Menu

Individual skill

tree-of-thoughts

0upvotes

Search over multiple reasoning paths — branch, evaluate, backtrack — for problems where one linear chain isn't enough.

skills/tree-of-thoughts/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
56
Repository last updated
Oct 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

## Overview

Tree-of-Thoughts (ToT) generalizes chain-of-thought from a single reasoning path
to a search tree. Instead of committing to one chain, the model generates multiple
candidate "thoughts" at each step, evaluates which partial solutions look
promising, and explores the best ones — backtracking when a branch dead-ends. It's
deliberative search applied to language-model reasoning: the model proposes, a
value function (often the model itself) scores, and a search algorithm (BFS or
DFS) manages the exploration.

The payoff comes on tasks requiring planning, lookahead, or creative exploration
— puzzles like Game of 24, crossword-style constraint satisfaction, or multi-step
plans where early choices determine success. On such tasks ToT substantially
outperforms single-chain CoT. The price is compute: ToT multiplies inference cost
Back to top