skills.rest
ucirello
ucirelloCOMMUNITY
Explore all skills by this author →
GitHub

using-sgai

Manage Sgai workspaces and sessions via HTTP API and MCP interface.

2|Updated Jan 27, 2026
Search Tags:#automation#ai#orchestration#workspace management#session control#sgai#software factory
One-click install
npx skills add https://github.com/ucirello/sgai --skill using-sgai-ucirello
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-sgai
Source: https://github.com/ucirello/sgai/tree/main/docs/sgai-skills/using-sgai
Command: npx skills add https://github.com/ucirello/sgai --skill using-sgai-ucirello

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables AI harnesses and agents to programmatically interact with and control the Sgai AI software factory, automating complex software development workflows.

Core Features & Use Cases

  • Workspace Management: Create, fork, delete, and rename AI development workspaces.
  • Session Control: Start, stop, and steer AI agent sessions within workspaces.
  • Human Interaction: Respond to agent questions and approve work gates.
  • Monitoring: Track workspace status, view progress, and receive real-time updates.
  • Use Case: An AI orchestrator can use this skill to automatically spin up new development environments, assign tasks based on a project goal, monitor progress, and handle any human-in-the-loop questions that arise during the development cycle.

Quick Start

Use the using-sgai skill to create a new workspace named 'my-new-project'.

Frequently Asked Questions about using-sgai

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

FAQPage Schema
How do I automate AI agent session control in a software factory?▼

Automate AI agent session control by driving the Sgai AI software factory through its HTTP API and MCP interface, enabling cyclical probe/poll/act workflows to start, stop, and steer development sessions.

Can I programmatically manage and fork AI development workspaces?▼

Programmatically manage and fork AI development workspaces by sending HTTP API requests to the Sgai software factory, allowing automated creation, renaming, and deletion of isolated development environments.

How does human-in-the-loop interaction work during AI orchestration?▼

Human-in-the-loop interaction during AI orchestration works through the Sgai interface to respond to agent questions and approve work gates, pausing cyclical workflows until manual confirmation is provided.

Do I need a running Sgai server to orchestrate AI development workflows?▼

You need a running Sgai server alongside an HTTP client or MCP-capable harness to orchestrate AI development workflows, as the Skill acts as the driver for the software factory's API.

How do I monitor AI agent progress and workspace status in real-time?▼

Monitor AI agent progress and workspace status in real-time by polling the Sgai HTTP API, tracking development updates and receiving status changes within the orchestration workflow.

What is the best way to handle multiple AI development environments concurrently?▼

The best way to handle multiple AI development environments concurrently is using the Sgai software factory orchestration to spin up workspaces, assign tasks based on project goals, and monitor progress via API.

Related Skills

Explore More Software Engineering Skills→
sandgardenhqsandgardenhq
130

using-sgai

Automate sgai software factory workspaces via probe, poll, and act loops.

Official
Advanced
k2worksk2works

tracking-progress

Analyze project progress from git logs, test results, and architectural data.

Community
Advanced
StonelukasStonelukas

google-adk-python

Design, orchestrate, and deploy AI agents with Google ADK Python.

Community
Advanced
sandgardenhqsandgardenhq
130

session-control

Start, stop, and steer AI agent sessions in sgai workspaces.

Official
Intermediate