Agent Migration Plan

作者 ruvnet6051f6702b61无许可证74K 个星标收录于 2026年10月8日更新于 2026年10月8日仓库今天更新

Agent skill for migration-plan - invoke with $agent-migration-plan

仅含说明AI & Agents
AI 生成的概览

提供将 Claude Flow 命令迁移为代理定义的迁移方案，包含角色、工具与触发条件。

功能
该技能提供一份书面迁移方案，用于把现有的 .claude/commands 结构转换为基于代理的系统。它定义了 YAML 代理定义格式，并按协调、GitHub 集成、SPARC 方法、分析、记忆、自动化、优化和监控等类别列出映射后的代理。每个条目说明职责、能力、允许与受限工具以及激活触发条件，并附有实施与验证指南。
适用场景
适用于规划或记录从命令式工作流向代理式工作流的转变。适合需要命令到代理映射、工具限制和上线步骤参考的团队。
运行要求
不包含脚本，仅为说明性文档。文中提及 Claude Flow MCP 工具和 .claude/commands 目录结构，但运行它除代理本身外无需其他条件。

name: migration-planner type: planning color: red description: Comprehensive migration plan for converting commands to agent-based system capabilities:

  • migration-planning
  • system-transformation
  • agent-mapping
  • compatibility-analysis
  • rollout-coordination priority: medium hooks: pre: | echo "📋 Agent System Migration Planner activated" echo "🔄 Analyzing current command structure for migration"

    Check existing command structure

    if [ -d ".claude$commands" ]; then echo "📁 Found existing command directory - will map to agents" find .claude$commands -name "*.md" | wc -l | xargs echo "Commands to migrate:" fi post: | echo "✅ Migration planning completed" echo "📊 Agent mapping strategy defined" echo "🚀 Ready for systematic agent system rollout"

Claude Flow Commands to Agent System Migration Plan

Overview

This document provides a comprehensive migration plan to convert existing .claude$commands to the new agent-based system. Each command is mapped to an equivalent agent with defined roles, responsibilities, capabilities, and tool access restrictions.

Agent Definition Format

Each agent uses YAML frontmatter with the following structure:

yaml
---role: agent-typename: Agent Display Nameresponsibilities:  - Primary responsibility  - Secondary responsibilitycapabilities:  - capability-1  - capability-2tools:  allowed:    - tool-name  restricted:    - restricted-tooltriggers:  - pattern: "regex pattern"    priority: high|medium|low  - keyword: "activation keyword"---

Migration Categories

1. Coordination Agents

Swarm Initializer Agent

Command: .claude$commands$coordination$init.md

yaml
---role: coordinatorname: Swarm Initializerresponsibilities:  - Initialize agent swarms with optimal topology  - Configure distributed coordination systems  - Set up inter-agent communication channelscapabilities:  - swarm-initialization  - topology-optimization  - resource-allocation  - network-configurationtools:  allowed:    - mcp__claude-flow__swarm_init    - mcp__claude-flow__topology_optimize    - mcp__claude-flow__memory_usage    - TodoWrite  restricted:    - Bash    - Write    - Edittriggers:  - pattern: "init.*swarm|create.*swarm|setup.*agents"    priority: high  - keyword: "swarm-init"---
Agent Spawner

Command: .claude$commands$coordination$spawn.md

yaml
---role: coordinatorname: Agent Spawnerresponsibilities:  - Create specialized cognitive patterns for task execution  - Assign capabilities to agents based on requirements  - Manage agent lifecycle and resource allocationcapabilities:  - agent-creation  - capability-assignment  - resource-management  - pattern-recognitiontools:  allowed:    - mcp__claude-flow__agent_spawn    - mcp__claude-flow__daa_agent_create    - mcp__claude-flow__agent_list    - mcp__claude-flow__memory_usage  restricted:    - Bash    - Write    - Edittriggers:  - pattern: "spawn.*agent|create.*agent|add.*agent"    priority: high  - keyword: "agent-spawn"---
Task Orchestrator

Command: .claude$commands$coordination$orchestrate.md

yaml
---role: orchestratorname: Task Orchestratorresponsibilities:  - Decompose complex tasks into manageable subtasks  - Coordinate parallel and sequential execution strategies  - Monitor task progress and dependencies  - Synthesize results from multiple agentscapabilities:  - task-decomposition  - execution-planning  - dependency-management  - result-aggregation  - progress-trackingtools:  allowed:    - mcp__claude-flow__task_orchestrate    - mcp__claude-flow__task_status    - mcp__claude-flow__task_results    - mcp__claude-flow__parallel_execute    - TodoWrite    - TodoRead  restricted:    - Bash    - Write    - Edittriggers:  - pattern: "orchestrate|coordinate.*task|manage.*workflow"    priority: high  - keyword: "orchestrate"---

2. GitHub Integration Agents

PR Manager Agent

Command: .claude$commands$github$pr-manager.md

yaml
---role: github-specialistname: Pull Request Managerresponsibilities:  - Manage complete pull request lifecycle  - Coordinate multi-reviewer workflows  - Handle merge strategies and conflict resolution  - Track PR progress with issue integrationcapabilities:  - pr-creation  - review-coordination  - merge-management  - conflict-resolution  - status-trackingtools:  allowed:    - Bash  # For gh CLI commands    - mcp__claude-flow__swarm_init    - mcp__claude-flow__agent_spawn    - mcp__claude-flow__task_orchestrate    - mcp__claude-flow__memory_usage    - TodoWrite    - Read  restricted:    - Write  # Should use gh CLI for GitHub operations    - Edittriggers:  - pattern: "pr|pull.?request|merge.*request"    priority: high  - keyword: "pr-manager"---
Code Review Swarm Agent

Command: .claude$commands$github$code-review-swarm.md

yaml
---role: reviewername: Code Review Coordinatorresponsibilities:  - Orchestrate multi-agent code reviews  - Ensure code quality and standards compliance  - Coordinate security and performance reviews  - Generate comprehensive review reportscapabilities:  - code-analysis  - quality-assessment  - security-scanning  - performance-review  - report-generationtools:  allowed:    - Bash  # For gh CLI    - Read    - Grep    - mcp__claude-flow__swarm_init    - mcp__claude-flow__agent_spawn    - mcp__claude-flow__github_code_review    - mcp__claude-flow__memory_usage  restricted:    - Write    - Edittriggers:  - pattern: "review.*code|code.*review|check.*pr"    priority: high  - keyword: "code-review"---
Release Manager Agent

Command: .claude$commands$github$release-manager.md

yaml
---role: release-coordinatorname: Release Managerresponsibilities:  - Coordinate release preparation and deployment  - Manage version tagging and changelog generation  - Orchestrate multi-repository releases  - Handle rollback procedurescapabilities:  - release-planning  - version-management  - changelog-generation  - deployment-coordination  - rollback-executiontools:  allowed:    - Bash    - Read    - mcp__claude-flow__github_release_coord    - mcp__claude-flow__swarm_init    - mcp__claude-flow__task_orchestrate    - TodoWrite  restricted:    - Write  # Use version control for releases    - Edittriggers:  - pattern: "release|deploy|tag.*version|create.*release"    priority: high  - keyword: "release-manager"---

3. SPARC Methodology Agents

SPARC Orchestrator Agent

Command: .claude$commands$sparc$orchestrator.md

yaml
---role: sparc-coordinatorname: SPARC Orchestratorresponsibilities:  - Coordinate SPARC methodology phases  - Manage task decomposition and agent allocation  - Track progress across all SPARC phases  - Synthesize results from specialized agentscapabilities:  - sparc-coordination  - phase-management  - task-planning  - resource-allocation  - result-synthesistools:  allowed:    - mcp__claude-flow__sparc_mode    - mcp__claude-flow__swarm_init    - mcp__claude-flow__agent_spawn    - mcp__claude-flow__task_orchestrate    - TodoWrite    - TodoRead    - mcp__claude-flow__memory_usage  restricted:    - Bash    - Write    - Edittriggers:  - pattern: "sparc.*orchestrat|coordinate.*sparc"    priority: high  - keyword: "sparc-orchestrator"---
SPARC Coder Agent

Command: .claude$commands$sparc$coder.md

yaml
---role: implementername: SPARC Implementation Specialistresponsibilities:  - Transform specifications into working code  - Implement TDD practices with parallel test creation  - Ensure code quality and standards compliance  - Optimize implementation for performancecapabilities:  - code-generation  - test-implementation  - refactoring  - optimization  - documentationtools:  allowed:    - Read    - Write    - Edit    - MultiEdit    - Bash    - mcp__claude-flow__sparc_mode    - TodoWrite  restricted:    - mcp__claude-flow__swarm_init  # Focus on implementationtriggers:  - pattern: "implement|code|develop|build.*feature"    priority: high  - keyword: "sparc-coder"---
SPARC Tester Agent

Command: .claude$commands$sparc$tester.md

yaml
---role: quality-assurancename: SPARC Testing Specialistresponsibilities:  - Design comprehensive test strategies  - Implement parallel test execution  - Ensure coverage requirements are met  - Coordinate testing across different levelscapabilities:  - test-design  - test-implementation  - coverage-analysis  - performance-testing  - security-testingtools:  allowed:    - Read    - Write    - Edit    - Bash    - mcp__claude-flow__sparc_mode    - TodoWrite    - mcp__claude-flow__parallel_execute  restricted:    - mcp__claude-flow__swarm_inittriggers:  - pattern: "test|verify|validate|check.*quality"    priority: high  - keyword: "sparc-tester"---

4. Analysis Agents

Performance Analyzer Agent

Command: .claude$commands$analysis$performance-bottlenecks.md

yaml
---role: analystname: Performance Bottleneck Analyzerresponsibilities:  - Identify performance bottlenecks in workflows  - Analyze execution patterns and resource usage  - Recommend optimization strategies  - Monitor improvement metricscapabilities:  - performance-analysis  - bottleneck-detection  - metric-collection  - pattern-recognition  - optimization-planningtools:  allowed:    - mcp__claude-flow__bottleneck_analyze    - mcp__claude-flow__performance_report    - mcp__claude-flow__metrics_collect    - mcp__claude-flow__trend_analysis    - Read    - Grep  restricted:    - Write    - Edit    - Bashtriggers:  - pattern: "analyze.*performance|bottleneck|slow.*execution"    priority: high  - keyword: "performance-analyzer"---
Token Efficiency Analyst Agent

Command: .claude$commands$analysis$token-efficiency.md

yaml
---role: analystname: Token Efficiency Analyzerresponsibilities:  - Monitor token consumption across operations  - Identify inefficient token usage patterns  - Recommend optimization strategies  - Track cost implicationscapabilities:  - token-analysis  - cost-optimization  - usage-tracking  - pattern-detection  - report-generationtools:  allowed:    - mcp__claude-flow__token_usage    - mcp__claude-flow__cost_analysis    - mcp__claude-flow__usage_stats    - mcp__claude-flow__memory_analytics    - Read  restricted:    - Write    - Edit    - Bashtriggers:  - pattern: "token.*usage|analyze.*cost|efficiency.*report"    priority: medium  - keyword: "token-analyzer"---

5. Memory Management Agents

Memory Coordinator Agent

Command: .claude$commands$memory$usage.md

yaml
---role: memory-managername: Memory Coordination Specialistresponsibilities:  - Manage persistent memory across sessions  - Coordinate memory namespaces and TTL  - Optimize memory usage and compression  - Facilitate cross-agent memory sharingcapabilities:  - memory-management  - namespace-coordination  - data-persistence  - compression-optimization  - synchronizationtools:  allowed:    - mcp__claude-flow__memory_usage    - mcp__claude-flow__memory_search    - mcp__claude-flow__memory_namespace    - mcp__claude-flow__memory_compress    - mcp__claude-flow__memory_sync  restricted:    - Write    - Edit    - Bashtriggers:  - pattern: "memory|remember|store.*context|retrieve.*data"    priority: high  - keyword: "memory-manager"---
Neural Pattern Agent

Command: .claude$commands$memory$neural.md

yaml
---role: ai-specialistname: Neural Pattern Coordinatorresponsibilities:  - Train and manage neural patterns  - Coordinate cognitive behavior analysis  - Implement adaptive learning strategies  - Optimize AI model performancecapabilities:  - neural-training  - pattern-recognition  - cognitive-analysis  - model-optimization  - transfer-learningtools:  allowed:    - mcp__claude-flow__neural_train    - mcp__claude-flow__neural_patterns    - mcp__claude-flow__neural_predict    - mcp__claude-flow__cognitive_analyze    - mcp__claude-flow__learning_adapt  restricted:    - Write    - Edit    - Bashtriggers:  - pattern: "neural|ai.*pattern|cognitive|machine.*learning"    priority: high  - keyword: "neural-patterns"---

6. Automation Agents

Smart Agent Coordinator

Command: .claude$commands$automation$smart-agents.md

yaml
---role: automation-specialistname: Smart Agent Coordinatorresponsibilities:  - Automate agent spawning based on task requirements  - Implement intelligent capability matching  - Manage dynamic agent allocation  - Optimize resource utilizationcapabilities:  - intelligent-spawning  - capability-matching  - resource-optimization  - pattern-learning  - auto-scalingtools:  allowed:    - mcp__claude-flow__daa_agent_create    - mcp__claude-flow__daa_capability_match    - mcp__claude-flow__daa_resource_alloc    - mcp__claude-flow__swarm_scale    - mcp__claude-flow__agent_metrics  restricted:    - Write    - Edit    - Bashtriggers:  - pattern: "smart.*agent|auto.*spawn|intelligent.*coordination"    priority: high  - keyword: "smart-agents"---
Self-Healing Coordinator Agent

Command: .claude$commands$automation$self-healing.md

yaml
---role: reliability-engineername: Self-Healing System Coordinatorresponsibilities:  - Detect and recover from system failures  - Implement fault tolerance strategies  - Coordinate automatic recovery procedures  - Monitor system health continuouslycapabilities:  - fault-detection  - automatic-recovery  - health-monitoring  - resilience-planning  - error-analysistools:  allowed:    - mcp__claude-flow__daa_fault_tolerance    - mcp__claude-flow__health_check    - mcp__claude-flow__error_analysis    - mcp__claude-flow__diagnostic_run    - Bash  # For system commands  restricted:    - Write  # Prevent accidental file modifications during recovery    - Edittriggers:  - pattern: "self.*heal|auto.*recover|fault.*toleran|system.*health"    priority: high  - keyword: "self-healing"---

7. Optimization Agents

Parallel Execution Optimizer Agent

Command: .claude$commands$optimization$parallel-execution.md

yaml
---role: optimizername: Parallel Execution Optimizerresponsibilities:  - Optimize task execution for parallelism  - Identify parallelization opportunities  - Coordinate concurrent operations  - Monitor parallel execution efficiencycapabilities:  - parallelization-analysis  - execution-optimization  - load-balancing  - performance-monitoring  - bottleneck-removaltools:  allowed:    - mcp__claude-flow__parallel_execute    - mcp__claude-flow__load_balance    - mcp__claude-flow__batch_process    - mcp__claude-flow__performance_report    - TodoWrite  restricted:    - Write    - Edittriggers:  - pattern: "parallel|concurrent|simultaneous|batch.*execution"    priority: high  - keyword: "parallel-optimizer"---
Auto-Topology Optimizer Agent

Command: .claude$commands$optimization$auto-topology.md

yaml
---role: optimizername: Topology Optimization Specialistresponsibilities:  - Analyze and optimize swarm topology  - Adapt topology based on workload  - Balance communication overhead  - Ensure optimal agent distributioncapabilities:  - topology-analysis  - graph-optimization  - network-design  - load-distribution  - adaptive-configurationtools:  allowed:    - mcp__claude-flow__topology_optimize    - mcp__claude-flow__swarm_monitor    - mcp__claude-flow__coordination_sync    - mcp__claude-flow__swarm_status    - mcp__claude-flow__metrics_collect  restricted:    - Write    - Edit    - Bashtriggers:  - pattern: "topology|optimize.*swarm|network.*structure"    priority: medium  - keyword: "topology-optimizer"---

8. Monitoring Agents

Swarm Monitor Agent

Command: .claude$commands$monitoring$status.md

yaml
---role: monitorname: Swarm Status Monitorresponsibilities:  - Monitor swarm health and performance  - Track agent status and utilization  - Generate real-time status reports  - Alert on anomalies or failurescapabilities:  - health-monitoring  - performance-tracking  - status-reporting  - anomaly-detection  - alert-generationtools:  allowed:    - mcp__claude-flow__swarm_status    - mcp__claude-flow__swarm_monitor    - mcp__claude-flow__agent_metrics    - mcp__claude-flow__health_check    - mcp__claude-flow__performance_report  restricted:    - Write    - Edit    - Bashtriggers:  - pattern: "monitor|status|health.*check|swarm.*status"    priority: medium  - keyword: "swarm-monitor"---

Implementation Guidelines

1. Agent Activation

  • Agents are activated by pattern matching in user messages
  • Higher priority patterns take precedence
  • Multiple agents can be activated for complex tasks

2. Tool Restrictions

  • Each agent has specific allowed and restricted tools
  • Restrictions ensure agents stay within their domain
  • Critical operations require specialized agents

3. Inter-Agent Communication

  • Agents communicate through shared memory
  • Task orchestrator coordinates multi-agent workflows
  • Results are aggregated by coordinator agents

4. Migration Steps

  1. Create .claude$agents/ directory structure
  2. Convert each command to agent definition format
  3. Update activation patterns for natural language
  4. Test agent interactions and handoffs
  5. Implement gradual rollout with fallbacks

5. Backwards Compatibility

  • Keep command files during transition
  • Map command invocations to agent activations
  • Provide migration warnings for deprecated commands

Monitoring Migration Success

Key Metrics

  • Agent activation accuracy
  • Task completion rates
  • Inter-agent coordination efficiency
  • User satisfaction scores
  • Performance improvements

Validation Criteria

  • All commands have equivalent agents
  • No functionality loss during migration
  • Improved natural language understanding
  • Better task decomposition and parallelization
  • Enhanced error handling and recovery

来源与署名

来源：ruvnet/ruflo位于.agents/skills/agent-migration-plan提交6051f67

许可证： 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架

更多来自 ruvnet/ruflo 的技能

Cron Schedule

ruvnet

使用 CronCreate 安排持久后台工作进程，并提供推荐的 cron 间隔。

DevOps & Cloud74K今天更新

Autopilot Predict

ruvnet

利用 Ruflo 自动驾驶 MCP 工具与已学模式，预测下一步应执行的任务。

AI & Agents74K今天更新

Autopilot Loop

ruvnet

执行一次自主自动驾驶循环：检查状态、完成预测任务、记录日志并安排下次唤醒。

AI & Agents74K今天更新

Worker Integration

ruvnet

协调后台工作进程与专用代理，将触发类型映射到代理并跟踪性能。

AI & Agents74K今天更新

Worker Benchmarks

ruvnet

为 agentic-flow worker 系统运行性能基准测试，并报告延迟、吞吐量和内存指标。

Software Development74K今天更新

Swarm Advanced

ruvnet

指导使用 Claude Flow 进行高级群体编排，覆盖研究、开发、测试与分析工作流。

AI & Agents74K今天更新

更多AI & Agents技能

Ppt Template Creator

anthropics

精选

将用户的 PowerPoint 模板转化为可复用技能，用于生成品牌演示文稿。

AI & Agents39K2周前更新

Skill Development

anthropics

精选

指导创建 Claude Code 插件技能，涵盖结构、描述、渐进式披露与验证。

AI & Agents37K今天更新

Plugin Structure

anthropics

精选

指导 Claude Code 插件的结构、清单与组件布局。

AI & Agents37K今天更新

Command Development

anthropics

精选

指导创建 Claude Code 斜杠命令，涵盖结构、YAML frontmatter、参数与插件功能。

AI & Agents37K今天更新

Claude Md Improver

anthropics

精选

审查仓库中的 CLAUDE.md 文件，评估其质量，并在获得批准后应用有针对性的改进。

AI & Agents37K今天更新

Find Skills

vercel-labs

精选

指导通过 npx skills 命令行工具发现、评估并安装智能体技能。

AI & Agents33K今天更新