菜单
Control a Vector robot via Wirepod’s local HTTP API on the same network. Use when you need to move Vector, tilt head/lift, speak text, capture camera frames, or run patrol/explore routines from the Pi/Wirepod host. Includes a CLI helper script and endpoint reference.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill vector-control命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
基于 SOC 职业分类
| name | vector-control |
| description | Control a Vector robot via Wirepod’s local HTTP API on the same network. Use when you need to move Vector, tilt head/lift, speak text, capture camera frames, or run patrol/explore routines from the Pi/Wirepod host. Includes a CLI helper script and endpoint reference. |
Control Vector through Wirepod’s /api-sdk/* endpoints and the camera stream at /cam-stream. Use this skill for movement, speech, camera snapshots, patrols, and exploration from the Pi.
Use the bundled script:
python3 skills/vector-control/scripts/vector_control.py --serial <ESN> assume
python3 skills/vector-control/scripts/vector_control.py --serial <ESN> say --text "Hello Dom"
python3 skills/vector-control/scripts/vector_control.py --serial <ESN> move --lw 160 --rw 160 --time 1.5
python3 skills/vector-control/scripts/vector_control.py --serial <ESN> snapshot --out /tmp/vector.mjpg
If you don’t have it, read:
/etc/wire-pod/wire-pod/jdocs/botSdkInfo.jsonAlways assume before movement, and release if the bot tips or a human needs manual control.
python3 .../vector_control.py --serial <ESN> assume
python3 .../vector_control.py --serial <ESN> release
move sends wheel speeds (0–200 typical). Use short timed moves.python3 .../vector_control.py --serial <ESN> move --lw 120 --rw 120 --time 1.0
python3 .../vector_control.py --serial <ESN> head --speed -2 --time 1.0
python3 .../vector_control.py --serial <ESN> lift --speed 2 --time 1.0
Speech can be interrupted by motion/camera. If it fails, pause after speaking before moving.
python3 .../vector_control.py --serial <ESN> say --text "Sneaking forward"
# wait 1–2s, then move
/cam-stream returns MJPG. Save it and convert to JPEG if needed (ffmpeg).
python3 .../vector_control.py --serial <ESN> snapshot --out /tmp/vector.mjpg
ffmpeg -y -loglevel error -i /tmp/vector.mjpg -frames:v 1 /tmp/vector.jpg
Streams an audio file through Vector's speaker. Automatically converts to the required format (8kHz mono WAV).
python3 .../vector_control.py --serial <ESN> play --file /path/to/music.mp3
python3 .../vector_control.py --serial <ESN> patrol --steps 6 --speed 140 --step-time 1.2 --turn-time 0.8 --speak --phrase "Patrolling"
python3 .../vector_control.py --serial <ESN> explore --steps 8 --speak --phrase "Exploring"
references/wirepod-api.md — endpoint list and notes.vector_control.py — CLI for basic control + patrol/explore routines.wirepod-api.md — HTTP API endpoints and usage notes.