Ingest Resource

The problem

Information fragments from URLs, YouTube videos, and PDFs often sit unorganized in raw notes or get lost in browser tabs. Converting these into structured knowledge requires manual folder management, date-stamping, and metadata tagging that most developers skip.

What it does

• Automates resource routing into either stable knowledge/ or task-specific projects/ directories.
• Generates standardized filenames using a Python-based slugging system with dates and kebab-case formatting.
• Extracts and synthesizes content into a three-layer Progressive Summary for fast retrieval.
• Automatically creates missing directory structures and inserts [[wikilinks]] for cross-referencing.
• Fetches full web content from URLs and handles transcripts or PDF summaries.

Frameworks & tools

Python 3 for slug generation and file renaming. Compatible with file-based knowledge bases like Obsidian, Logseq, or standard Markdown systems.

Why this beats prompting it yourself

This skill eliminates the friction of manual filing and consistency checks. It uses a dedicated Python script to ensure filenames never break system conventions and enforces a strict structural layout that makes your entire knowledge base programmatically searchable.

Use cases

• Processing research papers and technical articles into long-term mental models.
• Capturing YouTube transcripts for specific project deliverables or newsletter issues.
• Archiving raw meeting notes with automatic linking to project stakeholders.
• Converting paywalled or transient web content into stable Markdown archives.

Known limitations

Requires an environment capable of executing Python 3. Web fetching is subject to the agent's available tools and may be restricted by paywalls.