Open-Genealogy packages prompts, skills, and helper files for genealogical research. The work is organized around GPS-style evidence handling, with separate material for research, transcription, image analysis, photo restoration, writing, and GEDCOM work.
Builders who use Claude Code or other agent tools for family history research and need a structured evidence workflow.
You can analyze records with a repeatable genealogy method instead of improvising each search and conclusion.
Research prompts follow the Genealogical Proof Standard and include evidence classification, transparency, and conflict resolution.
The `skills/gra` folder provides the current GRA v9.2.0 Agent Skill and supporting references.
The `research/` folder includes self-contained prompt editions for ordinary chat, Custom GPTs, and Gems.
`genealogy-ai-starter-workspace/` gives a project folder with `AGENTS.md`, `CLAUDE.md`, prompts, notes, records, references, templates, and tutorials.
The `assistants/` folder includes GEDCOM analysis and builder prompts, plus other genealogy assistant definitions.
Dedicated folders cover transcription, image analysis, photo restoration, writing tools, scripts, benchmark material, and reference guides.
A toolkit of AI prompts and utilities for genealogical research, designed to follow the Genealogical Proof Standard. For genealogists at every level — from hobbyists exploring their first census record to credentialed professionals managing client work.
Before copying, pasting, or uploading a record: standard Codex, Claude, and other hosted AI workflows process the material with a cloud model. Do not send living-person details or any record that is too sensitive for the service you choose. Treat every AI response as draft analysis; verify records, citations, and conclusions yourself.
Choose the GRA v9.2.0 edition that fits your client.
GRA v8.5, v8, and v7 remain available under the documented compatibility and history route.
Full catalog: INDEX.md | Detailed guide: GETTING-STARTED.md | Historical v8 guide: GETTING-STARTED-v8-legacy.md | Guided tour: TOUR-REPORT.md
New here? The Getting Started guide walks through setup, first use, and common workflows.
The research/ folder contains prompts designed to follow the Genealogical Proof Standard—the professional methodology for evidence-based genealogical conclusions.
Key features:
Aligned with the methodology described in:
The benchmark/ folder preserves four historical model outputs and a teaching rubric for close reading. The retained evidence does not support a reproducible model ranking; read the benchmark's current methodology notice before using it.
This toolkit applies widely recognized genealogical research principles. It is not published by, endorsed by, or affiliated with Elizabeth Shown Mills, the Board for Certification of Genealogists, or any certifying body. References to published standards indicate methodological alignment, not authorization or derivation.
Creative Commons BY-NC-SA 4.0 covers Steve-authored content within its stated scope. It does not automatically cover third-party, historical, or limited-permission media included in the repository. Read RIGHTS.md and the Rights and License Matrix before reusing an image, audio file, captured model output, quotation, or other material that may have separate rights.
Steve Little (@DigitalArchivst)
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
