Many hard problems have many possible solutions. The Tree of Thoughts method helps you explore different ideas before picking the best one. It works like growing a tree where each branch is a new idea. You then prune the weak branches and grow the strong ones.
Multiple agents propose different approaches. A meta-judge creates rules for evaluating them. Judges then vote on the best ideas. The winning idea gets expanded into a full solution. If no clear winner, ideas are combined. This gives you a thorough and fair result.
Global
mkdir -p ~/.claude/skills/tree-of-thoughtsProject
mkdir -p .claude/skills/tree-of-thoughtsSource 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