ex-USSR Kinship Research: Evidence-First Genealogy Skill for AI

RepositoryDenisSergeevitch/ex-ussr-kinship-researchTool

An open-source skill for Claude Code, Codex and Agent Skills runtimes focused on family history across the former USSR. It enforces strict source tracking, separates records from interpretation, and logs findings in reproducible CSV registers.

Key points

  1. Covers records across all 15 former Soviet republics, the Soviet Union and the Russian Empire.
  2. Uses clear evidence statuses instead of percentages, preventing duplicate records from faking corroboration.
  3. Applies a historical jurisdiction model based on borders and authorities as of the event date.
  4. Includes an automated Python audit script to verify referential integrity, registers and claim statuses.
  5. Handles multilingual name matrices across pre-reform Russian, Polish, Ukrainian, German, and Yiddish.

Why it matters

It serves as an excellent blueprint for constraining LLM agents through rigorous external registers, schemas and audit scripts in evidence-critical workflows.

Analysis

Problem and Approach

Genealogical research in the former USSR faces major hurdles: changing borders, pre-reform alphabets, scattered archives, and homonyms. LLMs without strict guardrails easily hallucinate connections. This repository introduces an agent skill (compatible with Codex and Claude Code) designed to force models into a traceable, evidence-first workflow.

Architecture and Mechanics

The project structures research data into strict CSV registers covering persons, claims, artifacts, relationships, and a search log. Key methodological features include:

  • Independence Groups: Mirrors or repeated scans of the same original document cannot be treated as independent corroborating proof.
  • Historical Jurisdiction: Searches are mapped to historical districts, parishes, or administrative bodies at the time of the event, rather than modern maps.
  • Identity Resolution: People with identical names remain distinct entities until concrete proof (such as parents, house numbers, or birthdates) merges them.
  • Automated Audits: An integrity check script verifies that all cited IDs in the final report exist in the registers and that status labels match recorded evidence.

Target Audience and Maturity

The project is aimed at historians, family history researchers, and developers building structured research agents. With over 1,000 GitHub stars, active maintenance, and a detailed evidence framework, it represents a mature implementation of structured agent skill design.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 28 October 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:mohitagw15856/pm-claude-skills

    PM Skills: Agent Framework Collection for AI Assistants

    PM Skills is an MIT-licensed repository providing over 1,100 structured agent skills in plain Markdown. It equips models across Claude, ChatGPT, Gemini, Cursor, and Codex with step-by-step frameworks for professional duties and critical life events.

    1.3kstarsHTML

    AI & LLMs· Resource

  • Repository:briiirussell/cybersecurity-skills

    Cybersecurity Skills: Security Workflows for AI Coding Agents

    An open-source repository provides structured cybersecurity skills for AI agents like Claude Code, Cursor, and Codex. It helps developers and security engineers run automated audits, dependency scans, and code reviews directly within agent workflows.

    479starsJavaScript

    AI & LLMs· Tool

  • Repository:anthropics/skills

    Anthropic Skills: Reference Repository and Specification for Claude Agent Skills

    Anthropic provides a public repository containing example skills, templates, and specifications for Claude's Agent Skills standard. Skills package instructions, scripts, and resources inside folders with a central SKILL.md file to enable repeatable workflows ranging from document generation to technical testing.

    174.3kstarsPython

    AI & LLMs· Resource

  • Repository:K-Dense-AI/scientific-agent-skills

    Scientific Agent Skills: Open-Source Skills for AI-Driven Science

    Scientific Agent Skills (formerly Claude Scientific Skills) is an open-source library providing 177 validated skills and access to over 100 scientific databases, enabling AI agents to handle workflows across biology, chemistry, medicine, and drug discovery.

    52.3kstarsPython

    AI & LLMs· Tool

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.