If you're sitting on hardcoded OpenAI or Anthropic calls and want to move model, prompt, and tool definitions into LaunchDarkly, this walks you through a five stage migration: audit what's hardcoded, wrap the call with the SDK, externalize tool schemas, wire tracking for tokens and duration, then attach evaluators. It knows the common footguns in LangChain and LangGraph agent loops, especially where to scope the tracker so you don't accidentally mint a new run ID on every iteration. Python and Node.js get worked examples for direct provider calls, LangGraph agents, and CrewAI. Other languages stop at install commands. The skill prepares inputs for each LaunchDarkly write but doesn't auto invoke the sibling skills, so you'll manually run configs-create and the rest at the right checkpoints.
npx -y skills add launchdarkly/agent-skills --skill migrate --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot