Tree of Thoughts Reasoning
Systematic ToT reasoning framework with 6 phases: explore, prune, expand, evaluate, adaptive strategy selection, and synthesis with parallel agent dispatch
What is it?
Systematic ToT reasoning framework with 6 phases: explore, prune, expand, evaluate, adaptive strategy selection, and synthesis with parallel agent dispatch Built for use cases involving tree-of-thoughts, systematic-reasoning, multi-agent, exploration, decision-making.
How to use it?
Before starting, ensure the directory structure exists:
mkdir -p .specs/research .specs/reports
Naming conventions:
- Proposals:
.specs/research/{solution-name}-{YYYY-MM-DD}.proposals.[a|b|c].md - Pruning:
.specs/research/{solution-name}-{YYYY-MM-DD}.pruning.[1|2|3].md - Selection:
.specs/research/{solution-name}-{YYYY-MM-DD}.selection.md - Evaluation:
.specs/reports/{solution-name}-{YYYY-MM-DD}.[1|2|3].md
Where:
{solution-name}- Derived from output path (e.g.,users-apifrom outputspecs/api/users.md){YYYY-MM-DD}- Current date
Note: Solutions remain in their specified output locations; only research and evaluation files go to .specs/
Key Features
- Systematic ToT reasoning framework with 6 phases: explore, prune, expand, evaluate, adaptive strategy selection, and synthesis with parallel agent dispatch
- Seamless integration with Claude's development workflow
- Comprehensive guidelines and best practices for tree of thoughts reasoning
Related Skills
More from AI & MLMulti-Agent Architecture Patterns
Reference guide for multi-agent architecture patterns including Supervisor/Orchestrator, Peer-to-Peer/Swarm, and Hierarchical, with context isolation principles and Claude Code implementation
First Principles Hypothesis Framework
First Principles reasoning framework with hypothesis generation, logical and evidence validation, layered trust audit (L0/L1/L2), and reliability scoring
prompt-engineering
Teaches well-known prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles