skills.rest
launchdarkly-labs
launchdarkly-labsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

aiconfig-create

Create LaunchDarkly AI Configs with variations, model configurations, and targeting via REST API.

Updated Feb 4, 2026
Search Tags:#API#config-management#targeting#ai-configs#variations#aiconfigs#LaunchDarkly
One-click install
npx skills add https://github.com/launchdarkly-labs/aiconfigs-skills --skill aiconfig-create
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aiconfig-create
Source: https://github.com/launchdarkly-labs/aiconfigs-skills/tree/main/aiconfig-create
Command: npx skills add https://github.com/launchdarkly-labs/aiconfigs-skills --skill aiconfig-create

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables teams to automate the creation of LaunchDarkly AI Configs, including multiple variations, model configurations, and targeting rules, reducing manual setup time and human errors.

Core Features & Use Cases

  • Agent Mode: Create configs with persistent instructions and optional tools for orchestrated AI workflows.
  • Completion Mode: Create configs that drive direct LLM calls with structured messages and optional tools.
  • Variation Management: Define and deploy multiple variations to evaluate performance and outcomes.

Quick Start

Use the aiconfig-create skill to define a new AI Config by providing a unique key, a human-readable name, mode, and a default variation (agent or completion). Then call the LaunchDarkly API to create the config and obtain its URL.

Frequently Asked Questions about aiconfig-create

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

FAQPage Schema
How do I automate LaunchDarkly AI Config creation with variations?▼

Automate AI Config creation by providing a unique key, name, mode (agent or completion), and default variation to the aiconfig-create Skill, which handles REST API calls to LaunchDarkly and returns the config URL without manual setup.

What's the difference between agent mode and completion mode for AI Configs?▼

Agent mode creates configs with persistent instructions and optional tools for orchestrated AI workflows; completion mode drives direct LLM calls with structured messages and optional tools, letting you choose based on your orchestration needs.

What permissions do I need to create AI Configs in LaunchDarkly?▼

You need a LaunchDarkly API token with ai-configs:write permission to authenticate requests and create configs via the REST API through this Skill.

Can I deploy multiple variations of an AI Config?▼

Yes, the Skill supports defining and deploying multiple variations with different model configurations and targeting rules, enabling performance evaluation and outcome testing across variations.

Do I need to configure tools for my AI Config variations?▼

Tools are optional for both agent and completion modes; you can define variations with or without tools depending on whether your workflow requires external tool integration.

Related Skills

Explore More Software Engineering Skills→
launchdarkly-labslaunchdarkly-labs

aiconfig-targeting

Configure LaunchDarkly AI Config targeting rules via API.

Official
Intermediate
Snowflake-LabsSnowflake-Labs
12

read-ors-configuration

A concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略

Official
Intermediate
launchdarkly-labslaunchdarkly-labs

aiconfig-segments

Create, update, and query LaunchDarkly segments for AI Config targeting.

Official
Intermediate
launchdarkly-labslaunchdarkly-labs

aiconfig-api

Manage LaunchDarkly AI Configs via REST API with authentication headers.

Official
Intermediate