Agent skill

Xgorobot

by LeoYeAI in LeoYeAI/openclaw-master-skills

XGO 系列机器狗(Mini/Lite/Mini3W/Rider)完整控制能力. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passed

Install Xgorobot

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill xgorobot -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills xgorobot --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/xgorobot .claude/skills/xgorobot && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
xgorobot
GitHub stars
2.2k
Token cost
~3.7k tokens
SKILL.md length
845 words
Files
111 (incl. scripts)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

XGO 系列机器狗(Mini/Lite/Mini3W/Rider)完整控制能力. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 5 steps: API 细节:完整参数和返回值请直接查看 lib/ 下的源码文件 → 串口独占:XGO_DOG 占用串口,但可与 XGOEDU 同时使用 → 初始化顺序:建议先初始化 XGO_DOG,再初始化 XGOEDU → …
  • SKILL.md covers 执行环境(强制), 执行策略(重要), 预置脚本列表 and Python 库参考(用于编写新代码), plus 3 more sections
  • Runs Python scripts from its folder; needs DASHSCOPE_API_KEY

What it does

Xgorobot is an agent skill from LeoYeAI/openclaw-master-skills. XGO 系列机器狗(Mini/Lite/Mini3W/Rider)完整控制能力。 两层执行能力: 1. 预置脚本:scripts/ 目录下 80+ 个即用脚本,覆盖运动、动作、视觉、AI、传感器等 2. 自定义代码:参考 lib/ 中的 API 文档编写复杂逻辑和组合任务 功能覆盖: - 运动控制:前进/后退/左移/右移/转向/蹲下/站立/踏步/周期运动/步态切换 - 预设动作:坐下/趴下/招手/俯卧撑/祈祷/摇摆/匍匐/伸展/旋转等 - 视觉识别:拍照/人脸/手势/颜色/巡线/二维码/目标检测/情绪识别 - AI功能:语音识别/文字转语音/图片理解/图片生成 - 传感器:电量/IMU姿态角/舵机角度 - 屏幕音频:文字显示/图片显示/音频播放 - 机型专用:Mini机械臂/Mini3W轮控/Rider双轮足 当用户提到机器狗、XGO、走路、跑步、前进、后退、转向、蹲下、站立、摇摆、做动作、摄像头、拍照、识别、检测、手势、人脸、颜色、巡线、二维码、屏幕显示、语音、AI、机械臂、夹爪、轮控等场景时使用此 skill。

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 114 other files, including scripts (for example `_meta.json`, `lib/edulib.py` and `lib/xgolib/__init__.py`).

The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

Example prompts

  • “/xgorobot”

Requirements

  • Python 3
  • A credential in DASHSCOPE_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. API 细节:完整参数和返回值请直接查看 lib/ 下的源码文件
  2. 串口独占:XGO_DOG 占用串口,但可与 XGOEDU 同时使用
  3. 初始化顺序:建议先初始化 XGO_DOG,再初始化 XGOEDU
  4. 摄像头资源:视觉识别函数会自动管理摄像头
  5. 按键退出:用 edu.xgoButton("c") 作为程序退出条件

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 11 files in scripts/ (Python, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • DASHSCOPE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Xgorobot loads about 3.7k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 845 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~123
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 845 words, ~3,692 tokens.

Download SKILL.mdSave it as .claude/skills/xgorobot/SKILL.md (or your agent's skills folder). This skill also uses 110 other files; get the full folder from GitHub.
name
xgorobot
description
XGO 系列机器狗(Mini/Lite/Mini3W/Rider)完整控制能力。 **两层执行能力:** 1. **预置脚本**:scripts/ 目录下 80+ 个即用脚本,覆盖运动、动作、视觉、AI、传感器等 2. **自定义代码**:参考 lib/ 中的 API 文档编写复杂逻辑和组合任务 **功能覆盖:** - 运动控制:前进/后退/左移/右移/转向/蹲下/站立/踏步/周期运动/步态切换 - 预设动作:坐下/趴下/招手/俯卧撑/祈祷/摇摆/匍匐/伸展/旋转等 - 视觉识别:拍照/人脸/手势/颜色/巡线/二维码/目标检测/情绪识别 - AI功能:语音识别/文字转语音/图片理解/图片生成 - 传感器:电量/IMU姿态角/舵机角度 - 屏幕音频:文字显示/图片显示/音频播放 - 机型专用:Mini机械臂/Mini3W轮控/Rider双轮足 当用户提到机器狗、XGO、走路、跑步、前进、后退、转向、蹲下、站立、摇摆、做动作、摄像头、拍照、识别、检测、手势、人脸、颜色、巡线、二维码、屏幕显示、语音、AI、机械臂、夹爪、轮控等场景时使用此 skill。

XGO 机器狗控制

控制 XGO 系列机器狗(Mini/Lite/Mini3W/Rider),涵盖运动控制、视觉识别、AI 功能、传感器读取等完整能力。

执行环境(强制)

必须使用指定的虚拟环境 Python:

标准执行命令(必须使用)
bash
# 统一执行模板(cd到skill目录 + 超时保护)
cd /home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot && timeout 30 /home/pi/RaspberryPi-CM5/blocklyvenv/bin/python -u scripts/xxx.py

预置脚本示例:

bash
cd /home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot && timeout 30 /home/pi/RaspberryPi-CM5/blocklyvenv/bin/python -u scripts/motion/forward.py --step 15

自定义代码示例:

bash
cd /home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot && timeout 30 /home/pi/RaspberryPi-CM5/blocklyvenv/bin/python -u /tmp/my_script.py

重要:

  • 不要用 sudo(openclaw 不支持)
  • 必须用 timeout 30 包裹,防止脚本卡死
  • 如果仍然卡住,检查机器狗是否开机、串口连接是否正常

执行策略(重要)

优先级 1:使用预置脚本

优先检查 scripts/ 目录下是否有匹配的预置脚本,直接执行:

bash
cd /home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot && timeout 30 /home/pi/RaspberryPi-CM5/blocklyvenv/bin/python -u scripts/motion/forward.py --step 15
优先级 2:开放式识别优先用 AI 图片理解

当需要识别/理解任意物体时,优先使用 photo_understand.py:

场景用 AI 图片理解用 YOLO/传统视觉
识别任意物体(纸巾、胡萝卜、杯子...)✓ 推荐✗ 类别有限
判断物体位置(左/中/右)✓ 推荐✗ 需额外计算
理解场景/回答问题✓ 推荐✗ 不支持
实时追踪已知类别(人/球)✗ 太慢✓ 推荐
快速检测有无人脸✗ 太慢✓ 推荐

AI 图片理解示例:

bash
# 问图中某物体的位置
cd /home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot && timeout 30 /home/pi/RaspberryPi-CM5/blocklyvenv/bin/python -u scripts/ai/photo_understand.py --prompt "图中纸巾在什么位置?只回答:左边/中间/右边/没有"

# 识别图中有哪些物体
cd /home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot && timeout 30 /home/pi/RaspberryPi-CM5/blocklyvenv/bin/python -u scripts/ai/photo_understand.py --prompt "图中有哪些物品?列出名称"

# 判断场景
cd /home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot && timeout 30 /home/pi/RaspberryPi-CM5/blocklyvenv/bin/python -u scripts/ai/photo_understand.py --prompt "这是室内还是室外?"

简单说: YOLO 只能识别 80 种固定类别,AI 图片理解能识别任何东西并回答问题。

优先级 3:预置脚本不满足时才生成代码

当预置脚本参数无法满足需求,或需要组合多个功能时,参考 lib/ 目录的 API 编写新代码。


预置脚本列表

基础运动 (scripts/motion/)
脚本功能参数
forward.py前进--step 15 (0-25) --duration 2
backward.py后退--step 15 (0-25) --duration 2
left.py左移--step 10 (0-18) --duration 2
right.py右移--step 10 (0-18) --duration 2
turn.py旋转--speed 50 (-100~100,正左负右) --duration 1
turn_left.py左转--speed 50 (0-100) --duration 1
turn_right.py右转--speed 50 (0-100) --duration 1
stop.py停止无参数
reset.py复位无参数
姿态控制 (scripts/motion/)
脚本功能参数
squat.py蹲下--height 80 (75-120mm)
stand.py站立--height 115 (75-120mm)
tilt.py倾斜--roll 0 --pitch 0 --yaw 0
attitude.py姿态控制--roll 10 (-2020) --pitch 5 (-2222) --yaw 0 (-16~16)
translation.py机身平移--axis z (x/y/z) --distance 95
mark_time.py原地踏步--height 20 (10-35mm) --duration 3
周期运动 (scripts/motion/)
脚本功能参数
periodic_tran.py周期平移--axis z (x/y/z) --period 2 (1.5-8秒) --duration 5
periodic_rot.py周期旋转--axis r (r/p/y) --period 2 (1.5-8秒) --duration 5
步态与速度 (scripts/motion/)
脚本功能参数
gait_type.py步态类型--mode trot (trot/walk/high_walk/slow_trot)
pace.py步频控制--mode normal (normal/slow/high)
imu.pyIMU平衡--mode 1 (0=关, 1=开)
单腿与舵机 (scripts/motion/)
脚本功能参数
leg.py单腿控制--id 1 (1-4) --x 0 --y 0 --z 95
motor.py舵机控制--id 11 (11-43,51) --angle 45
motor_speed.py舵机速度--speed 128 (1-255)
load_motor.py加载舵机--leg 1 (1-5)
unload_motor.py卸载舵机--leg 1 (1-5)
机械臂 (scripts/motion/) - Mini/Mini3W
脚本功能参数
arm.py机械臂控制--action open (open/close/up/down)

预设动作 (scripts/action/)
脚本功能参数
action.py执行动作ID--id 1 (1-23/128-141/255)
sit.py坐下无参数
lie_down.py趴下无参数
stand.py起立无参数
wave.py招手无参数
pee.py撒尿无参数
pushup.py俯卧撑无参数
pray.py祈祷无参数
swing.py摇摆--duration 5
crawl.py匍匐无参数
stretch.py伸展无参数
spin.py旋转无参数

视觉识别 (scripts/vision/)
脚本功能参数输出
take_photo.py拍照--filename photo.jpg照片已保存: {path}
camera_preview.py摄像头预览--duration 10预览窗口显示
face_detect.py人脸检测--continuous (持续模式)检测到人脸: x=, y=, w=, h= 或 未检测到人脸
face_count.py人脸计数无共检测到 N 张人脸 + 每张人脸位置
gesture_detect.py手势识别--continuous识别到手势: {手势} 位置=({x},{y}) 或 无
color_detect.py颜色识别--color R (R/G/B/Y) --continuous检测到{颜色}: 位置=({x},{y}), 半径={r}
line_detect.py巡线检测--color K (K黑/W白/R/G/B/Y) --continuous巡线: x={x}, angle={角度}
qr_scan.py二维码扫描--continuous二维码内容: {内容} 或 无
yolo_detect.py目标检测--continuous检测到: {类别} 位置=({x},{y}) 或 无
emotion_detect.py情绪识别--continuous情绪: {情绪} 位置=({x},{y}) 或 无
视觉追踪 (scripts/vision/)
脚本功能参数输出
find_ball.py寻找小球--color R --timeout 30✓ 找到{颜色}色小球 或 ✗ 超时未找到
find_person.py寻找人类--timeout 45✓ 找到人类 或 ✗ 超时未找到
catch_ball.py抓取小球--color R --timeout 60✓ 抓取成功 或 ✗ 抓取失败

传感器读取 (scripts/sensor/)
脚本功能输出
battery.py读取电量百分比
read_roll.py读取Roll角横滚角度
read_pitch.py读取Pitch角俯仰角度
read_yaw.py读取Yaw角偏航角度
read_imu.py读取IMU--axis all (roll/pitch/yaw/all)
read_motor.py读取舵机角度所有舵机当前角度

屏幕显示 (scripts/display/)
脚本功能参数
text.py显示文字--text "Hello" --x 5 --y 5 --color WHITE --size 15
clear.py清除屏幕无参数
picture.py显示本地图片--filename photo.jpg --x 0 --y 0
http_image.py显示网络图片--url "http://..." --x 0 --y 0

音频播放 (scripts/audio/)
脚本功能参数
play.py播放本地音频--filename music.mp3
play_http.py播放网络音频--url "http://..."
play_music.py播放背景音乐(Dream.mp3)无参数

Show full SKILL.md (336 more words)Show less
AI功能 (scripts/ai/) - 需要 DASHSCOPE_API_KEY
脚本功能参数输出
photo_understand.pyAI拍照理解--prompt "提问内容"问题: {prompt} / 回答: {AI回答}
speech_recognition.py语音识别--seconds 3识别结果: {文字}
text_to_speech.pyAI语音合成--text "你好" --voice Cherry语音播放(自然人声,需API)
generate_image.pyAI生成图片--prompt "一只猫"图片已保存: {path}
goto_target.pyAI走向目标--target "黄色小鸡" --timeout 60✓ 已到达目标 或 ✗ 未能到达

语音输出选择: 机器狗说话优先用 text_to_speech.py

photo_understand.py 常用 prompt 示例:

任务prompt 示例
物体位置--prompt "图中纸巾在什么位置?只回答:左边/中间/右边/没有"
物体列举--prompt "图中有哪些物品?列出名称"
物体计数--prompt "图中有几个苹果?只回答数字"
颜色判断--prompt "图中最大的物体是什么颜色?"
场景理解--prompt "这是什么地方?简要描述"
是非判断--prompt "图中有人吗?只回答有/没有"
物体对比--prompt "图中哪个物体更大?"

API密钥通过环境变量 DASHSCOPE_API_KEY 自动读取,也可用 --api-key 参数覆盖


Mini3W专用 (scripts/mini3w/)
脚本功能参数
enable_wheel.py轮控开关--mode 0 (0=启用, 1=禁用)
wheel_control.py轮控制--w1 128 --w2 128 --w3 128 --w4 128
extern_motor.py外接电机--position 100

Rider专用 (scripts/rider/)
运动控制
脚本功能参数
move.py前后移动--speed 0.5 --runtime 3
turn.py原地旋转--speed 90 --runtime 2
roll.pyRoll姿态--angle 10
height.py身高调整--height 90
reset.py重置无参数
reset_odom.py重置里程计无参数
模式控制
脚本功能参数
action.py预设动作--id 1 (1-6/255)
balance_roll.pyRoll自平衡--mode 1 (0=关, 1=开)
perform.py表演模式--mode 1 (0=关, 1=开)
calibration.py软件标定--state start/end
周期运动
脚本功能参数
periodic_roll.py周期Roll--period 1.5 --duration 5
periodic_z.py周期升降--period 1.5 --duration 5
传感器与LED
脚本功能参数
battery.py读取电量无参数
read_roll.py读取Roll无参数
read_pitch.py读取Pitch无参数
read_yaw.py读取Yaw无参数
led.pyLED控制--index 0 --r 255 --g 0 --b 0

组合任务 (scripts/combo/)
脚本功能参数
ai_find_step.pyAI智能踩物--target "纸巾" --leg 1 (1=左前,2=右前) --speed 100 (越小越机械)
follow_face.py人脸追踪无参数,按C退出
follow_color.py颜色追踪--color R (R/G/B/Y)
gesture_control.py手势控制无参数,按C退出
line_follow.py巡线行走--color K (K黑/W白)
qr_patrol.py二维码巡逻无参数,按C退出

Python 库参考(用于编写新代码)

当预置脚本无法满足需求时,参考以下源码编写代码:

模块文件路径功能说明
运动控制lib/xgolib/xgolib_dog.pyXGO_DOG 类:四足机器狗运动、姿态、机械臂控制
Rider控制lib/xgolib/xgolib_rider.pyXGO_RIDER 类:双轮足机器人专用
视觉传感器lib/edulib.pyXGOEDU 类:摄像头、屏幕、按键、各种识别功能

这些文件包含完整的方法签名、参数范围和注释,是最准确的 API 参考。

代码模板(必须遵循)

python
import sys
sys.path.insert(0, '/home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot/lib')
from xgolib import XGO       # 通用类,自动识别机型
from edulib import XGOEDU    # 视觉/屏幕/按键

# 初始化(不带参数,自动检测)
dog = XGO()
edu = XGOEDU()

重要:sys.path.insert 和 XGO() 不带参数是必须的,否则会出错或卡死

机型识别

XGO 类自动识别机型,无需手动指定:

python
dog = XGO()  # 自动检测串口和机型
firmware = dog.read_firmware()  # 首字母: M=Mini, L=Lite, W=Mini3W, R=Rider
机型特征固件首字母
XGO-Mini12自由度,有机械臂M
XGO-Lite轻量版,无机械臂L
XGO-Mini3W支持轮控模式W
XGO-Rider双轮足,非四足R

快速参考

运动控制 (XGO)
python
dog = XGO()

# 基础运动
dog.forward(step)      # 前进 0-25
dog.back(step)         # 后退 0-25
dog.left(step)         # 左移 0-18
dog.right(step)        # 右移 0-18
dog.turnleft(step)     # 左转 0-100
dog.turnright(step)    # 右转 0-100
dog.stop()             # 停止

# 姿态控制
dog.translation('z', height)  # 身高 75-120mm
dog.attitude('r', angle)      # Roll 姿态
dog.attitude('p', angle)      # Pitch 姿态
dog.attitude('y', angle)      # Yaw 姿态

# 预设动作
dog.action(id)         # 执行预设动作 1-255
dog.reset()            # 恢复初始姿态

# 机械臂 (Mini/Mini3W)
dog.arm(x, z)          # 机械臂位置
dog.claw(pos)          # 夹爪开合 0-255

# 状态读取
dog.read_battery()     # 电量
dog.read_roll()        # Roll 角度
dog.read_pitch()       # Pitch 角度
dog.read_yaw()         # Yaw 角度
视觉传感器 (XGOEDU)
python
edu = XGOEDU()

# 屏幕显示
edu.lcd_clear()                          # 清屏
edu.lcd_text(x, y, text, color, size)    # 显示文字
edu.lcd_picture(filename, x, y)          # 显示图片
edu.lcd_line(x1, y1, x2, y2, color)      # 画线
edu.lcd_rectangle(x1, y1, x2, y2)        # 画矩形

# 按键检测
edu.xgoButton("a")  # 左上 (True/False)
edu.xgoButton("b")  # 右上
edu.xgoButton("c")  # 左下 (常用作退出)
edu.xgoButton("d")  # 右下

# 摄像头
edu.xgoCamera(True/False)  # 开关摄像头预览
edu.xgoTakePhoto(filename) # 拍照

# 识别功能
edu.gestureRecognition()    # 手势识别 -> ('5', (x,y)) 或 None
edu.ColorRecognition(mode)  # 颜色识别 mode='R'/'G'/'B'/'Y' -> ((x,y), radius)
edu.LineRecognition(mode)   # 巡线 mode='K'(黑)/'W'(白) -> {'x':, 'angle':}
edu.QRRecognition()         # 二维码 -> ['内容1', '内容2'] 或 []
edu.AprilTagRecognition()   # AprilTag -> tag_id 或 None
edu.face_detect()           # 人脸检测 -> [x, y, w, h] 或 None
edu.emotion()               # 情绪识别 -> ('Happy', (x,y)) 或 None
edu.agesex()                # 年龄性别 -> ('Male', '(25-32)', (x,y)) 或 None
edu.yoloFast()              # 目标检测 -> ('person', (x,y)) 或 None
edu.posenetRecognition()    # 骨骼检测 -> [angle1, angle2, ...] 或 None

典型代码模板

基础控制
python
import sys
sys.path.insert(0, '/home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot/lib')
from xgolib import XGO
from edulib import XGOEDU
import time

dog = XGO()
edu = XGOEDU()

# 显示提示
edu.lcd_text(10, 100, "按C键退出", "YELLOW", 20)

# 主循环
while not edu.xgoButton("c"):
    # 你的控制逻辑
    time.sleep(0.1)

dog.stop()
dog.reset()
视觉追踪
python
import sys
sys.path.insert(0, '/home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot/lib')
from xgolib import XGO
from edulib import XGOEDU
import time

dog = XGO()
edu = XGOEDU()

while not edu.xgoButton("c"):
    result = edu.ColorRecognition(mode='R')  # 追踪红色
    (x, y), radius = result
    
    if radius > 10:  # 检测到目标
        error = x - 160  # 偏离中心
        if error > 30:
            dog.turnright(30)
        elif error < -30:
            dog.turnleft(30)
        else:
            dog.forward(10)
    else:
        dog.stop()
    
    time.sleep(0.1)

dog.stop()
巡线行走
python
import sys
sys.path.insert(0, '/home/pi/.npm-global/lib/node_modules/openclaw/skills/xgorobot/lib')
from xgolib import XGO
from edulib import XGOEDU
import time

dog = XGO()
edu = XGOEDU()

while not edu.xgoButton("c"):
    result = edu.LineRecognition(mode='K')  # 黑线
    x = result['x']
    
    if x > 0:
        offset = x - 160
        if offset > 20:
            dog.turn(-20)
        elif offset < -20:
            dog.turn(20)
        else:
            dog.turn(0)
        dog.forward(10)
    else:
        dog.stop()
    
    time.sleep(0.05)

dog.stop()

注意事项

  1. API 细节:完整参数和返回值请直接查看 lib/ 下的源码文件
  2. 串口独占:XGO_DOG 占用串口,但可与 XGOEDU 同时使用
  3. 初始化顺序:建议先初始化 XGO_DOG,再初始化 XGOEDU
  4. 摄像头资源:视觉识别函数会自动管理摄像头
  5. 按键退出:用 edu.xgoButton("c") 作为程序退出条件

机型差异

功能MiniLiteMini3WRider
机械臂✓✗✓✗
轮控模式✗✗✓-
Y轴平移✓✓✓✗
四足行走✓✓✓✗
  • Lite:无机械臂,调用 arm() 或 claw() 无效
  • Mini3W:可用 enable_wheel_control() 切换轮控模式
  • Rider:统一使用 XGO() 类,调用 rider_* 方法(如 rider_move_x()),无侧移功能

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 110 other files (scripts) in skills/xgorobot of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json
  • lib/edulib.py
  • lib/xgolib/__init__.py
  • lib/xgolib/xgolib_dog.py
  • lib/xgolib/xgolib_rider.py
  • scripts/action/action.py
  • scripts/action/crawl.py
  • scripts/action/lie_down.py
  • scripts/action/pee.py
  • scripts/action/pray.py
  • scripts/action/pushup.py
  • scripts/action/sit.py
  • scripts/action/spin.py
  • scripts/action/stretch.py
  • scripts/action/swing.py
  • scripts/action/wave.py
  • … and 94 more

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Xgorobot next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Xgorobot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xgorobot this skillLeoYeAI/openclaw-master-skills2.2k—~3.7kAutomated safety check: PassMIT
Telegram Mini Appdavila7/claude-code-templates32k4 repos~1.5kAutomated safety check: PassMIT
Doc Chaser Litedavila7/claude-code-templates32k—~1.4kAutomated safety check: PassMIT
Openclaw Local Mac Minisickn33/agentic-awesome-skills47k2 repos~2.7kAutomated safety check: NotesMIT
Code Simplification for ego-litecitrolabs/ego-lite17k—~1.2kAutomated safety check: PassMIT
Mini Context Graphgithub/awesome-copilot40k1 repos~2kAutomated safety check: PassMIT

Similar skills

  • Telegram Mini App

    davila7/claude-code-templates

    Expert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience.

    32k GitHub starsUsed in 4 repos~1.5k tokens
    Backend & APIsAuto-check passed
  • Doc Chaser Lite

    davila7/claude-code-templates

    Free lite skill — drafts one friendly (level-1) client document-request email for a single tax client from a short brief plus the practice profile.

    32k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Openclaw Local Mac Mini

    sickn33/agentic-awesome-skills

    Set up OpenClaw locally and run it reliably on a Mac mini for private, always-on local agent workflows.

    47k GitHub starsUsed in 2 repos~2.7k tokens
    DevOps & CloudAuto-check: notes
  • Finds and implements evidence-backed simplifications in the ego-lite repository, such as dead code, duplicated state and speculative abstractions, without hiding behavior changes.

    17k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Mini Context Graph

    github/awesome-copilot

    Official

    A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph.

    40k GitHub starsUsed in 1 repo~2k tokens
    Knowledge ManagementAuto-check passed
  • AutoRAG Lite Setup

    Marker-Inc-Korea/AutoRAG

    Bootstraps and repairs the model-free AutoRAG Lite MCP server: installing it, initializing a config with approved search roots, building indexes and verifying discovery.

    5.1k GitHub stars~3.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Xgorobot

What does Xgorobot do?

XGO 系列机器狗(Mini/Lite/Mini3W/Rider)完整控制能力. An agent skill from LeoYeAI/openclaw-master-skills. Xgorobot is an agent skill from LeoYeAI/openclaw-master-skills. XGO 系列机器狗(Mini/Lite/Mini3W/Rider)完整控制能力。 两层执行能力: 1.

How do I install Xgorobot in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill xgorobot -a claude-code`. Or copy the skill folder (skills/xgorobot in LeoYeAI/openclaw-master-skills) into .claude/skills/xgorobot in your project. Claude Code loads it when a task matches its description.

How do I install Xgorobot in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill xgorobot -a codex`. Or copy the skill folder (skills/xgorobot in LeoYeAI/openclaw-master-skills) into .agents/skills/xgorobot in your project. Codex loads it when a task matches its description.

Can I use Xgorobot in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill xgorobot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xgorobot, .gemini/skills/xgorobot, .github/skills/xgorobot and .opencode/skills/xgorobot in your project.

What does Xgorobot need to run?

Going by SKILL.md and its folder, Xgorobot needs Python for the scripts in its folder and credentials named DASHSCOPE_API_KEY. Our summary lists: Python 3; A credential in DASHSCOPE_API_KEY.

Does Xgorobot access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Xgorobot safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Xgorobot use?

Xgorobot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Xgorobot use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Xgorobot?

Skills that share tags, products or a category with Xgorobot: Telegram Mini App (davila7/claude-code-templates, 32k stars), Doc Chaser Lite (davila7/claude-code-templates, 32k stars), Openclaw Local Mac Mini (sickn33/agentic-awesome-skills, 47k stars) and Code Simplification for ego-lite (citrolabs/ego-lite, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xgorobot?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.