wrap-up

Extract session summaries from .trinity files and upload them to NotebookLM.

1|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/gHashTag/t27 --skill wrap-up-ghashtag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wrap-up
Source: https://github.com/gHashTag/t27/tree/main/.claude/skills/wrap-up
Command: npx skills add https://github.com/gHashTag/t27 --skill wrap-up-ghashtag

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the frustration of losing critical session context, key decisions, and work progress between separate AI interactions, removing the need to manually re-explain past work or track outcomes across disconnected conversations.

Core Features & Use Cases

  • Automated Context Extraction: Pulls session details, modified files, and key decisions directly from local .trinity state files without manual input.
  • Structured Summary Formatting: Organizes session outcomes into Markdown with consistent metadata for easy readability and searchability.
  • NotebookLM Integration: Uploads formatted summaries directly to NotebookLM as searchable sources, creating a persistent, cross-session knowledge base.
  • Use Case: After completing a 12-iteration development cycle on a hardware spec, use this Skill to upload the full session summary so your next interaction can instantly retrieve past design decisions and progress without redundant context-setting.

Quick Start

Use the wrap-up skill to upload a summary of your just-completed session working on the Ring-071 Phi Loop iterations to your default NotebookLM notebook for future reference.

Frequently Asked Questions about wrap-up

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

FAQPage Schema
How do I save AI session context for future recall?

To save AI session context, you can automatically extract modified files and key decisions from local `.trinity` state files and upload them as structured Markdown summaries to NotebookLM for future recall.

What is the best way to prevent cross-session memory loss in development workflows?

Preventing cross-session memory loss requires persisting session outcomes to an external knowledge base. This Skill automates uploading structured summaries of design decisions and progress to NotebookLM, eliminating manual context re-explanation.

How does automated context extraction from local state files work?

Automated context extraction works by pulling session details, modified files, and key decisions directly from local `.trinity` state files without manual input, formatting the data into readable Markdown with consistent metadata.

Do I need NotebookLM cookie authentication to upload session summaries?

Yes, you need valid NotebookLM cookie authentication and the notebooklm-py SDK to upload structured session summaries to a designated searchable notebook.

Can I use this session wrap-up tool for research and project tracking?

Yes, this session wrap-up tool applies to technical development, research, and project workflows where tracking past session outcomes, design decisions, and modified files across separate AI interactions is required.

Why does uploading session context to NotebookLM require local state files?

Uploading session context requires local `.trinity` state files because they store the raw session details, modified files, and key decisions needed for the Skill to extract and format structured summaries without manual input.