Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

turnip-prophet萝卜先知

Agent Skill

turnip-prophet 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。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

17,856

周安装

767

GitHub Stars

公开资料未说明

下载量

6,259
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:turnip-prophet(萝卜先知)
来源仓库:https://github.com/nicholasjackson/turnip-prophet
安装命令:
openclaw skills install turnip-prophet
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 turnip-prophet

简介

turnip-prophet 基于《动物森友会》游戏算法预测萝卜价格走势。

  • 适合玩家制定种植与销售策略,优化游戏内收益。
  • 输入当前市场价格即可输出未来波动区间与建议操作。
  • 数据来源于公开算法而非实时联网,可能存在滞后。
  • 仅供娱乐参考,不构成真实投资建议。turnip-prophet 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
turnip-prophet
description
Predict Animal Crossing New Horizons turnip prices using the game's exact algorithm. Use when a user asks about turnip prices, ACNH turnips, stalk market, turnip predictions, when to sell turnips, or bell profit from turnips.
repository
https://github.com/nicholasjackson/openclaw-turnip-profit
metadata

Turnip Prophet - Animal Crossing Turnip Price Predictor

Predicts Animal Crossing: New Horizons turnip prices using the game's actual algorithm.

⚠️ IMPORTANT: Always Read Memory First!

Before doing ANYTHING, read the weekly data file:

memory/turnip-week.json

This contains the buy price, previous pattern, and all known prices for the current week. Do not ask the user for data you already have. Only ask for new/missing prices.

When the user gives a new price, update memory/turnip-week.json immediately with the new value before running the prediction.

Weekly Data Format (memory/turnip-week.json)

{
  "week_start": "2026-02-15",
  "buy_price": 96,
  "previous_pattern": 1,
  "prices": [84, 81, 78, null, null, null, null, null, null, null, null, null],
  "labels": ["Mon AM", "Mon PM", "Tue AM", "Tue PM", "Wed AM", "Wed PM", "Thu AM", "Thu PM", "Fri AM", "Fri PM", "Sat AM", "Sat PM"]
}

On Sundays, create a fresh file with the new buy price and reset prices to all nulls.

Triggers

Activate when user mentions:

  • "turnip prices" or "turnip price"
  • "ACNH turnips" or "Animal Crossing turnips"
  • "stalk market"
  • "turnip prophet" or "turnip prediction"
  • "bell profit" with context of turnips
  • Any question about when to sell turnips in Animal Crossing

Privacy & Data Storage

This skill stores local configuration data only on your machine in memory/turnip-config.json. No data is sent to external servers.

What gets stored (if you enable reminders):

  • Channel name (telegram/whatsapp/discord/signal)
  • Your user ID on that channel
  • OpenClaw binary path
  • Setup timestamp

Why: These values are needed so the cron reminders can send messages to the correct place without hard-coded values.

Where: Stored locally in the skill's memory directory on your OpenClaw instance. Not shared, not uploaded, not visible to anyone else.

How to disable/reset:

rm ~/.openclaw/workspace/skills/turnip-prophet/memory/turnip-config.json

Removing cron entries:

# Edit crontab and remove the turnip-prophet lines
crontab -e

Important: You must explicitly confirm the setup flow before any config is saved. Declining the setup offer means nothing is stored.

Credentials & Permissions

The skill itself does not request or store any API keys or credentials.

However, if you enable cron reminders, the installed cron jobs will:

  • Use your local openclaw CLI binary
  • Send messages using your existing OpenClaw configuration and credentials
  • Operate with whatever permissions your OpenClaw instance has

What this means:

  • Automated reminders will be sent as you, using your OpenClaw identity
  • The cron jobs require OpenClaw to be running and properly configured
  • Messages are sent through your configured channels (Telegram/WhatsApp/etc.) using your bot tokens or API credentials

You are granting permission for:

  • Automated message sending on your behalf
  • Using your existing messaging channel credentials
  • Running scheduled tasks that invoke openclaw gateway call message.send

If you're uncomfortable with automated messaging using your credentials, do not enable the cron reminders. The core prediction feature works fine without them.

Daily Reminders (Optional)

On first use, offer to set up daily reminders with an interactive flow:

Interactive Setup Flow (Agent Instructions)

On first trigger (when user asks about turnips for the first time):

  1. Check if already configured:
   test -f memory/turnip-config.json && echo "configured" || echo "not configured"
  1. If NOT configured, offer setup:

> "Want daily turnip reminders? I can ping you: > • Sunday 8am: Check Daisy Mae's price > • Mon-Sat noon + 8pm: Check Nook's prices > • Saturday 9:45pm: Final warning > > Reply 'yes' to set up, or 'no' to skip."

  1. If user says yes, auto-detect config:

- Channel: Extract from inbound context JSON "channel" field (telegram/whatsapp/discord/signal) - Target ID: Extract from inbound context JSON "sender_id" field - OpenClaw path: Run which openclaw or use /usr/local/bin/openclaw - Skill dir: Use the absolute path to this skill's directory

  1. If auto-detection fails:

- Ask user for missing values explicitly - Validate before proceeding

Store config in memory/turnip-config.json:

{
  "channel": "telegram",
  "target": "8577655544",
  "openclaw_bin": "/usr/local/bin/openclaw",
  "skill_dir": "/home/user/.openclaw/workspace/skills/turnip-prophet",
  "configured_at": "2026-02-23T10:30:00Z"
}

Generate and show cron entries: Show the user exactly what will be added, with their specific values. Example:

# Turnip Prophet reminders for telegram:8577655544
0 8 * * 0 /usr/local/bin/openclaw gateway call message.send --params '{"channel":"telegram","target":"8577655544","message":"🔔 Sunday! Check Daisy Mae'\''s turnip price (90-110 bells) and buy your turnips 🥬"}' 2>&1 | logger -t turnip-prophet
0 12 * * 1-6 /usr/local/bin/openclaw gateway call message.send --params '{"channel":"telegram","target":"8577655544","message":"🔔 Time to check Nook'\''s Cranny turnip prices!"}' 2>&1 | logger -t turnip-prophet
0 20 * * 1-6 /usr/local/bin/openclaw gateway call message.send --params '{"channel":"telegram","target":"8577655544","message":"🔔 Evening price check: Check Nook'\''s Cranny!"}' 2>&1 | logger -t turnip-prophet
45 21 * * 6 /usr/local/bin/openclaw gateway call message.send --params '{"channel":"telegram","target":"8577655544","message":"⏰ FINAL CALL: Turnips expire at 10 PM! Sell now or they'\''ll rot 🗑️"}' 2>&1 | logger -t turnip-prophet

Replace channel/target with detected values. Escape single quotes properly.

Show user what will be stored (before confirmation):

This will save:
• Channel: telegram
• User ID: 8577655544
• Location: memory/turnip-config.json (local only)

This data is stored locally on your machine and is needed so cron reminders can send messages to you.
You can delete the config file anytime with: rm memory/turnip-config.json

Continue? Reply 'confirm' to proceed, or 'cancel' to skip.

On confirmation:

  1. Write config to memory/turnip-config.json
  2. Generate a safe install command and show it to the user:
   # Save the cron entries to a temp file
   cat > /tmp/turnip-cron-$$.txt <<'TURNIP_EOF'
   [generated entries]
   TURNIP_EOF
   
   # Review the file
   cat /tmp/turnip-cron-$$.txt
   
   # If it looks good, install:
   (crontab -l 2>/dev/null; cat /tmp/turnip-cron-$$.txt) | crontab -
  1. Ask user to run the commands and confirm when done
  2. Reply: "✅ Reminders configured. You'll only get pings for missing data. Check crontab -l to verify installation. To remove: rm memory/turnip-config.json and remove the cron entries."

On rejection/cancel:

  • Reply: "No problem. No data was stored. You can set this up anytime by asking about turnip prices again."

Cron Handler (scripts/cron_handler.sh)

The cron script reads from memory/turnip-config.json for channel/target:

CONFIG_FILE="$SKILL_DIR/memory/turnip-config.json"
if [[ ! -f "$CONFIG_FILE" ]]; then
    echo "Config not found: $CONFIG_FILE" >&2
    exit 1
fi

CHANNEL=$(jq -r '.channel' "$CONFIG_FILE")
TARGET=$(jq -r '.target' "$CONFIG_FILE")
OPENCLAW_BIN=$(jq -r '.openclaw_bin' "$CONFIG_FILE")

Event types:

sunday-daisy:

  • Check if memory/turnip-week.json has a buy_price for current week
  • If missing: Send reminder "🔔 Sunday! Check Daisy Mae's turnip price (90-110 bells) and buy your turnips 🥬"
  • If already set: Stay silent

daily-check:

  • Determine which price slot is currently active (Mon AM/PM through Sat PM)
  • Check if that slot is filled in memory/turnip-week.json
  • If missing: Send reminder "🔔 [Day] [AM/PM]: Check Nook's Cranny turnip prices!"
  • If already filled: Stay silent

saturday-final:

  • Check how many prices are still null
  • If any missing OR no buy_price: Send "⏰ FINAL CALL: Turnips expire at 10 PM! Sell now or they'll rot 🗑️"
  • If all prices known: "⏰ Last chance to sell turnips tonight!"

Send via: "$OPENCLAW_BIN" gateway call message.send --params "{\"channel\":\"$CHANNEL\",\"target\":\"$TARGET\",\"message\":\"...\"}"

How It Works

The skill uses a Python implementation of the actual ACNH turnip price algorithm to predict future prices based on:

  • Your Sunday buy price (90-110 bells)
  • Any known sell prices from this week
  • Previous week's pattern (if known)

There are 4 price patterns:

  • Pattern 0 (Fluctuating): High-low-high-low-high waves
  • Pattern 1 (Large Spike): Decreasing then massive spike (up to 6x)
  • Pattern 2 (Decreasing): Consistently declining (bad week)
  • Pattern 3 (Small Spike): Decreasing then moderate spike (up to 2x)

Usage Instructions

When triggered:

  1. Read memory/turnip-week.json — get all known data
  2. Update the file if the user provided a new price
  3. Run the prediction with all known data
  4. Generate a chart and send it with the prediction summary

Running the Prediction

echo '{"buy_price": 96, "prices": [84, 81, 78, null, null, null, null, null, null, null, null, null], "previous_pattern": 1}' | python3 scripts/turnip_predict.py
  • prices array: [Mon AM, Mon PM, Tue AM, Tue PM, Wed AM, Wed PM, Thu AM, Thu PM, Fri AM, Fri PM, Sat AM, Sat PM]
  • Use null for unknown prices

Generating the Chart

After running the prediction, generate a chart image:

python3 scripts/generate_chart.py <buy_price> '<known_json>' '<mins_json>' '<maxs_json>' /tmp/turnip-chart.png
  • buy_price: Sunday buy price (integer)
  • known_json: array of 12 values, null for unknown (from memory/turnip-week.json prices)
  • mins_json: array of 12 min values from the prediction output
  • maxs_json: array of 12 max values from the prediction output
  • All script paths are relative to the skill directory: skills/turnip-prophet/

Then send the chart image via the message tool with a caption containing the prediction summary.

Always include the chart with every prediction update.

Presenting Results

Send the chart image via message tool, then reply with a conversational analysis. Don't be robotic — have a personality about it.

Format:

  1. Chart image with brief caption (buy price, known prices)
  2. Text reply with:

- Pattern odds as a bullet list with emoji reactions (😬🤞🚀💀 etc.) - Brief colour commentary — what the data actually means in plain English - "My take:" — a specific, opinionated recommendation for what to do next (which price to check, when to sell, when to hold)

Example:

Pattern odds:
📉 Decreasing: 84.7% 😬
📈 Large Spike: 15.1% 🤞
📊 Small Spike: 0.1%

Not great. Three consecutive drops is strongly pointing to a decreasing week. But there's still a 15% chance of a large spike hiding — if it happens, it'd be Wed-Fri with prices up to 576 bells.

My take: Check the Tuesday PM price. If it drops again, this week is almost certainly a bust — sell and cut your losses. If it jumps up, the spike is on. 🎰

Be direct, be opinionated, skip patterns with 0% probability.

Pattern Descriptions for Users

  • Fluctuating (0): Prices go up and down in waves — sell when above 120-130
  • Large Spike (1): Prices drop then SPIKE huge (400-600 bells) — wait for it!
  • Decreasing (2): Prices keep falling all week — sell ASAP to cut losses
  • Small Spike (3): Prices drop then small bump (150-200) — sell during the bump

Error Handling

If the script fails or returns an error:

  • Explain what went wrong in simple terms
  • Ask user to double-check their input data
  • Suggest they try again with corrected information

Notes

  • Predictions are probabilistic, not guaranteed
  • The algorithm matches the actual game code
  • More known prices = better predictions
  • Sunday buy price is required
  • Previous week's pattern helps but isn't required

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

94.21%
按下载量换算5,897

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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