Family History Research Skill — Install & Live Demo

Why use it

Key features

Research planning templates (research question → likely sources → search plan)
Genealogical Proof Standard checklist
Source evaluation rubric (original vs derivative)
Common record types and their gotchas
Citation formatting (Evidence Explained)

Live Demo

What it looks like in practice

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

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

~/.cursor/mcp.json · .cursor/mcp.json

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

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

~/.codeium/windsurf/mcp_config.json

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

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

~/.continue/config.json

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

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

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

claude mcp add family-history-research-skill -- git clone https://github.com/emaynard/claude-family-history-research-skill ~/.claude/skills/claude-family-history-research-skill

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

Use Cases

Real-world ways to use Family History Research Skill

Plan a research session for one ancestor's birth date

👤 Genealogists ⏱ ~15 min intermediate

When to use: You don't know where to look next for an ancestor stuck pre-1850.

Prerequisites

Server/skill installed and authenticated — See repo README

Flow

Frame

Using the genealogy skill, frame a research question for finding John Smith's birth date (b. ~1820, Cork, Ireland).✓ Copied

→ Research question + source hierarchy
Plan

Generate a search plan with specific record sets (Irish civil registration, Catholic parish registers, US naturalization).✓ Copied

→ Ordered, scoped search plan

Outcome: A real plan instead of random Ancestry hunts.

Pitfalls

Skill is methodology, not database. You still need subscriptions to Ancestry/FamilySearch/FindMyPast for the records themselves. — Skill is methodology, not database. You still need subscriptions to Ancestry/FamilySearch/FindMyPast for the records themselves.

Cost & Limits

What this costs to run

API quota: See provider docs for rate limits
Tokens per call: Varies by tool
Monetary: See repo README for pricing details
Tip: Cache tool results and avoid repeated identical calls.

Security

Permissions, secrets, blast radius

Credential storage: Use environment variables; never commit secrets

Data egress: Tool calls go to the provider's API as documented

Troubleshooting

Common errors and fixes

skill suggests invented record sets

Ask it to cite the record set's URL and verify on FamilySearch/Ancestry catalog before searching.

Verify: Catalog entry exists

citations don't render

Skill outputs Evidence Explained format. Use a markdown viewer that supports footnotes.

Verify: Render with pandoc

Alternatives

Family History Research Skill vs others

Alternative	When to use it instead	Tradeoff
Ancestry's own AI tools	You're deep in their ecosystem	Vendor lock-in

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills