Content Researcher
Gathers sources, stats, frameworks, and competitive analysis for a topic — keeps research separate from writing.
Entry verified April 20, 2026
The short answer
The separation-of-concerns trick that levels up every content operation. Research and writing are different jobs; running them as one agent gets you mid-quality output. Run this first, then hand its output to a writer.
When to use it
Before every substantial content piece. Not needed for quick personal posts.
Setup
- 1
Save as ~/.claude/agents/content-researcher.md.
- 2
Give it web fetch + search tools. No write access — research only.
- 3
Output: markdown brief with sources, stats, counter-arguments, suggested angle.
Example
You: Research 'Claude Code for writers' Researcher: [fetches 12 sources, returns 600-word brief with 8 cited stats, 3 competitor angles, and 1 contrarian take]
Source & attribution
- Author
- Bryan Collins (portfolio pattern)
- Licence
- MIT
- Type
- Original
Original pattern published under MIT — attribution preserved by convention, not licence requirement.
Caveats
Web fetch can fail on paywalled sources. Configure fallback behaviour explicitly.
Related skills
Content Writer
Drafts a blog post, newsletter, or landing page from a brief — using the site's established voice.
Competitor Scan
Scrapes 3-5 competitor pages on the same topic, compares stance, and identifies content gaps + differentiation angles.
Academic Brief
Summarises 3-5 academic papers on a topic into a plain-English brief with the core claim, method, and limitations of each.
Browse more skills
47 skills across 10 categories, all licence-verified.