Pattern Ingestion Skill

This skill intelligently analyzes sources for agentic AI patterns, matches them against existing patterns in the repository, and either creates new patterns or updates existing ones with additional sources and insights.

Overview

Input: A source (URL, PDF file, YouTube link, codebase path, or pasted text)

Process:

1. Ingest and analyze the source
2. Extract pattern concepts
3. Match against existing 105+ patterns
4. Decide: create new OR update existing
5. Execute and build

Output: New pattern file OR updated existing pattern + build confirmation

---

Phase 1: Ingest Source

Detect the input type and process accordingly:

URL (blog post, documentation, article)

Use mcp__web_reader__webReader with the URL:

{"url": "USER_PROVIDED_URL", "return_format": "markdown"}

PDF File

Use Read tool with the PDF path.

YouTube Video

Use mcp__web_reader__webReader with the YouTube URL (transcript extraction).

Codebase/Repository

Use Glob to find key files, then Read to analyze:

• **/*.md - Documentation
• **/*.py - Python implementation
• **/*.ts - TypeScript implementation
• README files

Pasted Text

Analyze directly (no tool needed).

---

Phase 2: Analyze & Extract

From the source content, extract:

1. Pattern Title - What is this pattern called?
2. Problem Statement - What challenge does it solve?
3. Solution - What's the core approach/mechanism?
4. Category - Which of 8 categories fits best?
5. Source URL - The original source
6. Author/Originator - Who created/originated this?
7. Tags - 3+ relevant keywords
8. Key Insights - Any novel techniques, constraints, trade-offs

Generate candidate metadata:

• Title: descriptive, concise
• Category: select from allowed categories (see reference below)
• Tags: generate 5-10 relevant tags
• Status: default to "emerging" unless evidence suggests otherwise

---