skills.rest
elastic
elasticOFFICIAL
Explore all skills by this author →
WebsiteGitHub

build-data-source

Generate, review, and test Workplace AI data source connector code.

21.2k|8.6k|Updated Jan 26, 2013
Search Tags:#automation#workflow#testing#code generation#kibana#data source
One-click install
npx skills add https://github.com/elastic/kibana --skill build-data-source
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: build-data-source
Source: https://github.com/elastic/kibana/tree/main/x-pack/platform/plugins/shared/data_sources/.claude/skills/build-data-source
Command: npx skills add https://github.com/elastic/kibana --skill build-data-source

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the entire process of creating a new data source for Workplace AI, from initial code generation to final testing and activation.

Core Features & Use Cases

  • End-to-end Orchestration: Manages the full lifecycle of data source development.
  • Automated Code Generation: Creates necessary connector specs, workflows, and documentation.
  • Quality Assurance: Integrates code reviews and iterative testing to ensure high quality.
  • Use Case: When you need to implement a new way for Workplace AI to access and interact with a third-party data service, use this skill to build and deploy it.

Quick Start

Use the build-data-source skill to create a new data source for the 'tavily' API.

Frequently Asked Questions about build-data-source

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

FAQPage Schema
How do I automate building a data source from scratch for Workplace AI?▼

To automate building a data source from scratch, this Skill orchestrates the end-to-end development lifecycle including code generation, review, activation, and testing for new Workplace AI connectors.

How do I generate connector specifications and workflows for a new third-party data source?▼

Generating connector specifications and workflows for third-party data sources is handled through automated code generation, which creates the necessary configurations and documentation for immediate integration.

What is the process for testing a newly generated data source connector?▼

Testing a newly generated data source connector involves agent-based iterative testing and code reviews to validate code quality, ensuring the workflow functions properly before final delivery and activation.

Can I use this automation to integrate any third-party API into Kibana data sources?▼

Yes, you can use this automation to integrate third-party APIs by orchestrating the creation of connector specifications and workflows, demonstrated effectively by building a data source for the Tavily API.

Does the data source build process include automated code review?▼

Yes, the data source build process includes automated code review as part of its quality assurance, managing iterative checks to ensure high code quality before a connector is activated.

What are the limitations of automating data source development?▼

Automating data source development focuses strictly on orchestrating connector specs, workflows, and documentation for specified third-party services; it does not manually override the iterative agent-based testing required for final delivery.

Related Skills

Explore More Software Engineering Skills→
rampstackcorampstackco
523

security-baseline

Establish a security baseline for websites and web apps.

Official
Advanced
patrykkopycinskipatrykkopycinski
6

kibana-alerting

Configure Kibana alerting rules and connectors for threshold, anomaly, and ML conditions.

Community
Intermediate
viktorbezdekviktorbezdek
10

moai-workflow-testing

Automate end-to-end development workflows integrating testing, debugging, profiling, and code review.

Community
Advanced
databrickslabsdatabrickslabs
60

build_connector_package

Create a pyproject.toml file and build a source connector as a Python package.

Official
Intermediate