script-driven-skill

Coordinate multi-step AI workflows with a Python orchestrator and phase files.

5|12|Updated Nov 24, 2025

Search Tags:#automation #Python #orchestrator #phases #state-machine #workflow-management #AI-workflow

Ready to run

npx skills add https://github.com/cbgbt/bottlerocket-forest --skill script-driven-skill

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: script-driven-skill
Source: https://github.com/cbgbt/bottlerocket-forest/tree/main/skills/script-driven-skill
Command: npx skills add https://github.com/cbgbt/bottlerocket-forest --skill script-driven-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build reliable multi-step skills by coordinating a simple orchestrator with a state machine and phase files.

Core Features & Use Cases

Orchestrator loops: A minimal control loop that spawn subagents without embedding phase logic.
Phase files: Self-contained instructions per phase that travel with subagents.
Progress tracking & gates: Uses progress.json and gating to prevent skipping steps; supports resumable runs.

Quick Start

Initialize a workspace and run the state-machine orchestrator:

Create a workspace directory under planning, e.g., mkdir -p planning/workspace
Run the orchestrator: python3 skills/script-driven-skill/next-step.py planning/workspace

Frequently Asked Questions about script-driven-skill

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

FAQPage Schema

How do I orchestrate multi-phase AI workflows reliably?▼

Multi-phase AI workflows are orchestrated using a Python-based state machine that coordinates subagents via self-contained phase files, ensuring deterministic and auditable execution. The orchestrator outputs a progress.json file to track state and enable resumable runs.

How do I prevent an AI workflow from skipping required steps?▼

To prevent skipping steps in an AI workflow, the orchestrator uses progress tracking and gating mechanisms. It enforces phase-by-phase execution by evaluating a progress.json file, ensuring all required phases complete sequentially before advancing.

Can I resume a complex AI task from where it left off?▼

Yes, you can resume complex AI tasks because the orchestrator supports resumable runs. It records execution state in progress.json and uses phase artifacts, allowing the state machine to pick up accurately from the last completed phase.

What is the best way to structure multi-step AI task instructions?▼

The best way to structure multi-step AI tasks is using self-contained phase markdown files under a phases/ directory. This approach separates phase logic from the orchestrator loop, allowing subagents to execute instructions deterministically.

Do I need Python to run an AI workflow state machine?▼

Yes, you need Python to run this AI workflow state machine. The orchestrator relies on a Python script called next-step.py, which manages the control loop, spawns subagents, and updates the progress.json file.

How do I start an AI workflow orchestrator from a workspace directory?▼

You start the AI workflow orchestrator by creating a workspace directory under planning, then executing the next-step.py script with that workspace path. This initializes the state machine and generates progress tracking artifacts.