Agent Orchestration
Covers four major patterns: single-agent loops (ReAct, plan-and-execute), multi-agent coordination (supervisor routing, fan-out/fan-in), framework selection (CrewAI, AutoGen, OpenAI Agents SDK), and multi-scenario orchestration. The meat is in 10 separate rule files loaded on demand, which is smart for keeping context manageable. Use this when you're building autonomous agents that need to reason iteratively, coordinate multiple specialists in parallel, or evaluate which framework fits your team. The note about Claude Code's native /workflows feature is important: this skill handles foreground coordination of up to 8 agents with shared memory, while /workflows does background fan-out at larger scale. Reference-heavy with good decision tables on step limits and agent counts.
- skills.sh installs
- 1.4K
- GitHub stars
- 301
- last updated
- Aug 21, 2026
Install
$ npx -y skills add yonatangross/orchestkit --skill agent-orchestration --agent claude-codeInstalls into .claude/skills of the current project.
Files
Agent Orchestration
Comprehensive patterns for building and coordinating AI agents -- from single-agent reasoning loops to multi-agent systems and framework selection. Coordination and multi-scenario categories have individual rule files in rules/ loaded on-demand; loop and framework tutorials live upstream (see Upstream coverage), with house defaults in references/ork-delta.md.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/yonatangross/orchestkit
- Categories
- AI & Agent Building, Automation & Workflows
- First seen
- Jun 3, 2026
More from yonatangross/orchestkit
All 61- Domain Driven Design1.3K
- Memory755
- Security Patterns738
- Langgraph371
- Write Prd336
- Distributed Systems293
- Ascii Visualizer283
- Monitoring Observability269
- Vite Advanced265
- Quality Gates259
- Code Review Playbook254
- Python Backend249
- Accessibility245
- Memory Fabric243
- Multimodal Llm242
- Database Patterns238
- Architecture Patterns236
- Performance232
- Github Operations228
- Remember228
- Doctor227
- React Server Components Framework227
- Web Research Workflow227
- Explore224
Recommended
More AI & Agent Building
llm-contextbrave/brave-search-skillsUSE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. S1.3Kskills.sh installs
agent-uiinference-sh/skillsBatteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabi1.2Kskills.sh installs
agentic-jujutsuruvnet/rufloQuantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination1.2Kskills.sh installs
agent-supply-chaingithub/awesome-copilotVerify supply chain integrity for AI agent plugins, tools, and dependencies. Use this skill when: - Generating SHA-256 integrity manifests for agent plugins or 1.1Kskills.sh installsmcp-security-auditgithub/awesome-copilotAudit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: - Reviewing .mcp.json files for security risks - Checking MCP1.1Kskills.sh installs
agentic-gatewayalchemyplatform/skillsWire Alchemy into application code without an API key, using the x402 or MPP gateway with wallet-based auth (SIWE/SIWS) and per-request payments (USDC via x402,1.1Kskills.sh installs