super-orchestrator

Orchestrate multi-step AI engineering workflows with human-gated run manifests.

Updated May 20, 2026
One-click install
npx skills add https://github.com/samuelcastro/skills --skill super-orchestrator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: super-orchestrator
Source: https://github.com/samuelcastro/skills/tree/main/super-orchestrator
Command: npx skills add https://github.com/samuelcastro/skills --skill super-orchestrator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

super-orchestrator coordinates multiple specialized AI engineering workflows into a single looped run, so builds, QA, visual polish, and review can execute in the right order with explicit stop and human-gate controls.

Core Features & Use Cases

  • Preset-driven sequencing: Chooses the best workflow chain (e.g., Build Queue, QA → UX, Review Loop, Release Ready) based on what the user asks.
  • Loop policy and halt gates: Continues until each step is “done,” and stops when safety, lack of progress, merge conflicts, or unreliable verification is detected.
  • Provider-agnostic headless worker execution: Runs worker steps using a configurable headless coding-agent backend while keeping the orchestration contract stable.
  • Run manifests for auditability: Writes a resumable run log capturing inputs, inferred preset, sequence, artifacts, and final status.

Quick Start

Run a coordinated release workflow by telling your agent: "Use super-orchestrator to make this project release-ready with human confirmation for risky actions."

Frequently Asked Questions about super-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate multi-step AI engineering workflows safely?▼

Multi-step AI engineering workflows can be orchestrated by chaining build, QA, UX polish, and review tasks into a coordinated loop with explicit stop and human-gate controls for safe execution.

What is the best way to automate release readiness and PR validation?▼

Automating release readiness involves running a coordinated workflow loop that applies preset-driven sequencing to validate PRs, execute QA coverage, and confirm merge readiness through resumable run manifests.

Can I run Playwright QA coverage and visual-diff UX iterations in one loop?▼

Yes, you can run Playwright-based BFS QA coverage and visual-diff UX iterations sequentially within a single orchestrated loop, stopping automatically when safety issues or lack of progress are detected.

How do GitHub Project board-driven build queues work with workflow orchestration?▼

GitHub Project board-driven build queues are orchestrated by dispatching provider-agnostic headless workers to execute build tasks in sequence, while maintaining a resumable run log for auditability.

When should I use halt gates in agent loop automation?▼

Halt gates should be used to stop agent loops automatically when merge conflicts, unsafe actions, unreliable verification, or lack of progress are detected, requiring human confirmation before proceeding.

Do I need a specific coding agent backend to run orchestrated engineering loops?▼

No, orchestrated engineering loops use a provider-agnostic headless worker dispatch system, allowing you to configure your preferred coding-agent backend while keeping the orchestration contract stable.