Migrate
launchdarkly/agent-skillsMigrating an AI app from hardcoded prompts to a managed system is easy with this guide. It walks you through five clear stages. You start by auditing your code to find all hardcoded values. Then you wrap the provider call with a new SDK and launch configuration. Next you move tool definitions into the managed config. After that you add per-request tracking for duration, tokens, and errors. Finally you attach evaluators to test and score your prompts automatically.
This skill works best for Python and Node.js applications. It supports many popular frameworks like LangChain, LangGraph, and CrewAI. You will avoid common mistakes like tracker scope errors and wrapper reuse. Follow the stages one by one and confirm each step before moving on.
Add Migrate skill to your workflow
Global
mkdir -p ~/.claude/skills/migrateProject
mkdir -p .claude/skills/migrateSource Repository
More AI & Agent Building Claude Code Skills
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly