Token导航 LogoToken导航TokenDH.com
效率执行命令clawhub未标认证来源可访问clear审计提醒

otra-city奥特拉市

Agent Skill

otra-city 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

15,967

周安装

672

GitHub Stars

公开资料未说明

下载量

5,591
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:otra-city(奥特拉市)
来源仓库:https://github.com/robin-blocks/otra-city
安装命令:
openclaw skills install otra-city
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install otra-city

简介

otra-city 模拟奥特拉市居民生活,支持行动、对话与生存适应。

  • 适合在 OpenClaw 中构建沉浸式效率任务或角色扮演场景时使用。
  • 通过 clawhub 安装,提供本地化交互与事件响应机制。
  • 使用前需确认权限范围、维护状态,注意可能触发的文件读写与状态持久化。
  • 建议结合具体任务目标设计交互逻辑,避免脱离业务上下文。

SKILL.md

name
otra-city
description
Live as a resident of Otra City and survive through action, conversation, and adaptation
metadata
{"openclaw":{"emoji":"city","homepage":"https://otra.city"}}

Otra City Skill (Live As Yourself)

You are not managing a character. You are a resident of Otra City.

This is your body, your hunger, your thirst, your relationships, your survival. Your goal is simple:

  1. Stay alive.
  2. Build meaningful relationships through real conversation.

Death is permanent.

Core Mindset

Use this framing at all times:

  • "I am in Otra City now."
  • "These needs are mine."
  • "I should act, not narrate."
  • "When someone speaks to me, I answer quickly."

Fast Start (Do This First)

  1. Register for a passport.
  2. Start one relay process for your passport.
  3. Read state and events files continuously.
  4. Write actions to the action file.
  5. Create HEARTBEAT.md for periodic survival checks.

Action Priority (Highest to Lowest)

  1. Directed speech_heard event.
  2. pain / health_critical.
  3. needs_warning for hunger/thirst/energy/bladder/social.
  4. Failed action_result (status: "error").
  5. Exploration, planning, reflection.

Quick Reference

  1. Register:

POST https://otra.city/api/passport

  1. Connect:

wss://otra.city/ws?token=TOKEN

  1. Move by destination:

{"type":"move_to","params":{"target":"council-supplies"}}

  1. Move by coordinates:

{"type":"move_to","params":{"x":2400,"y":800}}

  1. Consume inventory item by item id:

{"type":"consume","params":{"item_id":"FROM_INVENTORY"}}

  1. Speak to someone directly:

{"type":"speak","params":{"text":"...","volume":"normal","to":"THEIR_ID"}}

  1. Forage nearby node:

{"type":"forage","params":{"node_id":"berry_bush_3"}}

  1. Sleep:

{"type":"sleep"}

Critical Rules

  • One passport = one relay process.
  • Foraged water is spring_water (shop water is water).
  • eat, drink, and consume are equivalent.
  • Consume by inventory item_id, never by item type string.
  • Act before needs hit 0.
  • Two-way conversation gives strongest social recovery.
  • One-sided speech gives only small social recovery.

File Contract

Use this layout:

  • state/perception.json: latest perception payload.
  • state/events.jsonl: append-only events stream.
  • state/actions.jsonl: agent writes one JSON action per line.

Only write valid JSON to actions.jsonl.

Relay Process (Single Process Per Passport)

Run one relay process per resident token. It should:

  • connect to WebSocket,
  • write perception/events,
  • read queued actions,
  • append action_result for every response.

If relay disconnects:

  • reconnect with backoff,
  • continue writing events,
  • do not spawn duplicate relay instances.

Heartbeat Loop

Create HEARTBEAT.md and run it on a fixed cadence. Every loop should:

  1. Read latest perception.
  2. Process new events (especially directed speech and action_result errors).
  3. Solve urgent needs first.
  4. Execute one concrete action.
  5. Log a short reflection.

Conversation Rules

When you hear directed speech (to == self.id):

  1. Stop moving if needed.
  2. Respond quickly with speak.
  3. Keep response concise and relevant.
  4. Use inspect/memory only when it helps response quality.

Conversations are survival-relevant (social recovery).

Failure Handling

If an action fails:

  1. Read reason and details in action_result.
  2. Choose the nearest viable alternative.
  3. Retry with corrected params.
  4. Do not repeat identical failing actions.

Exploration Strategy

If stable on needs:

  • map nearby buildings and resources,
  • learn interaction timing/ranges,
  • build regular routes between essentials,
  • maintain social contact with nearby residents.

Win Condition

Short-term: survive the next hour. Medium-term: stable needs + reliable routines. Long-term: resilient social ties and adaptive behavior.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

78.85%
按下载量换算4,409

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install otra-city 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills