skills.rest
rdeknijf
rdeknijfCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

onboard-datasource

Create data source connection skills for genealogy archives or databases.

Updated Aug 23, 2026
Search Tags:#workflow#api#integration#onboard#datasource#sru
One-click install
npx skills add https://github.com/rdeknijf/ai-genealogy-kit --skill onboard-datasource
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: onboard-datasource
Source: https://github.com/rdeknijf/ai-genealogy-kit/tree/main/.claude/skills/onboard-datasource
Command: npx skills add https://github.com/rdeknijf/ai-genealogy-kit --skill onboard-datasource

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Create a data-source onboarding workflow that generates a Claude skill for a genealogy archive or database, enabling rapid discovery and reuse across projects.

Core Features & Use Cases

  • Investigate & choose method: Evaluate the fastest access method (api, sparql/oai-pmh/sru, url fetch, or browser automation) and document the rationale.
  • Skill generation: Produce .claude/skills/<source-name>.md with frontmatter, coverage, and a step-by-step workflow.
  • Documentation update: Add the new source to research/DATA_SOURCES.md and perform end-to-end validation.

Quick Start

Create a new data-source onboarding skill and generate the corresponding .claude/skills/<source-name>.md file.

Frequently Asked Questions about onboard-datasource

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I onboard a new genealogy data source connection?▼

To onboard a new genealogy data source, this workflow investigates the fastest access method and outputs a ready-to-use skill file with frontmatter, coverage details, and a step-by-step workflow.

What is the best way to connect to a genealogy archive API?▼

The best way to connect to a genealogy archive is evaluating available access methods like API, SPARQL, OAI-PMH, SRU, URL fetch, or browser automation to identify the fastest retrieval approach.

How do I generate a skill file for querying a database via SRU?▼

You generate a skill file by selecting SRU as the access method during the workflow, which then produces a .claude/skills/<source-name>.md file documenting the connection steps and coverage.

Can I use browser automation to access a genealogy database without an API?▼

Yes, browser automation is supported as an access method when no direct API is available, allowing you to extract genealogy archive data and document the workflow in a skill file.

Does onboarding a data source update the main documentation?▼

Yes, onboarding a data source automatically updates the research/DATA_SOURCES.md file with the new entry and performs an end-to-end validation to ensure the connection works.

When should I choose SPARQL over URL fetch for data source integration?▼

You should choose SPARQL over URL fetch when the genealogy archive exposes a semantic query endpoint, as the workflow evaluates and documents the rationale for selecting the fastest available access method.

Related Skills

Explore More Software Engineering Skills→
vlad-ryzhkovvlad-ryzhkov
25

repo-scout

Audit Go backend repositories for API endpoints, infrastructure, and test coverage.

Community
Intermediate
lhllhl
38

check

Run three-stage Reality Check analyses on web sources with Python and RC-CLI tools.

Community
Advanced
uhvc7652uhvc7652

data

Converts JSON, CSV, YAML, and XML formatsUTE and parses JSON strings with JSONPath for targeted extraction.

Community
Intermediate
HouseGarofaloHouseGarofalo
3

browserless

Automate headless Chrome browser tasks via REST API and WebSocket.

Official
Intermediate