orchestrating-swarms
Claude Code Swarm Orchestration
Master multi-agent orchestration using Claude Code's TeamCreate, SendMessage, TeamDelete, and Agent tools.
This skill is a facade that routes to 4 specialist skills. Load whichever you need.
Specialist Skills
Core Concepts
Skill(skill: "swarm-primitives")
What teams, teammates, tasks, and inboxes are. File layouts, team config structure, lifecycle diagrams, message flow sequences.
Spawning Agents
Skill(skill: "swarm-spawning")
How to create agents -- subagent vs teammate decision, built-in agent types (Explore, Plan, general-purpose, Bash, etc.), plugin agent types, spawn backends (in-process, tmux, iterm2), environment variables.
API Reference
Skill(skill: "swarm-operations")
Tool signatures and message schemas -- TeamCreate, SendMessage (direct, broadcast, shutdown, plan approval), TeamDelete, Agent tool parameters. Error handling, graceful shutdown sequence, crashed teammate recovery, debugging.
Patterns and Recipes
Skill(skill: "swarm-patterns")
6 orchestration patterns (parallel specialists, pipeline, swarm, research+implement, plan approval, coordinated refactoring), 3 complete workflows, best practices, quick reference.
Quick Start
flowchart TD
Start([What do you need?]) --> Q1{Your goal?}
Q1 -->|Understand how swarms work| P[swarm-primitives]
Q1 -->|Choose agent types or backends| S[swarm-spawning]
Q1 -->|Look up tool API or message format| O[swarm-operations]
Q1 -->|Build a workflow from a recipe| R[swarm-patterns]
Q1 -->|Full reference on everything| All[Load all 4 skills]
Minimal Example
// 1. Create team
TeamCreate({ team_name: "my-team" })
// 2. Create tasks
TaskCreate({ subject: "Review auth", description: "Review auth module", activeForm: "Reviewing..." })
TaskCreate({ subject: "Review API", description: "Review API endpoints", activeForm: "Reviewing..." })
// 3. Spawn teammates
Agent({ team_name: "my-team", name: "reviewer-1", subagent_type: "general-purpose", prompt: "Claim task #1, review it, send findings to team-lead.", run_in_background: true })
Agent({ team_name: "my-team", name: "reviewer-2", subagent_type: "general-purpose", prompt: "Claim task #2, review it, send findings to team-lead.", run_in_background: true })
// 4. Collect results (messages arrive automatically)
// 5. Shutdown and cleanup
SendMessage({ type: "shutdown_request", recipient: "reviewer-1", content: "Done" })
SendMessage({ type: "shutdown_request", recipient: "reviewer-2", content: "Done" })
// Wait for approvals...
TeamDelete()
SOURCE: Claude Code v2.1.45 -- verified 2026-02-18
More from jamie-bitflight/claude_skills
perl-lint
This skill should be used when the user asks to lint Perl code, run perlcritic, check Perl style, format Perl code, run perltidy, or mentions Perl Critic policies, code formatting, or style checking.
24brainstorming-skill
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or when users request help with ideation, marketing, and strategic planning. Explores user intent, requirements, and design before implementation using 30+ research-validated prompt patterns.
11design-anti-patterns
Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents "Codex UI" — the generic AI aesthetic of soft gradients, floating panels, oversized rounded corners, glassmorphism, hero sections in dashboards, and decorative copy. Applies constraints from Linear/Raycast/Stripe/GitHub design philosophy: functional, honest, human-designed interfaces. Triggers on: UI generation, dashboard building, frontend component creation, CSS styling, landing page design, or any task producing visual interface code.
7python3-review
Comprehensive Python code review checking patterns, types, security, and performance. Use when reviewing Python code for quality issues, when auditing code before merge, or when assessing technical debt in a Python codebase.
7hooks-guide
Cross-platform hooks reference for AI coding assistants — Claude Code, GitHub Copilot, Cursor, Windsurf, Amp. Covers hook authoring in Node.js CJS and Python, per-platform event schemas, inline-agent hooks and MCP in agent frontmatter, common JSON I/O, exit codes, best practices, and a fetch script to refresh docs from official sources. Use when writing, reviewing, or debugging hooks for any AI assistant.
7agent-creator
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following Anthropic best practices (v2.1.63+).
6