Agent skill

zork

Play Zork text adventure via dfrotz. Use /zork <command> to play (e.g., /zork go north), /zork for status, /zork new to restart, /zork setup to configure Obsidian sync.

View SKILL.md on GitHub Repository
Stars 11
Forks 1

Install this agent skill to your Project

npx add-skill https://github.com/jonathanprozzi/claude-utils/tree/main/skills/zork

SKILL.md

Zork Interactive Fiction Skill

Play the classic text adventure Zork I via dfrotz, with persistent save state and optional Obsidian integration for capturing learnings.

Quick Reference

Command What it does
/zork look Look around current room
/zork go north Move north (or any direction)
/zork take lamp Pick up an item
/zork inventory Check what you're carrying
/zork Show current status (look + inventory)
/zork new Start a fresh game
/zork setup Configure Obsidian vault for sync

How to Play

Execute a single command:

bash
bash scripts/play.sh "go north"

Check current status:

bash
bash scripts/status.sh

Start a new game:

bash
bash scripts/new.sh

Configure Obsidian sync:

bash
bash scripts/setup.sh /path/to/your/vault

Game State

  • Save file: state/claude.sav.qzl - automatically saved after each command
  • Transcript: Append-only log of all commands and responses
  • Learnings: Your observations about the game (update with /zork reflect)

Obsidian Integration

If configured, transcript and learnings sync to your Obsidian vault as:

  • Claude Plays Zork Transcript.md
  • Claude Plays Zork Learnings.md

Run bash scripts/setup.sh to see current config or set a vault path.

Tips

  • Classic text adventure verbs: look, examine, take, drop, open, close, go, inventory
  • Directions: north, south, east, west, up, down, ne, nw, se, sw
  • You can abbreviate: n for north, i for inventory, l for look
  • Save happens automatically after each command

Purpose

This skill helps Claude build experiential intuition about text adventures and parser conventions, informing the design of AI companions in Emergent Quest.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

mattpocock/skills

setup-pre-commit

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

111,310 9,758
Explore
mattpocock/skills

migrate-to-shoehorn

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

111,310 9,758
Explore
mattpocock/skills

scaffold-exercises

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

111,310 9,758
Explore
mattpocock/skills

handoff

Compact the current conversation into a handoff document for another agent to pick up.

111,310 9,758
Explore
mattpocock/skills

obsidian-vault

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

111,310 9,758
Explore
mattpocock/skills

git-guardrails-claude-code

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

111,310 9,758
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results