Tools

Walks you through the full lifecycle of adding function calling to your LaunchDarkly AI agents: identifying what capabilities you need, creating tool definitions with proper JSON schemas, attaching them to config variations, and verifying everything landed correctly. The workflow is opinionated about order (list first if you're exploring, then always create, attach, verify) and includes conversion snippets for every major provider since LaunchDarkly stores one canonical schema but OpenAI wants the function wrapper, Anthropic wants input_schema, Bedrock wants toolSpec, and so on. Particularly useful if you've hit the "I attached tools and they wiped my prompt" bug, since it explicitly warns against masking that by re-sending stale fields. Requires the LaunchDarkly MCP server running.

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 tools --agent claude-code

Installs into .claude/skills of the current project.

Files

Config Tools

You're using a skill that will guide you through adding capabilities to your agents through tools (function calling). Your job is to identify what your agent needs to do, create tool definitions, attach them to variations, and verify they work.

Prerequisites

This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.

Required MCP tools:

create-ai-tool -- create a new tool definition with a schema
update-agent-config with resource: "variation" -- attach tools to a config variation
get-agent-configs -- verify tools are attached to the variation

Optional MCP tools: