAML metadata, meaning the skill’s name and description, and separates essential steps from detailed references.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning recurring workflows into custom skills
• Creating skill templates with supporting scripts
• Organizing long instructions into reference files