macroflow-network

Orchestrate MacroFlow as a flow network for dynamic AI orchestration.

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 10, 2026⬇️1downloads

When & Why to Use This Skill

The MacroFlow Network skill provides a sophisticated framework for dynamic AI orchestration by modeling complex tasks as a flow network. It utilizes graph-based logic and the Ford-Fulkerson algorithm to optimize task distribution, enabling efficient parallel execution and seamless coordination between multiple AI sub-skills for high-level problem solving.

Use Cases

  • Complex Software Engineering: Managing the end-to-end development lifecycle by orchestrating phases like requirement clarification, architectural planning, and code implementation in a structured flow.
  • Parallel Task Optimization: Accelerating research and analysis by running context-gathering (Clarify) and rule-setting (Constitution) nodes simultaneously before merging data for final synthesis.
  • Dynamic Workflow Management: Using flow network theory to identify the most efficient path for data through various AI modules, ensuring optimal resource allocation and reducing processing latency.
namemacroflow-network
descriptionOrchestrate MacroFlow as a flow network for dynamic AI orchestration.

MacroFlow Network Skill

Instructions

  1. Load graph from graph.json (nodes: Constitution, Clarify, Specify, Plan, Tasks, Implement; edges with capacities).
  2. Simulate max-flow using Ford-Fulkerson for optimization.
  3. Traverse: Parallel start Constitution/Clarify, merge at Plan, etc.
  4. Invoke sub-skills for each node with flow data.
  5. Output: Final result at sink.

Examples

  • Input: User query for code gen.
  • Output: Orchestrated flow through phases.

Learned Patterns

  • Constitution and Clarify run in parallel for speed.
  • Grok X-insights enhance Clarify with real-time data.