mkt-autoresearch

Generate and score marketing content variants through iterative expert rounds.

520|175|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/evolution-foundation/evo-nexus --skill mkt-autoresearch-evolution-foundation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mkt-autoresearch
Source: https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/mkt-autoresearch
Command: npx skills add https://github.com/evolution-foundation/evo-nexus --skill mkt-autoresearch-evolution-foundation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, and includes references (resource) components.

What problem does it solve?

It helps you improve marketing and conversion content quality without waiting weeks for real A/B test results by running iterative, expert-scored optimization loops.

Core Features & Use Cases

  • Iterative autoresearch loop: generates 50+ variants, scores them, and evolves winners across multiple rounds until a target score is reached.
  • Simulated 5-persona expert panel: evaluates copy on conversion-focused dimensions (e.g., clarity, trust, urgency, would-convert).
  • Content-type coverage: supports landing pages, email sequences, ad copy, and form pages, optimizing both headlines and supporting elements.
  • Decision-ready outputs: produces the best optimized content plus a full experiment log for review and iteration.

Quick Start

Run python3 autoresearch.py with your input file, set the desired content type if needed, and choose a minimum target score to generate the optimized version and a full report.

Frequently Asked Questions about mkt-autoresearch

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

FAQPage Schema
How do I optimize conversion copy for landing pages without running live A/B tests?

Conversion copy optimization uses a simulated five-persona expert panel to score generated variants on dimensions like clarity, trust, and urgency. The iterative loop evolves winning variants across rounds until a target score is reached, producing optimized content and a structured experiment log.

Can I generate and score email and ad copy variants before launching a campaign?

Yes, the tool generates 50+ email and ad copy variants and scores them with a simulated expert panel. It evaluates configurable elements on conversion-focused dimensions, producing decision-ready optimized content and a structured experiment log for pre-launch campaign review.

What do I need to run iterative autoresearch for marketing optimization?

You need source content in a local file and the ANTHROPIC_API_KEY environment variable configured. Running the python script with your input file and a target score initiates the variant generation and simulated expert scoring process.

Does simulated expert scoring work for form pages and supporting elements?

Yes, simulated expert scoring supports form pages by optimizing both headlines and supporting elements. The five-persona panel evaluates copy on conversion-focused dimensions, applying the same iterative autoresearch loop used for landing pages.

What is the best way to evaluate marketing content strategy before launch?

Pre-launch marketing content strategy evaluation is best done via an iterative autoresearch loop that generates variants and scores them with a simulated expert panel. This produces a structured experiment log and markdown report for decision-ready review.