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.
npx -y skills add launchdarkly/agent-skills --skill tools --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot