Menu

Individual skill

react-pattern

0upvotes

Build agents that interleave reasoning and acting — the ReAct loop of thought, action, and observation.

skills/react-pattern/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Not checked yet
Last checked
Nov 8, 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)
54
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

ReAct (Reason + Act) is the foundational agent loop: the model alternates between
thinking (a reasoning trace about what to do next), acting (calling a tool), and
observing (reading the tool's result), repeating until the task is done. The
interleaving is the point — reasoning guides which action to take, and
observations ground the next round of reasoning in reality instead of speculation.
A ReAct trajectory looks like: Thought: "I need the current price, so I'll
search." Action: search("..."). Observation: results. Thought: "Got it, now
I'll..."

It's deliberately simple — no planner, no memory system, no multi-agent
choreography — which is why it's the default starting architecture for tool-using
agents and the baseline everything else is compared against. Few-shot