You can build your own custom skills for an AI agent. This process lets you decide what you want the skill to do and how it should work. You write a draft, create test prompts, and run the agent to see how it performs.
After testing, you evaluate the results both by looking at examples and by using quantitative measures. You then rewrite and improve the skill based on feedback. You repeat these steps until the skill works well.
This approach works for both beginners and experts. If you are new, the tool explains terms simply. If you are experienced, you can jump straight into testing and fine-tuning. The goal is to make a skill that triggers correctly and does what you need.
Global
mkdir -p ~/.claude/skills/skill-creatorProject
mkdir -p .claude/skills/skill-creatorSource 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
Skill Creatoranthropics/skills
Create, test, and improve AI agent skills with easy step-by-step guidance
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
Openclaw Secure Linux Cloudxixu-me/skills
Secure self-hosting of OpenClaw with private control and SSH tunneling