talk-stage1-extract

Ingest source material and metadata to produce a structured talk summary.

5.7k|744|Updated Jan 9, 2026
One-click install
npx skills add https://github.com/FlorianBruniaux/claude-code-ultimate-guide --skill talk-stage1-extract
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: talk-stage1-extract
Source: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples/skills/talk-pipeline/stage-1-extract
Command: npx skills add https://github.com/FlorianBruniaux/claude-code-ultimate-guide --skill talk-stage1-extract

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill streamlines turning raw material (article, transcript, notes) into a structured talk summary, saving time and reducing manual drafting effort.

Core Features & Use Cases

  • Auto-detects source type (REX vs Concept) and tailors narrative arc
  • Metadata collection: collects slug, event, date, duration, audience, and other essential fields
  • Output generation: creates a ready-to-use summary file at talks/{YYYY}-{slug}-summary.md
  • Integrates with downstream stages (Stage-2: Research, Stage-3: Concepts) for end-to-end workflows

Quick Start

Ingest source material and metadata, detect the source type, and produce a structured talk summary file ready for downstream stages.

Frequently Asked Questions about talk-stage1-extract

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

FAQPage Schema
How do I turn raw notes and transcripts into a structured talk summary?

To create a structured talk summary, ingest your raw article, transcript, or notes material to auto-detect the source type and generate a ready-to-use markdown summary file.

What is the best way to extract a presentation narrative arc from source material?

Extracting a presentation narrative arc involves reading the source material, determining whether it is a REX or Concept type, and tailoring the summary structure to match that detected format.

What metadata do I need to prepare to generate a talk summary file?

You need to provide essential metadata fields including slug, event, date, duration, and audience alongside your raw source material to produce a complete talk summary file.

Does this talk extraction approach work for both REX and Concept presentation types?

Yes, the talk extraction process auto-detects both REX and Concept source types, automatically tailoring the narrative arc and summary output to fit the specific presentation format.

How does the output talk summary integrate with downstream research stages?

The output talk summary integrates by generating a structured markdown file at a standard file path, which serves as the direct input for downstream research and concept development stages.

Can I use this to summarize raw materials for different types of events and audiences?

Yes, you can summarize raw materials for various events and audiences by specifying those metadata fields during ingestion, ensuring the resulting talk summary matches your specific presentation context.