Configs Create

This walks you through creating AI configs in LaunchDarkly, helping you pick between agent mode (for frameworks like LangGraph that expect instruction strings) and completion mode (for direct API calls with message arrays). It uses the setup-ai-config tool to create the config and first variation in one shot, setting model, prompts, and parameters. The biggest gotcha: newly created configs default to a disabled variation, so you'll get enabled=False from the SDK until you run the targeting skill to point at your actual variation. It's opinionated about moving fast, using reasonable defaults when you don't specify variation keys or names, and completing the entire workflow without stopping to ask for details it can infer.

skills.sh installs: 1.3K
GitHub stars: 19
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add launchdarkly/agent-skills --skill configs-create --agent claude-code

Installs into .claude/skills of the current project.

Files

Create Config

You're using a skill that will guide you through creating a config in LaunchDarkly. Your job is to understand the use case, choose the right mode, create the config and its variations, and verify everything is set up correctly.

⚠️ This skill creates a config — it does not make it servable. A freshly-created config has its fallthrough pointing at an auto-generated disabled variation, not at the variation you just created. The SDK will return ai_config.enabled=False on every evaluation until you flip targeting on and point the fallthrough at your new variation. This is not a bug — it's the default state. You must run /configs-targeting (or the equivalent REST / CLI call shown in Step 5) before verifying against the SDK, or verification will look like the LD-served path is broken when it isn't. The single most common failure mode users hit with this skill is skipping the targeting step and spending time debugging enabled=False in their application code.