Agent skill · operations · aiskillstore
cascade-orchestrator
Creates sophisticated workflow cascades coordinating multiple micro-skills with sequential pipelines, parallel execution, conditional branching, and Codex sandbox iteration. Enhanced with multi-model routing (Gemini/Codex), ruv-swarm coordination, memory persistence, and audit-pipeline patterns for production workflows.
Why this skill is useful
Adds complex orchestration capabilities with executable scripts for multi-model routing, error handling, and Codex sandbox iteration that extend the AI's workflow management abilities.
What it needs
Requires github-cli installed locally. About 5k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Cascade Orchestrator (Enhanced) Overview Manages workflows (cascades) that coordinate multiple micro-skills into cohesive processes. This enhanced version integrates Codex sandbox iteration, multi-model routing, ruv-swarm coordination, and memory persistence across stages. Philosophy: Composable Excellence Complex capabilities emerge from composing simple, well-defined components. Enhanced Capabilities: Codex Sandbox Iteration: Auto-fix failures in isolated environment (from audit-pipeline) Multi-Model Routing: Use Gemini/Codex based on stage requirements Swarm Coordination: Parallel execution via ruv-swarm MCP Memory Persistence: Maintain context across stages GitHub Integration: CI/CD pipeline automation Key Principles: 1. Separation of concerns (micro-skills execute, cascades coordinate) 2. Reusability through composition 3. Flexible orchestration patterns 4. Declarative workflow definition 5. Intelligent model selection Cascade Architecture (Enhanced) Definition Layer Extended Stage Types: Enhanced Data Flow: Advanced Error Handling: Execution Engine (Enhanced) Stage Scheduling with AI Selection: Codex Sandbox Iteration Loop: Multi-Model Routing: Enhanced Cascade Patterns Pattern 1: Linear Pipeline with Multi-Model Pattern 2: Parallel Fan-Out with Swarm Pattern 3: Codex Sandbox Iteration Pattern 4: Conditional with Model Switching Pattern 5: Iterative with Memory Creating Enhanced Cascades Step 1: Define with AI Considerations Identify Model Requirements: Step 2: Design with Swarm Parallelism When to Use Swarm: Multiple independent tasks Resource-intensive operations Need load balancing Want fault tolerance Swarm Configuration: Step 3: Add Codex Iteration for Quality Pattern from audit-pipeline: Step 4: Enable Memory Persistence Shared Memory Across Stages: Enhanced Cascade Definition Format Real-World Enhanced Cascades Example 1: Complete Development Workflow Example 2: Legacy Modernization Example 3: Bug Fix with RCA Integration Points With Micro-Skills Execut …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/cascade-orchestrator