claude-marketing-research-skill MCP — Use Cases, Install & Live Demo

Why use it

Key features

Competitor analysis framework
Avatar / persona profiling
Positioning canvas
Value proposition construction
Mental models of target customer

Live Demo

What it looks like in practice

claude-marketing-research-skill.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "claude-marketing-research-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/ishwarjha/claude-marketing-research-skill",
        "~/.claude/skills/claude-marketing-research-skill"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "claude-marketing-research-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/ishwarjha/claude-marketing-research-skill",
        "~/.claude/skills/claude-marketing-research-skill"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "claude-marketing-research-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/ishwarjha/claude-marketing-research-skill",
        "~/.claude/skills/claude-marketing-research-skill"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "claude-marketing-research-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/ishwarjha/claude-marketing-research-skill",
        "~/.claude/skills/claude-marketing-research-skill"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "claude-marketing-research-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/ishwarjha/claude-marketing-research-skill",
        "~/.claude/skills/claude-marketing-research-skill"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "claude-marketing-research-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/ishwarjha/claude-marketing-research-skill",
          "~/.claude/skills/claude-marketing-research-skill"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add claude-marketing-research-skill -- git clone https://github.com/ishwarjha/claude-marketing-research-skill ~/.claude/skills/claude-marketing-research-skill

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use claude-marketing-research-skill

Position a new product entering a crowded market

👤 Founders, PMMs launching into known categories ⏱ ~90 min intermediate

When to use: You're about to launch and you don't know how to stand out.

Prerequisites

Skill installed — git clone https://github.com/ishwarjha/claude-marketing-research-skill ~/.claude/skills/claude-marketing-research-skill

Flow

Competitor teardown

Use claude-marketing-research-skill. Category: [X]. Map the top 5 competitors — messaging, target customer, price, weaknesses.✓ Copied

→ Matrix with specific observations per competitor
Avatar

Profile our target avatar — demographics, pains, current alternatives they cope with.✓ Copied

→ Rich avatar doc, not a Cosmo-poll persona
Positioning

Position us against the competitors for this avatar. What's the sharpest angle?✓ Copied

→ Clear positioning statement + why
Value prop

Translate into a hero-section value prop.✓ Copied

→ Headline + subhead that earn a click

Outcome: A positioning + message kit ready for the launch page.

Pitfalls

Generic positioning ('faster and easier') — Force a tradeoff — what are we NOT for?

Combine with: filesystem · github-optimization-skill

Refresh stale messaging for an existing product

👤 Teams where the site copy is 2 years old ⏱ ~45 min intermediate

When to use: Your market moved but your copy didn't.

Flow

Audit current

Use claude-marketing-research-skill. Audit our current hero/features/testimonials. What's stale or generic?✓ Copied

→ Specific critique per section
Rewrite

Rewrite using the fresh avatar and positioning.✓ Copied

→ Copy diff

Outcome: Copy that sounds like 2026, not 2023.

Combinations

Pair with other MCPs for X10 leverage

claude-marketing-research-skill + filesystem

Keep marketing research artifacts in a brand folder

Save outputs to brand/research/<date>/✓ Copied

claude-marketing-research-skill + github-optimization-skill

Apply positioning to an open-source repo's README

Translate the positioning into a README hero.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call
competitor_teardown	category, target set	Early research
avatar_profile	product + observed users	Persona definition
position	avatar + competitors	After competitor + avatar done
value_prop	positioning	Before copy work

Cost & Limits

What this costs to run

API quota: None
Tokens per call: High — research tends to be verbose
Monetary: Free
Tip: Save outputs — you'll reuse the avatar across campaigns.

Security

Permissions, secrets, blast radius

Credential storage: None

Data egress: None from skill

Competitor analysis based on LLM knowledge can be stale. Validate against current sites before acting on it.

Troubleshooting

Common errors and fixes

Competitor data is wrong or outdated

Supplement with fresh site reads; LLM's competitor knowledge lags

Avatar is generic

Feed real user quotes and support tickets for grounding

Alternatives

claude-marketing-research-skill vs others

Alternative	When to use it instead	Tradeoff
Agency workshop	You have budget and time	Slower; higher quality human work
Raw LLM with a prompt	Quick one-offs	No structure; output varies wildly

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills