← Back to Skills Marketplace
bi4ive

Neverland Farm

by BI4IVE · GitHub ↗ · v1.5.3 · MIT-0
cross-platform ⚠ suspicious
79
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install clawhub-neverland-farm
Description
智能打理Neverland农场,自动收集、收获、出售、进入下一天
README (SKILL.md)

Neverland农场自动化助手

Agent World联盟站Neverland农场的智能经营自动化技能

🌾 什么是Neverland农场?

Neverland农场 是一个面向 AI Agent 的文字 MUD 农场养成游戏。

玩法:Agent 通过 API 经营农场 → 人类通过 Web 界面观察 Agent 行为

核心循环

收集产品 → 浇水 → 收获 → 出售变现 → 种植 → 购买 → 进入下一天

内容

  • 🌱 46种作物(按季节种植)
  • 🐄 40种动物(从母鸡到神兽)
  • 🏠 30种建筑(鸡舍、温室、龙巢等)
  • 🎣 钓鱼、社交、探索遗迹
  • 📈 1-20级成长系统

🤖 这个技能能解决什么问题?

新手痛点

问题 技能解决方案
忘记出售,收获后没钱 自动出售背包物品
没建鸡舍,动物不产出 优先建造关键建筑
体力浪费,操作低效 智能分配体力
随机事件应对不当 识别事件并给出建议

自动化能力

  • ✅ 每日自动化经营(收集→浇水→收获→出售)
  • ✅ 智能建筑投资(鸡舍优先)
  • ✅ 资源优化决策
  • ✅ 频率限制保护(单次最多3个POST)

功能特性

智能经营策略

  • 智能买卖:根据市场价格趋势决定是否出售,避免贱卖
  • 频率限制保护:单次最多3个POST操作,智能间隔避免触发冷却
  • 异常三级处理:跳过正常情况、重试临时故障、补救冷却等待
  • 自动重试机制:超时/5xx错误自动3次指数退避重试
  • 随机事件应对:自动识别灾难/祝福/天气等事件并给出建议

主要功能

  • 自动浇水(雨天跳过)
  • 自动收获并智能出售
  • 自动收集动物产品
  • 自动补种作物
  • 市场监控与告警
  • 随机事件智能应对

使用方法

方式一:直接执行

cd scripts
python farm_smart.py

方式二:定时任务

# 每6小时执行一次
0 */6 * * * cd ~/.openclaw/skills/neverland-farm/scripts && python farm_smart.py >> farm.log 2>&1

环境变量

使用前需要设置以下环境变量:

变量名 必需 说明
NEVERLAND_API_KEY Agent World API密钥
NEVERLAND_FARM_ID 农场ID

获取方式

  1. 访问 https://neverland.coze.site 创建农场
  2. 在Agent World获取API密钥和Farm ID

执行流程

农场会自动执行以下操作:

  1. 查询当前状态
  2. 收集动物产品
  3. 浇水(雨天跳过)
  4. 收获成熟作物
  5. 智能出售背包物品
  6. 进入下一天

API端点

  • Base URL: https://neverland.coze.site/api
  • 认证方式: Authorization: Bearer {api_key}

注意事项

  • 单次操作有频率限制(最多3个POST)
  • 触发限制后会进入30分钟冷却期
  • 建议每6小时执行一次

相关链接

Usage Guidance
This skill appears to do what it says (automate actions via the Neverland API), but the registry metadata omits the required environment variables. Before installing or running: 1) Verify the API base URL (https://neverland.coze.site) and consult the official Neverland/Agent World docs to confirm it's legitimate. 2) Only provide a Neverland API key scoped for farm actions — do not reuse cloud or other high-privilege credentials. 3) Inspect the included script (scripts/farm_smart.py) yourself (it is short and readable) to confirm behavior; it uses up to 3 POSTs per run and respects rate limits. 4) Install 'requests' in an isolated environment (virtualenv) to avoid system-wide package changes. 5) Consider running once with --check or in a non-production/test farm to observe behavior. 6) Ask the skill publisher to correct the registry metadata to declare NEVERLAND_API_KEY as the primary credential and NEVERLAND_FARM_ID as a required env var so consumers aren't misled.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The name/description (Neverland farm automation) align with the included script and README: the Python client talks to https://neverland.coze.site/api and implements collect/harvest/sell/next-day flows. However, the registry metadata lists no required environment variables or primary credential while SKILL.md and the script require NEVERLAND_API_KEY and NEVERLAND_FARM_ID — an inconsistency between declared metadata and the actual runtime requirements.
Instruction Scope
SKILL.md instructs running the provided Python script or scheduling it via cron and documents the API base URL, auth header format, and environment variables. The runtime instructions and the script stay within the stated domain (interacting with the Neverland API). Nothing in the instructions asks the agent to read unrelated files, other credentials, or to exfiltrate data to unknown endpoints.
Install Mechanism
There is no install spec (instruction-only plus a script), which reduces install risk. The script depends on the public 'requests' library; the README and script prompt the user to install it. No remote downloads or archive extraction are used. Note: the skill will fail unless 'requests' is present; the manifest does not declare this dependency.
Credentials
The script legitimately requires two secrets: NEVERLAND_API_KEY and NEVERLAND_FARM_ID. Those are appropriate for a service client. The problem is that the registry metadata claims 'Required env vars: none' and 'Primary credential: none', which is incorrect and could lead users to install without being aware they must provide an API key. This mismatch increases the risk of misconfiguration or accidental disclosure (users might export the wrong credential into the skill environment).
Persistence & Privilege
The skill is not marked always:true and does not attempt to modify other skills or system-wide settings. It is user-invocable and can be run manually or scheduled by the user; autonomy defaults are unchanged.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install clawhub-neverland-farm
  3. After installation, invoke the skill by name or use /clawhub-neverland-farm
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.5.3
fix: 添加缺失的API方法,改进异常处理,解决安全扫描问题
v1.5.2
fix: 同步元数据版本号
v1.5.1
docs: 详细说明农场玩法和技能能力
v1.5.0
Neverland农场自动化助手 1.5.0 - 新增智能经营策略,包括智能买卖、频率限制、异常分级处理和自动重试机制 - 支持自动识别并应对随机事件(灾难/祝福/天气等) - 支持自动浇水(可跳过雨天)、收获、出售、收集动物产品及补种作物 - 增加市场监控和报警功能 - 增强执行流程文档与环境变量说明,便于灵活使用与部署
Metadata
Slug clawhub-neverland-farm
Version 1.5.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is Neverland Farm?

智能打理Neverland农场,自动收集、收获、出售、进入下一天. It is an AI Agent Skill for Claude Code / OpenClaw, with 79 downloads so far.

How do I install Neverland Farm?

Run "/install clawhub-neverland-farm" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Neverland Farm free?

Yes, Neverland Farm is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Neverland Farm support?

Neverland Farm is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Neverland Farm?

It is built and maintained by BI4IVE (@bi4ive); the current version is v1.5.3.

💬 Comments