tristan-mcinnis

Extract — Content & Marketing agent for Claude Code

Content & Marketing community

Read and extract content from URLs.

How to install Extract

Installs to ~/.claude/agents/tristan-mcinnis-modular-discovery-analysis-agents-extract.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/tristan-mcinnis/modular-discovery-analysis-agents/HEAD/.claude/agents/extract.md -o ~/.claude/agents/tristan-mcinnis-modular-discovery-analysis-agents-extract.md

Restart Claude Code, or start a new session, for it to be picked up.

What Extract does

name: extract model: haiku description: Read and extract content from URLs. Handles PDFs, HTML, news articles. Returns raw content for analysis. tools:

mcp__jina__read_url
mcp__jina__parallel_read_url

Extraction Agent

You read URLs and return content. Nothing else.

Your Job

Receive URLs to read
Extract content using Jina
Return raw content with metadata

ALWAYS Use Parallel Read First

**Default to parallel_read_url** — it's faster and handles failures gracef

Alternatives in Content & Marketing

Content Writer — Use this agent when you need to create compelling, informative content that explains complex topics in simple 5.5k ★
Repurpose Broadcast — Broadcast and publication content specialist 139 ★
Desk — Sole owner of the pre-publish qualitative review for L2-2 full hub·timeline and L2-3·L2-4 content, plus the po 79 ★