session-learnings

Generate investigation-log.md, README.md, chat-transcript.md, and Marp deck artifacts from AI coding sessions.

1|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/ktundwal/session-learnings --skill session-learnings
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-learnings
Source: https://github.com/ktundwal/session-learnings/tree/main/session-learnings
Command: npx skills add https://github.com/ktundwal/session-learnings --skill session-learnings

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Capture learnings from AI coding sessions and turn them into durable, portable artifacts that survive beyond the chat.

Core Features & Use Cases

  • Generates an investigation-log.md documenting decisions, dead ends, and rationale
  • Creates a README.md summary, chat-transcript.md, and a Marp deck (deck.md / deck.pptx / deck.html)
  • Updates MEMORY.md with new learnings to feed auto-memory systems

Quick Start

Run the /session-learnings [topic-name] command at the end of a productive session to begin collecting artifacts.

Frequently Asked Questions about session-learnings

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

FAQPage Schema
How do I capture AI coding session learnings as durable documentation artifacts?

Capture session learnings by generating portable artifacts like investigation-log.md and chat-transcript.md that preserve coding decisions and breakthroughs beyond the chat context.

What's the best way to document coding session decisions and dead ends for future reference?

Documenting session decisions is best handled by generating an investigation-log.md that records rationale, dead ends, and breakthroughs alongside a chat-transcript.md for full context.

How do I generate a Marp deck from a coding session transcript?

Generate a Marp deck by running an end-of-session workflow that extracts context and exports deck.md, deck.pptx, and deck.html files summarizing the coding session.

Does this session capture workflow require any external dependencies or components?

No external dependencies or components are required. The session capture workflow operates independently to extract context, generate artifacts, perform optional cross-model review, and update memory files.

How do I update MEMORY.md with new learnings from an investigation log?

Update MEMORY.md by running an end-of-session workflow that integrates new learnings from the generated investigation log directly into the memory file to feed auto-memory systems.

When should I use an automated session capture workflow instead of manual note-taking?

Use automated session capture at the end of productive AI coding sessions when you need deterministic, searchable documentation artifacts and memory integration rather than relying on manual notes.