ex-ussr-kinship-research
by DenisSergeevitch
A skill pack for AI coding agents such as Codex and Claude Code that makes them act as careful family-history researchers for the former USSR and Russian Empire. It guides the agent through church, civil, military, deportation and repression records, keeping a traceable evidence log and producing a final HTML report.
- Stars
- 1.4k +195 a day, est.
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Moderate
- Language
- Python
- Age
- 6 days
What you can do with it
- Trace an ancestor through church books, civil, military and repression records, with each finding linked to its source
- Check whether records from different scans refer to the same person and build an evidence chain
- Draft archive request letters and produce a final HTML family-history report with contradictions and next steps
Make money with it
Offer paid family-history research reports for clients with roots in Eastern Europe, using the skill to organise searches and evidence.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- A professional genealogist or freelance researcher could use it to speed up and document client family-history cases.
- A heritage or citizenship-document service could use it to organise archive searches and request letters for clients.
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install with the Skills CLI via npx, or clone the repository into your agent's skills folder; most scripts need only Python 3.
Follow the official instructions in the project README.
Things to check
- Needs an AI agent such as Codex or Claude Code, which may require a paid subscription or API access
- Skill instructions are written in Russian, though the agent replies in your language
- FamilySearch features depend on your own account and its terms of use
- Archive coverage varies, so results depend on what records are available
Who's talking about it
Checked 01 Nov 2026. Summary drafted by AI from the project's README.
