肩部外设控制 SKILL.md skillA

肩部外设控制 from yuxinbeiyi/lianxin-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add yuxinbeiyi/lianxin-ai/肩部外设控制@v2

Pins v2 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: yuxinbeiyi/lianxin-ai
Path: skills/肩部外设控制/SKILL.md
Versions recorded: 2
Latest version: v2, committed Aug 25, 2026
First version recorded: Jun 6, 2026
Size: 2,264 bytes
Repository stars: 15
License: MIT

ESP32-CAM 肩载摄像头控制、云台舵机、观察模式、人脸追踪.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 肩部外设控制

激活此技能后，你可以控制莲心的肩载摄像头（ESP32-CAM）和云台系统。

## 硬件能力
1. 摄像头（OV2640）：拍照看世界，VGA 分辨率（640×480）
2. 云台舵机（Pan/Tilt）：水平 0~180°（90=正前方），垂直 0~180°（90=水平）
3. DHT11 温湿度传感器：读取当前环境的温度和湿度
4. 白色补光灯（上电指示用）

## 使用场景
- 用户问「看看周围/有什么/我在干嘛」→ 先调 shoulder_pan/tilt 或 shoulder_servo 摆好角度 → 调 shoulder_photo 拍照 → 调 describe_image 描述画面
- 用户问「左边/右边有什么」→ shoulder_pan 转到对应方向 → shoulder_photo → describe_image
- 需要同时调整水平和垂直角度 → shoulder_servo(pan, tilt) 比分两次调更高效
- 用户问「温度/湿度/热不热」→ shoulder_temp
- 主动想看看主人在做什么 → 拍一张看看
- 云台复位 → shoulder_center
- 查看设备状态和 WiFi 信号 → shoulder_status

## 【观察模式】说明
- start_observation_mode — 启动观察模式，持续主动转头→拍照→分析→发QQ
- stop_observation_mode — 退出观察模式，云台复位
- 注意：start/stop_observation_mode 是启动/停止后台自主循环，与单次拍照观察不同

## 已弃用的人体跟踪模式
- shoulder_human_track — 启动人体跟踪：摄像头推流→MediaPipe Pose推理→舵机跟随
- stop_human_tracking — 停止跟踪，云台回中

## 本人脸追踪模式
- shoulder_face_track — 电脑端显示 ESP32-CAM 视频和本人脸框，云台动态跟随本人
- stop_face_tracking — 停止人脸追踪、停止推流并让云台回中

## 重要规则
- 除非用户明确要求复位/回中，否则绝对不要调用 shoulder_center！看完一个方向后保持角度不变
- 调整角度时如果用户只说方向（如"看看左边"），用极值角度：最左=0、最右=180、最上=180、最下=0。如果只说"稍微"，则微调 ±15°
- 拍照后如果画面内容需要描述，必须调用 describe_image 或 ocr_image

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add yuxinbeiyi/lianxin-ai/肩部外设控制@sha256:0fc004c891914578

The line at the top of this page pins the label v2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_koh67optsbm5kzdo.svg)](https://markdownregistry.com/a/art_koh67optsbm5kzdo)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jun 6, 2026 and Aug 25, 2026, about one every 80 days.

version	committed	commit	size	audit
v2 latest	2026-08-25	fb481bf	2,264 B	A	view · diff
v2	2026-06-06	62e4be2	2,048 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2264 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

yuxinbeiyi/lianxin-ai · 15 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_koh67optsbm5kzdo
GET https://markdownregistry.com/api/v1/resolve?ref=yuxinbeiyi/lianxin-ai/肩部外设控制
GET https://markdownregistry.com/api/v1/blob/0fc004c891914578ac865ec9b9f12073a5cbf6f45b9252c31e023e3c974762b5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.