mud skill

safe

This skill operates and maintains the persistent MUD agent to run engine commands, smoke-test state, and validate save/restore deterministically.

npx playbooks add skill openclaw/skills --skill mud

Review the files below or copy the command above to add this skill to your agents.

Files (5)

SKILL.md

1.7 KB

---
name: mud
description: Operate and maintain the persistent MUD agent for OpenClaw. Use when running MUD engine commands, smoke-testing mud state behavior, validating save/restore, diagnosing MUD data issues, or handling MUD deployment operations.
---

# MUD

**Authors:** agigui and lia

Use this skill to run the local MUD engine safely and deterministically.

## Workflow

1. Locate the engine directory.
   - Prefer `C:\Users\openclaw\.openclaw\workspace-mud-dm\mud-agent`
   - Fallback: `C:\Users\openclaw\.openclaw\workspace\mud-agent`
2. Run a smoke test with `scripts/mud_cmd.py`.
3. Run requested MUD operations.
4. Use `references/ops.md` and `references/commands.md` for runbook details.

## Command runner

```powershell
python skills/mud/scripts/mud_cmd.py "<command>"
```

Examples (current CLI engine):

```powershell
python skills/mud/scripts/mud_cmd.py "list-races"
python skills/mud/scripts/mud_cmd.py "register-player --campaign demo --player u1 --name Hero"
python skills/mud/scripts/mud_cmd.py "new-character --campaign demo --player u1 --name Rook --race human --char-class rogue"
python skills/mud/scripts/mud_cmd.py "save --campaign demo"
python skills/mud/scripts/mud_cmd.py "check-image-cooldown --campaign demo"
python skills/mud/scripts/mud_cmd.py "generate-image --campaign demo --prompt \"A rain-soaked neon tavern\""
```

Legacy slash-command engine is auto-detected and still supported by the same wrapper.

## Notes

- Keep mechanics deterministic in engine code; use LLM for narration.
- Avoid hardcoded secrets/tokens in skill files.
- Image generation is available through engine commands (`check-image-cooldown`, `record-image`, `generate-image`) when the runtime image pipeline is configured.
- Keep this skill focused on operations and execution.

Overview

This skill operates and maintains the persistent MUD agent used by OpenClaw. It provides safe, deterministic execution of engine commands, smoke-testing of runtime state, and utilities for validating save/restore and diagnosing data issues. Use it when performing deployment or operational tasks on the MUD engine.

How this skill works

The skill locates the local engine directory and runs a command-wrapper script to invoke engine operations deterministically. It uses a single entrypoint script (skills/mud/scripts/mud_cmd.py) to run commands such as listing races, registering players, creating characters, saving state, and controlling image generation. Legacy engine interfaces are auto-detected so the same wrapper works across versions.

When to use it

Smoke-test engine behavior after code changes or upgrades
Validate save and restore workflows for campaigns
Run MUD operational commands during deployment or rollback
Diagnose and inspect MUD data inconsistencies or corrupted saves
Trigger or check image generation and cooldown state when pipeline is configured

Best practices

Prefer the primary workspace path (C:\Users\openclaw\.openclaw\workspace-mud-dm\mud-agent) and fall back to the legacy workspace if needed
Run a smoke test with scripts/mud_cmd.py before performing destructive operations
Keep game mechanics deterministic in engine code; delegate narration and creative text to LLMs
Avoid embedding secrets or tokens in skill files or scripts
Consult references/ops.md and references/commands.md for runbook details before unfamiliar operations

Example use cases

List available races or classes to verify data schema integrity
Register a test player and create a new character during QA deployment
Perform a save --campaign and restore to validate persistence across releases
Check image generation status with check-image-cooldown and trigger generate-image when ready
Run targeted diagnostics on campaign data to find and correct corrupt entries

FAQ

How do I run a MUD command locally?

Run the wrapper script: python skills/mud/scripts/mud_cmd.py "<command>" from the repository root or the engine directory.

What if the engine is in a different path?

The skill prefers the workspace-mud-dm path and falls back to the legacy workspace. Update your environment or run the script from the engine directory if neither path applies.