技能详情（站内镜像，无评论）
作者：Andrew Goetz @andrew-goetz-com
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.1
统计：⭐ 0 · 241 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：可疑 · OpenClaw ：良性
Package：andrew-goetz-com/mud
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：良性
OpenClaw 评估
The skill's files, instructions, and minimal requirements are coherent with its stated purpose of operating a local MUD engine; it runs local engine code and does not request unrelated credentials or network installs.
目的
Name/description match the actual behavior: the skill is an operations wrapper to run a local MUD engine (either by importing a legacy MudAgent or invoking mud_agent.py). It requests no external credentials, binaries, or installs, which is appropriate for a local ops helper.
说明范围
SKILL.md instructs the agent to locate the engine directory and run the included wrapper script with a command string. The script only reads mud_agent.py to detect engine style and then either imports it or runs it as a subprocess. There is no instruction to read unrelated system files, exfiltrate data, or contact external endpoints in the skill itself.
安装机制
No install spec is present (instruction-only plus a small helper script). Nothing is downloaded or written to disk by the skill itself, which minimizes install risk.
证书
The skill requires no environment variables or credentials, which is appropriate. One important operational note: the script executes or imports local code (mud_agent.py) found in the workspace. That means the effective privileges and behavior depend entirely on the contents of that engine file — importing or running it will execute arbitrary code from the local project. That is expected for an ops wrapper, but users should ensure the engine c…
持久
always:false (default) and no requests to modify other skills or system-wide agent settings. The skill does not request permanent presence or elevated platform privileges.
综合结论
This skill appears to do what it says: it runs your local MUD engine. Before using it, inspect the local mud_agent.py (and any engine code) in the referenced workspace paths, because the helper will import or execute that file — which runs arbitrary local code. Only run this skill if you trust the engine source; prefer running it as a non-administrative user or in a sandboxed environment. Also verify there are no unexpected network calls or ha…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「MUD」。简介：Operate and maintain the persistent MUD agent for OpenClaw. Use when running MU…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/andrew-goetz-com/mud/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
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:Usersopenclaw.openclawworkspace-mud-dmmud-agent`
- Fallback: `C:Usersopenclaw.openclawworkspacemud-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.