BD xgorobot
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。
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-eval-dynamiclib/edulib.py:419Dynamic code execution from decoded/untrusted inputos.system("mplayer"+" "+path+filename) -
medium Dangerous commands
cmd-eval-dynamicscripts/ai/speech_recognition.py:30Dynamic code execution from decoded/untrusted inputos.system(f"arecord -d {args.seconds} -f S16_LE -r 16000 -c 1 -t wav {temp_audio}") -
medium Dangerous commands
cmd-eval-dynamicscripts/audio/play.py:13Dynamic code execution from decoded/untrusted inputos.system(f"mplayer /home/pi/Music/{args.filename}") -
low Dangerous commands
cmd-background-processscripts/audio/play_music.py:24Starts a background / autostarted processpreexec_fn=os.setsid
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3523 tokens
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 483: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.