audience-matcher

Score MCP personas on five factors to match topics to audience segments.

Updated Mar 9, 2026

Search Tags:#MCP #topics #content-segmentation #audience-matcher #persona-matching #voice-fit

Ready to run

npx skills add https://github.com/Bishwas-py/webmatrices-skills --skill audience-matcher

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: audience-matcher
Source: https://github.com/Bishwas-py/webmatrices-skills/tree/main/skills/audience-matcher
Command: npx skills add https://github.com/Bishwas-py/webmatrices-skills --skill audience-matcher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Match a topic or trend to the best Webmatrices persona and audience segment. Retrieve personas live from MCP and avoid hardcoded mappings to ensure accurate voice and backstory alignment.

Core Features & Use Cases

Live persona data from MCP used for dynamic, up-to-date matching (no hardcoded usernames, IDs, or topic mappings).
Weighted scoring across Topic Relevance, Voice Fit, Backstory Relevance, Recency, and Fatigue to select the best persona.
Use Case: decide which persona should cover a topic or tailor content to a particular audience segment, with runner-up recommendations as a fallback.

Quick Start

Provide a topic, and Audience Matcher will return the best matching MCP persona and the target audience segment.

Frequently Asked Questions about audience-matcher

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

FAQPage Schema

How do I match a topic to the right audience persona for content segmentation?▼

Persona matching for content segmentation works by evaluating topic relevance, voice fit, backstory relevance, recency, and fatigue. Audience Matcher uses live MCP data to score these five factors and returns a primary persona, runner-up, target segment, tone, and hook.

What factors determine the best persona fit for a specific topic?▼

Topic relevance, voice fit, backstory relevance, recency, and fatigue are the five factors used to determine the best persona fit. The scoring mechanism evaluates these against live MCP data to select a primary persona and a runner-up fallback.

Can I use hardcoded persona mappings for topic matching with MCP?▼

Hardcoded persona mappings are not used for topic matching. The system avoids static usernames, IDs, and topic mappings, relying exclusively on live MCP data to ensure accurate voice and backstory alignment for dynamic persona selection.

How do I get a runner-up persona recommendation when assigning content?▼

You get a runner-up persona recommendation by running your topic through a five-factor scoring evaluation. The system applies weighted scoring to live MCP data and returns a structured match complete with a primary persona, a runner-up, target segment, tone, and hook.

Does audience persona matching work without live MCP data?▼

No, audience persona matching requires live MCP data to function accurately. The system depends on live data to evaluate voice fit and backstory relevance dynamically, deliberately avoiding hardcoded mappings to ensure up-to-date persona selection.