Run a single experiment iteration with one simple command. The AI agent reviews past results, decides a change, edits the target file, and evaluates the outcome. Each run is one small step to improve your code or system.
This tool helps you explore improvements methodically. It follows a strategy that starts with easy wins and moves to bigger changes. You can keep or discard each result. The agent learns from every attempt.
Anyone doing research or optimization can benefit. The process is automated and transparent. You stay in control of what changes to accept.
Add Run skill to your workflow
Global
mkdir -p ~/.claude/skills/runProject
mkdir -p .claude/skills/runSource 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