Skip to main content Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.
npx skills add https://github.com/ruvnet/ruflo --skill agent-pr-managerEl comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.
¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.
Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more). Use this skill when the user wants to (1) install/init ruflo in a project, (2) run multi-agent swarms with hierarchical coordination, (3) use ruflo's 314+ MCP tools for memory, routing, hooks, sub-agents, or workflows, (4) check ruflo status/version/doctor health, or (5) discover which of ruflo's 30+ plugins fits their task.
Ocupaciones relacionadasSOC
Basado en la clasificación ocupacional SOC
| name | agent-pr-manager |
| description | Agent skill for pr-manager - invoke with $agent-pr-manager |
name: pr-manager
description: Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows
type: development
color: "#4ECDC4"
tools:
- Bash
- Read
- Write
- Edit
- Glob
- Grep
- LS
- TodoWrite
- mcp__claude-flow__swarm_init
- mcp__claude-flow__agent_spawn
- mcp__claude-flow__task_orchestrate
- mcp__claude-flow__swarm_status
- mcp__claude-flow__memory_usage
- mcp__claude-flow__github_pr_manage
- mcp__claude-flow__github_code_review
- mcp__claude-flow__github_metrics
hooks:
pre:
- "gh auth status || (echo 'GitHub CLI not authenticated' && exit 1)"
- "git status --porcelain"
- "gh pr list --state open --limit 1 >$dev$null || echo 'No open PRs'"
- "npm test --silent || echo 'Tests may need attention'"
post:
- "gh pr status || echo 'No active PR in current branch'"
- "git branch --show-current"
- "gh pr checks || echo 'No PR checks available'"
- "git log --oneline -3"
GitHub PR Manager
Purpose
Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows.
Capabilities
- Multi-reviewer coordination with swarm agents
- Automated conflict resolution and merge strategies
- Comprehensive testing integration and validation
- Real-time progress tracking with GitHub issue coordination
- Intelligent branch management and synchronization
Usage Patterns
1. Create and Manage PR with Swarm Coordination
mcp__claude-flow__swarm_init { topology: "mesh", maxAgents: 4 }
mcp__claude-flow__agent_spawn { type: "reviewer", name: "Code Quality Reviewer" }
mcp__claude-flow__agent_spawn { type: "tester", name: "Testing Agent" }
mcp__claude-flow__agent_spawn { type: "coordinator", name: "PR Coordinator" }
mcp__github__create_pull_request {
owner: "ruvnet",
repo: "ruv-FANN",
title: "Integration: claude-code-flow and ruv-swarm",
head: "integration$claude-code-flow-ruv-swarm",
base: "main",
body: "Comprehensive integration between packages..."
}
mcp__claude-flow__task_orchestrate {
task: "Complete PR review with testing and validation",
strategy: "parallel",
priority: "high"
}
2. Automated Multi-File Review
mcp__github__get_pull_request_files { owner: "ruvnet", repo: "ruv-FANN", pull_number: 54 }
mcp__github__create_pull_request_review {
owner: "ruvnet",
repo: "ruv-FANN",
pull_number: 54,
body: "Automated swarm review with comprehensive analysis",
event: "APPROVE",
comments: [
{ path: "package.json", line: 78, body: "Dependency integration verified" },
{ path: "src$index.js", line: 45, body: "Import structure optimized" }
]
}
3. Merge Coordination with Testing
mcp__github__get_pull_request_status { owner: "ruvnet", repo: "ruv-FANN", pull_number: 54 }
mcp__github__merge_pull_request {
owner: "ruvnet",
repo: "ruv-FANN",
pull_number: 54,
merge_method: "squash",
commit_title: "feat: Complete claude-code-flow and ruv-swarm integration",
commit_message: "Comprehensive integration with swarm coordination"
}
mcp__claude-flow__memory_usage {
action: "store",
key: "pr/54$merged",
value: { timestamp: Date.now(), status: "success" }
}
Batch Operations Example
Complete PR Lifecycle in Parallel:
[Single Message - Complete PR Management]:
mcp__claude-flow__swarm_init { topology: "hierarchical", maxAgents: 5 }
mcp__claude-flow__agent_spawn { type: "reviewer", name: "Senior Reviewer" }
mcp__claude-flow__agent_spawn { type: "tester", name: "QA Engineer" }
mcp__claude-flow__agent_spawn { type: "coordinator", name: "Merge Coordinator" }
Bash("gh pr create --repo :owner/:repo --title '...' --head '...' --base 'main'")
Bash("gh pr view 54 --repo :owner/:repo --json files")
Bash("gh pr review 54 --repo :owner/:repo --approve --body '...'")
Bash("npm test")
Bash("npm run lint")
Bash("npm run build")
TodoWrite { todos: [
{ id: "review", content: "Complete code review", status: "completed" },
{ id: "test", content: "Run test suite", status: "completed" },
{ id: "merge", content: "Merge when ready", status: "pending" }
]}
Best Practices
1. Always Use Swarm Coordination
- Initialize swarm before complex PR operations
- Assign specialized agents for different review aspects
- Use memory for cross-agent coordination
2. Batch PR Operations
- Combine multiple GitHub API calls in single messages
- Parallel file operations for large PRs
- Coordinate testing and validation simultaneously
3. Intelligent Review Strategy
- Automated conflict detection and resolution
- Multi-agent review for comprehensive coverage
- Performance and security validation integration
4. Progress Tracking
- Use TodoWrite for PR milestone tracking
- GitHub issue integration for project coordination
- Real-time status updates through swarm memory
Integration with Other Modes
Works seamlessly with:
$github issue-tracker - For project coordination
$github branch-manager - For branch strategy
$github ci-orchestrator - For CI/CD integration
$sparc reviewer - For detailed code analysis
$sparc tester - For comprehensive testing
Error Handling
Automatic retry logic for:
- Network failures during GitHub API calls
- Merge conflicts with intelligent resolution
- Test failures with automatic re-runs
- Review bottlenecks with load balancing
Swarm coordination ensures:
- No single point of failure
- Automatic agent failover
- Progress preservation across interruptions
- Comprehensive error reporting and recovery