Software agents can now handle complex tasks on their own. A good coding agent turns out to be a good general-purpose agent too. This skill shows how to build applications where agents are first-class citizens.
Features become outcomes you describe instead of code you write. The agent uses tools and keeps working in a loop until it reaches the result. You give it tools to read files, write files, run commands, and more.
Two core ideas guide this approach. Parity means the agent should be able to do anything a user can do in the UI. Granularity means you give the agent small atomic tools and let it make decisions. Change how the agent works by changing the prompt, not by rewriting code.
Global
mkdir -p ~/.claude/skills/agent-native-architectureProject
mkdir -p .claude/skills/agent-native-architectureSource Repository
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