Agent Multi Repo Swarm Skill for Claude

by majiayu000

Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm

3k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

532

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/majiayu000/claude-skill-registry --skill agent-multi-repo-swarm

What comes with it

819 bytes besides the instruction

metadata.json

The instruction itself

48 sections, as written by the author

name: multi-repo-swarm

description: Cross-repository swarm orchestration for organization-wide automation and intelligent collaboration

type: coordination

color: "#FF6B35"

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_repo_analyze
mcp__claude-flow__github_pr_manage
mcp__claude-flow__github_sync_coord
mcp__claude-flow__github_metrics

hooks:

pre:

"gh auth status || (echo 'GitHub CLI not authenticated' && exit 1)"
"git status --porcelain || echo 'Not in git repository'"
"gh repo list --limit 1 >$dev$null || (echo 'No repo access' && exit 1)"

post:

"gh pr list --state open --limit 5 | grep -q . && echo 'Active PRs found'"
"git log --oneline -5 | head -3"
"gh repo view --json name,description,topics"

Multi-Repo Swarm - Cross-Repository Swarm Orchestration

Overview

Coordinate AI swarms across multiple repositories, enabling organization-wide automation and intelligent cross-project collaboration.

Core Features

1. Cross-Repo Initialization

# Initialize multi-repo swarm with gh CLI
# List organization repositories
REPOS=$(gh repo list org --limit 100 --json name,description,languages \
  --jq '.[] | select(.name | test("frontend|backend|shared"))')

# Get repository details
REPO_DETAILS=$(echo "$REPOS" | jq -r '.name' | while read -r repo; do
  gh api repos$org/$repo --jq '{name, default_branch, languages, topics}'
done | jq -s '.')

# Initialize swarm with repository context
npx ruv-swarm github multi-repo-init \
  --repo-details "$REPO_DETAILS" \
  --repos "org$frontend,org$backend,org$shared" \
  --topology hierarchical \
  --shared-memory \
  --sync-strategy eventual

2. Repository Discovery

# Auto-discover related repositories with gh CLI
# Search organization repositories
REPOS=$(gh repo list my-organization --limit 100 \
  --json name,description,languages,topics \
  --jq '.[] | select(.languages | keys | contains(["TypeScript"]))')

# Analyze repository dependencies
DEPS=$(echo "$REPOS" | jq -r '.name' | while read -r repo; do
  # Get package.json if it exists
  if gh api repos$my-organization/$repo$contents$package.json --jq '.content' 2>$dev$null; then
    gh api repos$my-organization/$repo$contents$package.json \
      --jq '.content' | base64 -d | jq '{name, dependencies, devDependencies}'
  fi
done | jq -s '.')

# Discover and analyze
npx ruv-swarm github discover-repos \
  --repos "$REPOS" \
  --dependencies "$DEPS" \
  --analyze-dependencies \
  --suggest-swarm-topology

3. Synchronized Operations

# Execute synchronized changes across repos with gh CLI
# Get matching repositories
MATCHING_REPOS=$(gh repo list org --limit 100 --json name \
  --jq '.[] | select(.name | test("-service$")) | .name')

# Execute task and create PRs
echo "$MATCHING_REPOS" | while read -r repo; do
  # Clone repo
  gh repo clone org/$repo $tmp/$repo -- --depth=1
  
  # Execute task
  cd $tmp/$repo
  npx ruv-swarm github task-execute \
    --task "update-dependencies" \
    --repo "org/$repo"
  
  # Create PR if changes exist
  if [[ -n $(git status --porcelain) ]]; then
    git checkout -b update-dependencies-$(date +%Y%m%d)
    git add -A
    git commit -m "chore: Update dependencies"
    
    # Push and create PR
    git push origin HEAD
    PR_URL=$(gh pr create \
      --title "Update dependencies" \
      --body "Automated dependency update across services" \
      --label "dependencies,automated")
    
    echo "$PR_URL" >> $tmp$created-prs.txt
  fi
  cd -
done

# Link related PRs
PR_URLS=$(cat $tmp$created-prs.txt)
npx ruv-swarm github link-prs --urls "$PR_URLS"

Configuration

Multi-Repo Config File

# .swarm$multi-repo.yml
version: 1
organization: my-org
repositories:
  - name: frontend
    url: github.com$my-org$frontend
    role: ui
    agents: [coder, designer, tester]
    
  - name: backend
    url: github.com$my-org$backend
    role: api
    agents: [architect, coder, tester]
    
  - name: shared
    url: github.com$my-org$shared
    role: library
    agents: [analyst, coder]

coordination:
  topology: hierarchical
  communication: webhook
  memory: redis:/$shared-memory
  
dependencies:
  - from: frontend
    to: [backend, shared]
  - from: backend
    to: [shared]

Repository Roles

// Define repository roles and responsibilities
{
  "roles": {
    "ui": {
      "responsibilities": ["user-interface", "ux", "accessibility"],
      "default-agents": ["designer", "coder", "tester"]
    },
    "api": {
      "responsibilities": ["endpoints", "business-logic", "data"],
      "default-agents": ["architect", "coder", "security"]
    },
    "library": {
      "responsibilities": ["shared-code", "utilities", "types"],
      "default-agents": ["analyst", "coder", "documenter"]
    }
  }
}

Orchestration Commands

Dependency Management

# Update dependencies across all repos with gh CLI
# Create tracking issue first
TRACKING_ISSUE=$(gh issue create \
  --title "Dependency Update: [email protected]" \
  --body "Tracking issue for updating TypeScript across all repositories" \
  --label "dependencies,tracking" \
  --json number -q .number)

# Get all repos with TypeScript
TS_REPOS=$(gh repo list org --limit 100 --json name | jq -r '.[].name' | \
  while read -r repo; do
    if gh api repos$org/$repo$contents$package.json 2>$dev$null | \
       jq -r '.content' | base64 -d | grep -q '"typescript"'; then
      echo "$repo"
    fi
  done)

# Update each repository
echo "$TS_REPOS" | while read -r repo; do
  # Clone and update
  gh repo clone org/$repo $tmp/$repo -- --depth=1
  cd $tmp/$repo
  
  # Update dependency
  npm install --save-dev [email protected]
  
  # Test changes
  if npm test; then
    # Create PR
    git checkout -b update-typescript-5
    git add package.json package-lock.json
    git commit -m "chore: Update TypeScript to 5.0.0

Part of #$TRACKING_ISSUE"
    
    git push origin HEAD
    gh pr create \
      --title "Update TypeScript to 5.0.0" \
      --body "Updates TypeScript to version 5.0.0\n\nTracking: #$TRACKING_ISSUE" \
      --label "dependencies"
  else
    # Report failure
    gh issue comment $TRACKING_ISSUE \
      --body "❌ Failed to update $repo - tests failing"
  fi
  cd -
done

Refactoring Operations

# Coordinate large-scale refactoring
npx ruv-swarm github multi-repo-refactor \
  --pattern "rename:OldAPI->NewAPI" \
  --analyze-impact \
  --create-migration-guide \
  --staged-rollout

Security Updates

# Coordinate security patches
npx ruv-swarm github multi-repo-security \
  --scan-all \
  --patch-vulnerabilities \
  --verify-fixes \
  --compliance-report

Communication Strategies

1. Webhook-Based Coordination

// webhook-coordinator.js
const { MultiRepoSwarm } = require('ruv-swarm');

const swarm = new MultiRepoSwarm({
  webhook: {
    url: 'https:/$swarm-coordinator.example.com',
    secret: process.env.WEBHOOK_SECRET
  }
});

// Handle cross-repo events
swarm.on('repo:update', async (event) => {
  await swarm.propagate(event, {
    to: event.dependencies,
    strategy: 'eventual-consistency'
  });
});

2. GraphQL Federation

# Federated schema for multi-repo queries
type Repository @key(fields: "id") {
  id: ID!
  name: String!
  swarmStatus: SwarmStatus!
  dependencies: [Repository!]!
  agents: [Agent!]!
}

type SwarmStatus {
  active: Boolean!
  topology: Topology!
  tasks: [Task!]!
  memory: JSON!
}

3. Event Streaming

# Kafka configuration for real-time coordination
kafka:
  brokers: ['kafka1:9092', 'kafka2:9092']
  topics:
    swarm-events: 
      partitions: 10
      replication: 3
    swarm-memory:
      partitions: 5
      replication: 3

Advanced Features

1. Distributed Task Queue

# Create distributed task queue
npx ruv-swarm github multi-repo-queue \
  --backend redis \
  --workers 10 \
  --priority-routing \
  --dead-letter-queue

2. Cross-Repo Testing

# Run integration tests across repos
npx ruv-swarm github multi-repo-test \
  --setup-test-env \
  --link-services \
  --run-e2e \
  --tear-down

3. Monorepo Migration

# Assist in monorepo migration
npx ruv-swarm github to-monorepo \
  --analyze-repos \
  --suggest-structure \
  --preserve-history \
  --create-migration-prs

Monitoring & Visualization

Multi-Repo Dashboard

# Launch monitoring dashboard
npx ruv-swarm github multi-repo-dashboard \
  --port 3000 \
  --metrics "agent-activity,task-progress,memory-usage" \
  --real-time

Dependency Graph

# Visualize repo dependencies
npx ruv-swarm github dep-graph \
  --format mermaid \
  --include-agents \
  --show-data-flow

Health Monitoring

# Monitor swarm health across repos
npx ruv-swarm github health-check \
  --repos "org/*" \
  --check "connectivity,memory,agents" \
  --alert-on-issues

Synchronization Patterns

1. Eventually Consistent

// Eventual consistency for non-critical updates
{
  "sync": {
    "strategy": "eventual",
    "max-lag": "5m",
    "retry": {
      "attempts": 3,
      "backoff": "exponential"
    }
  }
}

2. Strong Consistency

// Strong consistency for critical operations
{
  "sync": {
    "strategy": "strong",
    "consensus": "raft",
    "quorum": 0.51,
    "timeout": "30s"
  }
}

3. Hybrid Approach

// Mix of consistency levels
{
  "sync": {
    "default": "eventual",
    "overrides": {
      "security-updates": "strong",
      "dependency-updates": "strong",
      "documentation": "eventual"
    }
  }
}

Use Cases

1. Microservices Coordination

# Coordinate microservices development
npx ruv-swarm github microservices \
  --services "auth,users,orders,payments" \
  --ensure-compatibility \
  --sync-contracts \
  --integration-tests

2. Library Updates

# Update shared library across consumers
npx ruv-swarm github lib-update \
  --library "org$shared-lib" \
  --version "2.0.0" \
  --find-consumers \
  --update-imports \
  --run-tests

3. Organization-Wide Changes

# Apply org-wide policy changes
npx ruv-swarm github org-policy \
  --policy "add-security-headers" \
  --repos "org/*" \
  --validate-compliance \
  --create-reports

Best Practices

1. Repository Organization

Clear repository roles and boundaries
Consistent naming conventions
Documented dependencies
Shared configuration standards

2. Communication

Use appropriate sync strategies
Implement circuit breakers
Monitor latency and failures
Clear error propagation

3. Security

Secure cross-repo authentication
Encrypted communication channels
Audit trail for all operations
Principle of least privilege

Performance Optimization

Caching Strategy

# Implement cross-repo caching
npx ruv-swarm github cache-strategy \
  --analyze-patterns \
  --suggest-cache-layers \
  --implement-invalidation

Parallel Execution

# Optimize parallel operations
npx ruv-swarm github parallel-optimize \
  --analyze-dependencies \
  --identify-parallelizable \
  --execute-optimal

Resource Pooling

# Pool resources across repos
npx ruv-swarm github resource-pool \
  --share-agents \
  --distribute-load \
  --monitor-usage

Troubleshooting

Connectivity Issues

# Diagnose connectivity problems
npx ruv-swarm github diagnose-connectivity \
  --test-all-repos \
  --check-permissions \
  --verify-webhooks

Memory Synchronization

# Debug memory sync issues
npx ruv-swarm github debug-memory \
  --check-consistency \
  --identify-conflicts \
  --repair-state

Performance Bottlenecks

# Identify performance issues
npx ruv-swarm github perf-analysis \
  --profile-operations \
  --identify-bottlenecks \
  --suggest-optimizations

Examples

Full-Stack Application Update

# Update full-stack application
npx ruv-swarm github fullstack-update \
  --frontend "org$web-app" \
  --backend "org$api-server" \
  --database "org$db-migrations" \
  --coordinate-deployment

Cross-Team Collaboration

# Facilitate cross-team work
npx ruv-swarm github cross-team \
  --teams "frontend,backend,devops" \
  --task "implement-feature-x" \
  --assign-by-expertise \
  --track-progress

See also: swarm-pr.md, project-board-sync.md

Other skills for the same job

different authors, same section of the catalogue

Skill Creator

by anthropics

vendor ×10

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Replace with description of the skill and when Claude should use it.

35 tokens

Dispatching Parallel Agents

by ZhanlinCui

×5

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

26k tokens scripts

How to use it

Copy the folder

Take majiayu000/agent-multi-repo-swarm from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference npm, npx. Without those the skill loads but fails at the first command.