Autoresearch Genealogy
Run autonomous Claude Code genealogy research loops with vault templates, archive guides, and verification workflows for family-history projects.
Overview
autoresearch-genealogy is an agent skill most often used in Idea (also Validate, Grow) that supplies autoresearch prompts, Obsidian templates, and genealogy methodologies for AI-assisted family-history research.
Install
npx skills add https://github.com/aradotso/trending-skills --skill autoresearch-genealogyWhat is this skill?
- 12 Claude Code /autoresearch prompts that search the web, update your vault, and self-verify results
- 19-file Obsidian vault starter kit with YAML frontmatter and markdown templates
- 24 country and region-specific archive guides including Jewish genealogy coverage
- 9 methodology references for confidence tiers, DNA guardrails, naming, and source hierarchy
- 7 step-by-step workflows for OCR, oral history, discrepancy resolution, and phase planning
- 12 autoresearch prompts
- 24 country/region archive guides
Adoption & trust: 1.2k installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want AI to help trace ancestors but raw chat produces unsourced claims, messy notes, and no repeatable archive or DNA verification workflow.
Who is it for?
Solo builders or genealogists already using Claude Code and Obsidian who want autonomous search-update-verify loops with regional archive context.
Skip if: Teams building unrelated B2B SaaS without personal-history research, or anyone who needs certified genealogist legal proof without human review.
When should I use this skill?
Triggers include helping research a family tree with AI, setting up a genealogy vault template, running autoresearch genealogy prompts, or organizing documents with DNA and audit workflows.
What do I get? / Deliverables
You get a vault-backed, prompt-driven research system where autonomous runs update structured notes and follow confidence and source-hierarchy rules before you publish or share family findings.
- Populated genealogy vault from templates
- Autoresearch run logs and updated person/source notes
- Audit-ready discrepancy and confidence-tier documentation
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Genealogy autoresearch starts in Idea when you are discovering ancestors and sources; the skill’s canonical shelf is deep research before you treat findings as validated family facts. Subphase research matches web archives, cross-references, DNA notes, and vault updates—the same discovery work solo builders do before scoping any derivative app or content product.
Where it fits
Spin up /autoresearch to query regional archives and append sourced person notes into your Obsidian vault starter kit.
Run cross-reference audit workflows to resolve conflicting census versus church records before adding a new branch to the tree.
Turn verified oral-history workflows into publishable family narrative pages with confidence tiers visible to readers.
Use archive guides to discover lesser-known record sets for a specific country before committing to a paid subscription service.
How it compares
Use instead of unstructured “find my ancestors” chats when you need vault templates, archive routing, and explicit verification steps like a mini research ops playbook.
Common Questions / FAQ
Who is autoresearch-genealogy for?
It is for indie researchers and family historians who combine Claude Code autoresearch with Obsidian (or similar markdown vaults) and want country-specific archive guidance plus DNA and sourcing guardrails.
When should I use autoresearch-genealogy?
Use it in Idea while discovering ancestors and archives, in Validate when cross-reference auditing discrepancies before trusting conclusions, and in Grow when organizing oral histories or published family content from verified notes.
Is autoresearch-genealogy safe to install?
Check the Security Audits panel on this page; the skill drives web research and local vault writes, so review prompts before runs that touch sensitive relative data or third-party genealogy APIs.
SKILL.md
READMESKILL.md - Autoresearch Genealogy
# autoresearch-genealogy > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. A structured system of autoresearch prompts, Obsidian vault templates, archive guides, and methodology references for AI-assisted genealogy research. Built for Claude Code's autonomous research loops, adaptable to any AI tool or manual workflow. --- ## What This Project Does - Provides 12 Claude Code `/autoresearch` prompts that autonomously search the web, update your vault, and self-verify results - Supplies a complete 19-file Obsidian vault starter kit with YAML frontmatter and markdown templates - Includes 24 country/region-specific archive guides (Europe, Americas, Oceania, Jewish genealogy) - Offers 9 methodology reference documents covering confidence tiers, DNA guardrails, naming conventions, and source hierarchy - Defines 7 step-by-step workflows for OCR pipelines, oral history, discrepancy resolution, and phase planning --- ## Installation ```bash # Clone the repository git clone https://github.com/mattprusak/autoresearch-genealogy.git cd autoresearch-genealogy # Copy vault template into your Obsidian vault cp -r vault-template/ ~/path/to/your/ObsidianVault/genealogy/ # Or copy to any markdown editor folder cp -r vault-template/ ~/Documents/my-genealogy/ ``` No package manager or build step required — this is a pure markdown/prompt project. --- ## Project Structure ``` autoresearch-genealogy/ ├── prompts/ # 12 autoresearch prompt files for Claude Code ├── vault-template/ # 19-file Obsidian vault starter kit │ ├── Family_Tree.md │ ├── Research_Log.md │ ├── Open_Questions.md │ ├── templates/ # Person, certificate, postcard, region, etc. │ └── ... ├── archives/ # 24 country/region research guides ├── reference/ # 9 methodology documents ├── workflows/ # 7 step-by-step process guides └── examples/ # 6 anonymized worked examples ``` --- ## Quick Start Workflow ### Step 1: Seed your family tree Open `vault-template/Family_Tree.md` and fill in what you already know, starting with yourself and working backward: ```markdown --- title: Family Tree last_updated: 2026-03-19 generations_documented: 3 lines_active: 2 --- # Family Tree ## Generation 1 (Self) - **Name**: Jane Smith (b. 1985, Chicago, IL) ## Generation 2 (Parents) - **Father**: John Smith (b. 1955, Detroit, MI) - **Mother**: Mary O'Brien (b. 1958, Boston, MA) ## Generation 3 (Grandparents) - **Paternal Grandfather**: Robert Smith (b. ~1920, unknown) - **Paternal Grandmother**: Helen Kowalski (b. ~1925, Poland?) ``` ### Step 2: Scan physical documents Photograph or scan certificates, letters, postcards. Use the OCR workflow: ``` See: workflows/ocr-pipeline.md ``` ### Step 3: Run autoresearch prompts in Claude Code ``` /autoresearch prompts/01-tree-expansion.md ``` ### Step 4: Audit and verify ``` /autoresearch prompts/02-cross-reference-audit.md ``` --- ## Autoresearch Prompts — Reference Each prompt in `prompts/` follows this structure: ```markdown ## Goal [What this iteration should accomplish] ## Metric [Measurable success condition — e.g., "increase sourced person files from N to N+10"] ## Direction [Step-by-step instructions for the AI] ## Verify [Cross-check to run after each iteration] ## Guard Rails [What NOT to do — prevent hallucination, preserve source rigor] ## Iterations [How many loops to run before stopping for human review] ## Protocol [Output format, file