skills.rest
jlenrique
jlenriqueCOMMUNITY
Explore all skills by this author →
GitHub

source-wrangler

Consolidates Notion pages, Box references, web content and local PDFs into extracted.md with provenance metadata.

Updated Mar 26, 2026
Search Tags:#workflow#pdf#notion#extraction#web#bundle#box-drive
One-click install
npx skills add https://github.com/jlenrique/course-DEV-IDE-with-AGENTS --skill source-wrangler
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: source-wrangler
Source: https://github.com/jlenrique/course-DEV-IDE-with-AGENTS/tree/main/skills/source-wrangler
Command: npx skills add https://github.com/jlenrique/course-DEV-IDE-with-AGENTS --skill source-wrangler

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pypdf, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Consolidates disparate course sources from Notion, Box Drive, and the web into a single, audit-friendly source bundle that includes extracted content and provenance.

Core Features & Use Cases

  • Notion page to Markdown extraction for bundles
  • Box Drive file discovery and content ingestion
  • HTTP/Playwright-enabled web exemplar capture and HTML-to-text wrangling
  • Local PDF text extraction via pypdf
  • Preflight validation and deterministic bundle output to course-content paths
  • Output includes extracted.md and metadata.json with provenance

Quick Start

Ask the tool to gather Notion pages, Box files, and a web exemplar, then emit extracted.md and metadata.json in the configured bundle directory.

Frequently Asked Questions about source-wrangler

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

FAQPage Schema
How do I consolidate Notion pages and Box Drive files into a single bundle?▼

The bundle includes extracted Markdown content and a metadata.json file containing full provenance trails for audit purposes, tracking where each piece of content originated across Notion, Box, web, and local PDF sources.

Can I extract text from local PDFs and web content for course modules?▼

Both extracted texts are merged into the extracted.md file alongside provenance metadata, ensuring all local PDF and web sources are validated during preflight and tracked in the final output bundle.

What's the best way to add provenance metadata to extracted course content?▼

This provenance trail ensures the final extracted.md output remains audit-friendly, providing full traceability for Marcus and specialists who need to verify the sources of the consolidated course knowledge.

Does this source consolidation approach support preflight validation?▼

This validation step ensures that HTML-to-text wrangling and pypdf extraction processes only valid, accessible sources, preventing errors during the generation of extracted.md and metadata.json files.

How do I convert Notion pages to Markdown for a knowledge bundle?▼

The extracted Markdown is combined with content from Box Drive, web exemplars, and local PDFs into a single extracted.md file, accompanied by metadata.json containing the full provenance trail.

Related Skills

Explore More Software Engineering Skills→
JuanMS20JuanMS20

github-auth

Configure GitHub authentication for Hermes Agent using git, gh CLI, or SSH credentials.

Community
Intermediate
MantisWareMantisWare

learn

Search the web, convert pages to Markdown, and ingest provenance-enriched knowledge.

Community
Advanced
eddmanneddmann
2

playwright

Render dynamic web pages with Playwright to capture HTML, text, and screenshots.

Community
Intermediate
wtyler2505wtyler2505
1

vault-source

Render provenance and coverage data from vault notes.

Community
Intermediate