session_persistence

Persist Read Aloud session metadata to local extension_state.json files.

2|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/IdanDavidAviv/virgo --skill session-persistence
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session_persistence
Source: https://github.com/IdanDavidAviv/virgo/tree/main/.agent/skills/session_persistence
Command: npx skills add https://github.com/IdanDavidAviv/virgo --skill session-persistence

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local AI workflows often lose context across interactions because session data is not reliably stored outside memory. This protocol persists session metadata locally to provide human-readable titles and consistent turn metadata for the Read Aloud extension.

Core Features & Use Cases

  • Local storage architecture under the Antigravity path: ~/.gemini/antigravity/read_aloud/<sessionId>/ to house per-session state and snippet files.
  • Metadata schema: extension_state.json containing session_title, current_turn_index, and last_updated to drive UI resolution and continuity.
  • UI resilience and MCP compatibility: UI resolution reads extension_state.json to derive display names; MCP injections update the state atomically and reflect new titles in the UI.

Quick Start

Install the agent and configure it to store session metadata in extension_state.json under ~/.gemini/antigravity/read_aloud/<sessionId>/ and write new snippet files to read_aloud as MCP outputs.

Frequently Asked Questions about session_persistence

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

FAQPage Schema
How do I persist Read Aloud session metadata locally for UI resolution?

To persist Read Aloud session metadata locally, store state in an extension_state.json file under ~/.gemini/antigravity/read_aloud/<sessionId>/. This schema retains human-readable titles and turn order for UI continuity across sessions.

What is the extension_state.json schema used for local session persistence?

The extension_state.json schema manages local session persistence by storing session_title, current_turn_index, and last_updated. It drives UI resolution and ensures MCP injections update the state atomically to reflect new titles.

How do I write MCP snippet outputs to a specific local session directory?

Write MCP snippet outputs to the read_aloud/<sessionId>/ directory path. This local storage architecture houses per-session state and snippet files, applying proper session_title updates and turn index incrementation.

Does local session persistence for Read Aloud work with MCP-safe updates?

Yes, local session persistence supports MCP-safe updates by reading extension_state.json to derive display names while MCP injections update the state atomically. This ensures UI resilience and compatibility across local extension workflows.

Why do local AI workflows lose Read Aloud context across interactions?

Local AI workflows lose Read Aloud context across interactions because session data is not reliably stored outside memory. Persisting metadata locally in extension_state.json solves this by providing consistent turn metadata and human-readable titles.