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 philips-hue-thinking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 | philips-hue-thinking |
| description | Visual AI activity indicator using Philips Hue lights. Pulse red when thinking, green when done. |
| homepage | https://github.com/yourusername/philips-hue-thinking |
| metadata | {"clawdbot":{"emoji":"🚦","requires":{"bins":["hue"]},"install":[{"id":"manual","kind":"manual","label":"Copy hue script to PATH"}]}} |
Visual AI activity indicator — Connect your AI assistant's work status to your physical environment through Philips Hue smart lights.
Turns a Philips Hue light into an AI activity indicator:
| Light State | Meaning |
|---|---|
| 🟢 Green | Ready / Done / Idle |
| 🔴 Pulsing Red | AI is thinking, analyzing, or planning |
| 🔴 Solid Red | AI is actively building/working |
# Find your bridge IP (check router or Hue app), then run:
hue setup <bridge-ip>
# Example:
hue setup 192.168.1.100
hue lights
# Output:
# 2: Bed room 1 💡 ON
# 3: Bedroom 2 ⚫ OFF
# 5: Front door 💡 ON ← Use this one
# AI starts thinking
hue thinking 5
# AI is done
hue done 5
# Clone or download
git clone https://github.com/yourusername/philips-hue-thinking.git
# Add to PATH
cp philips-hue-thinking/hue /usr/local/bin/
chmod +x /usr/local/bin/hue
# Add to your shell profile (.zshrc or .bashrc)
export PATH="$PATH:/path/to/philips-hue-thinking"
# Then reload
source ~/.zshrc
# Setup (press bridge button first!)
hue setup <bridge-ip>
# List all lights
hue lights
# Thinking mode (pulsing red)
hue thinking <light-id>
# Done (solid green)
hue done <light-id>
# Set any color
hue set <light-id> <color>
hue set 5 red
hue set 5 green
hue set 5 blue
hue set 5 yellow
hue set 5 purple
hue set 5 orange
# Turn off
hue off 5
# Pulse continuously
hue pulse 5 --color red
Planning Mode:
User: "Planning mode — I want to build a website"
AI: [runs 'hue thinking 5'] 🔴 Pulsing...
"Here are my questions..."
User: [answers]
AI: [runs 'hue done 5'] ✅ Green
"Starting build now..."
[runs 'hue thinking 5'] 🔴 Solid red while building
AI: [runs 'hue done 5'] ✅ Green
"Done!"
Add to ~/.zshrc:
# Quick aliases
alias think='hue thinking 5'
alias done='hue done 5'
Then just type:
think # Light pulses red
done # Light turns green
~/.config/philips-hue/| Color | X | Y |
|---|---|---|
| Red | 0.675 | 0.322 |
| Green | 0.214 | 0.709 |
| Blue | 0.167 | 0.040 |
| Yellow | 0.492 | 0.476 |
| Purple | 0.265 | 0.100 |
| Orange | 0.600 | 0.380 |
# Brightness oscillation
254 (bright) → 50 (dim) → 254
# Timing
~2 second cycle
Background process keeps pulsing
Config stored in: ~/.config/philips-hue/config.json
{
"bridge_ip": "192.168.1.100",
"username": "your-api-key"
}
curlPress the physical button on your Hue Bridge, then run setup within 30 seconds.
# Check connection
hue lights
# Verify config
cat ~/.config/philips-hue/config.json
# Kill background process
pkill -f "hue-pulse-loop"
# Reset light
hue done 5
MIT — See LICENSE file
Created by Jesse & Kate (Clawdbot)
Inspired by the need for AI physical presence
Questions? Open an issue or DM @jesse on Twitter