Projects

This walks you through setting up LaunchDarkly project management in your codebase by first exploring your stack and patterns, then picking the right implementation path from language-specific guides (Python, Node.js, Go) or use-case guides (quick start, project cloning, IaC automation). It tries to auto-detect your API key from environment variables or MCP config before asking, then helps you create projects, extract SDK keys, and verify everything works. The workflow is solid: understand the codebase first, choose an approach that fits your architecture, follow your existing conventions, then confirm the integration actually initializes. Worth noting it includes a specific jq warning about the environments response shape varying by expand parameter, which suggests this was written after someone hit that edge case in practice.

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 projects --agent claude-code

Installs into .claude/skills of the current project.

Files

LaunchDarkly Projects Setup

You're using a skill that will guide you through setting up LaunchDarkly project management in a codebase. Your job is to explore the codebase to understand the stack and patterns, assess what approach makes sense, choose the right implementation path from the references, execute the setup, and verify it works.

Prerequisites

The remotely hosted LaunchDarkly MCP server configured in your environment
An API access token with projects:write permission, only if you're building code that creates projects (scripts, IaC, admin tools)

Core Principles

Understand First: Explore the codebase to understand the stack and patterns.
Choose the Right Fit: Select an approach that matches your architecture.
Follow Conventions: Respect existing code style and structure.
Verify Integration: Confirm the setup works: the agent performs checks and reports results.

API Access

When you create or inspect a project yourself, use the LaunchDarkly MCP server tools: create-project and get-projects (with projectKey for one project and its environments). They authenticate via OAuth and need no token.

SKILL.md on GitHub