ALFWorld Embodied Agent

by microsoft

ALFWorld Embodied Agent is an AI Engineering skill for Claude Code, published by microsoft in SkillOpt.

16K stars1.5K forkson microsoft/SkillOptAdded 2026/08/14Repository updated 2026/08/13

View source on GitHub Download repo ZIP

agent-skillsself-evolving-agents

Install in seconds

Install ALFWorld Embodied Agent

Copy ALFWorld Embodied Agent into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/microsoft/SkillOpt/tree/main/ckpt/alfworld ~/.claude/skills/alfworld

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/microsoft/SkillOpt.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: ckpt/alfworld/gpt5.5_skill.md in microsoft/SkillOpt
Installs to: ~/.claude/skills/alfworld
Collection: One of 12 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What ALFWorld Embodied Agent does

ALFWorld Embodied Agent guides agents in the ALFWorld text environment to complete household tasks by navigating rooms, interacting with objects, and using appliances. Use it when an agent needs to choose admissible actions for pick-and-place, clean, heat, cool, or examine tasks.

ALFWorld Embodied Agent is cataloged under AI Engineering on DirSkills. ALFWorld Embodied Agent comes from a repository tagged agent-skills and self-evolving-agents.

Documentation

README

Excerpt

ALFWorld Embodied Agent Skill

Overview

This skill guides agents operating in the ALFWorld text-based embodied environment. The agent must complete household tasks by navigating rooms, interacting with objects, and using appliances. Actions must be chosen from the admissible action list provided at each step.

Output format: Always output <think>...</think> for reasoning, then <action>...</action> for the chosen action.

Task Types

Type	Goal	Key Steps
Pick & Place	Put object X in/on receptacle Y	Find X -> take X -> go to Y -> put X in/on Y
Pick Two & Place	Put two instances of X in/on Y	Find X1 -> take -> place -> find X2 -> take -> place

This is the opening of the README. Read the full README on GitHub.

Frequently asked about ALFWorld Embodied Agent

What else does microsoft publish alongside ALFWorld Embodied Agent?
ALFWorld Embodied Agent is one of 12 skills that DirSkills catalogs from microsoft/SkillOpt, the repository it ships in. Its siblings there include DocVQA, Document Rewriter and Live Mathematical MCQ Heuristics. Each one is a separate skill with its own page in this directory, installs the same way ALFWorld Embodied Agent does, and is maintained by microsoft in that same repository. The rest of the collection is listed on the microsoft/SkillOpt page.
How does ALFWorld Embodied Agent compare to other AI Engineering skills?
ALFWorld Embodied Agent ranks #276 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of ALFWorld Embodied Agent against them. Open each page to compare what they document and how they install.