dmuhoro
Community@dmuhoro
dmuhoro maintains claude-flow v3 skills for multi-agent orchestration, AgentDB vector memory, GitHub CI/CD coordination, and SPARC development methodology.
Agent Skills by dmuhoro
Showing 30 vetted skills indexed across 1 GitHub repositories.
V3 MCP Optimization
Optimizes MCP server performance with connection pooling, load balancing, and tool registry indexing.
stream-chain
Chains sequential prompts so each step's output feeds the next in multi-agent workflows.
sparc-methodology
Orchestrates multi-agent software development using the SPARC phased methodology with TDD workflows.
Hooks Automation
Automates pre/post-operation hooks, session management, and memory coordination for Claude Code workflows.
V3 CLI Modernization
Modernizes claude-flow v3 CLI with modular commands, interactive prompts, and hooks integration.
github-workflow-automation
Automates GitHub Actions CI/CD pipelines with swarm-coordinated workflow generation and analysis.
Verification & Quality Assurance
Verifies code quality with truth scoring, automated checks, and git-based rollback.
V3 Deep Integration
Migrates claude-flow onto agentic-flow@alpha adapters to eliminate duplicate orchestration code.
Skill Builder
Create Claude Code Skills with YAML frontmatter and progressive disclosure structure.
V3 Core Implementation
Implements DDD domains, clean architecture, and dependency injection for claude-flow v3 TypeScript modules.
ReasoningBank with AgentDB
Implements adaptive agent learning with trajectory tracking, verdict judgment, and memory distillation on AgentDB.
ReasoningBank Intelligence
Implements adaptive learning for AI agents using pattern recognition and strategy optimization.
V3 Security Overhaul
Remediates critical CVEs and implements secure-by-default patterns for claude-flow v3.
swarm-advanced
Orchestrates multi-agent swarms for research, development, testing, and analysis workflows.
github-release-management
Orchestrates GitHub releases with automated versioning, testing, deployment, and rollback workflows.
AgentDB Advanced Features
Configure QUIC synchronization, hybrid search, and multi-database management for AgentDB vector stores.
browser
Automates web browser navigation, interaction, and data extraction using AI-optimized accessibility snapshots.
V3 DDD Architecture
Decomposes monolithic orchestrator code into bounded-context DDD domains with clean architecture layers.
Swarm Orchestration
Orchestrates multi-agent swarms with mesh, hierarchical, and adaptive topologies for parallel task execution.
V3 Memory Unification
Consolidates multiple memory backends into AgentDB with HNSW vector search indexing.
github-code-review
Orchestrates multi-agent code reviews on GitHub pull requests using swarm coordination.
AgentDB Performance Optimization
Optimizes AgentDB vector databases using quantization, HNSW indexing, caching, and batch operations.
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB vector storage.
V3 Performance Optimization
Benchmarks and validates Flash Attention, HNSW search, and memory optimization targets for claude-flow v3.
Frequently Asked Questions About dmuhoro
FAQPage SchemaWhat tasks can I accomplish with dmuhoro's claude-flow skills?▼
You can orchestrate multi-agent swarms for parallel development, implement semantic vector search and persistent agent memory with AgentDB, automate GitHub code review, releases, and project boards, apply SPARC methodology with TDD, and run pair programming sessions with truth-score verification and automatic rollback.
Who are these skills designed for?▼
These skills target software engineers and platform teams building distributed multi-agent systems, RAG pipelines, and CI/CD pipelines on GitHub. They suit developers working with claude-flow v3, agentic-flow, and ruv-swarm who need coordination, memory, and quality verification capabilities.
What are the installation prerequisites and dependencies?▼
GitHub skills require the GitHub CLI (gh) authenticated, git, Node.js v16+ (v20+ for releases), and claude-flow or ruv-swarm MCP servers configured. Multi-repo coordination needs ruv-swarm@^1.0.11 and gh-cli@^2.0.0. Skills install as Claude Code skill folders with YAML frontmatter.
How does AgentDB improve agent memory and search performance?▼
AgentDB provides HNSW indexing delivering 150x-12,500x faster search, quantization for 4-32x memory reduction, QUIC synchronization, and hybrid search. It unifies 6+ memory systems into one service and supports ReasoningBank adaptive learning with trajectory tracking and verdict judgment.
What performance targets does claude-flow v3 achieve?▼
The v3 skills target sub-100ms MCP response times via connection pooling and load balancing, 2.49x-7.47x Flash Attention speedup, 50-75% memory reduction, and elimination of 10,000+ duplicate lines through deep agentic-flow integration following ADR-001 and DDD bounded contexts.