You can test and improve AI prompts by measuring their results. This skill helps you compare different versions of a prompt using small test sets. It tracks key metrics to show which prompt works best.
It also checks how well a knowledge retrieval system finds the right information. You can measure relevance, accuracy, and completeness. These checks help fix problems in the retrieval step before changing the prompt.
For AI agents that use tools, this skill validates their setup and workflow. All tools work with any AI model. You just provide the pricing data to get cost estimates.
Global
mkdir -p ~/.claude/skills/senior-prompt-engineerProject
mkdir -p .claude/skills/senior-prompt-engineerSource 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