nest-devices
Control Nest smart home devices (thermostat, cameras, doorbell) via the Device Access API. Use when asked to check or adjust home temperature, view camera feeds, check who's at the door, monitor rooms, or set up temperature schedules.
Best use case
nest-devices is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Control Nest smart home devices (thermostat, cameras, doorbell) via the Device Access API. Use when asked to check or adjust home temperature, view camera feeds, check who's at the door, monitor rooms, or set up temperature schedules.
Teams using nest-devices should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/nest-devices/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How nest-devices Compares
| Feature / Agent | nest-devices | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Control Nest smart home devices (thermostat, cameras, doorbell) via the Device Access API. Use when asked to check or adjust home temperature, view camera feeds, check who's at the door, monitor rooms, or set up temperature schedules.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Nest Device Access
Control Nest devices via Google's Smart Device Management API.
## Setup
### 1. Google Cloud & Device Access
1. Create a Google Cloud project at [console.cloud.google.com](https://console.cloud.google.com)
2. Pay the $5 fee and create a Device Access project at [console.nest.google.com/device-access](https://console.nest.google.com/device-access)
3. Create OAuth 2.0 credentials (Web application type)
4. Add `https://www.google.com` as an authorized redirect URI
5. Link your Nest account to the Device Access project
### 2. Get Refresh Token
Run the OAuth flow to get a refresh token:
```bash
# 1. Open this URL in browser (replace CLIENT_ID and PROJECT_ID):
https://nestservices.google.com/partnerconnections/PROJECT_ID/auth?redirect_uri=https://www.google.com&access_type=offline&prompt=consent&client_id=CLIENT_ID&response_type=code&scope=https://www.googleapis.com/auth/sdm.service
# 2. Authorize and copy the 'code' parameter from the redirect URL
# 3. Exchange code for tokens:
curl -X POST https://oauth2.googleapis.com/token \
-d "client_id=CLIENT_ID" \
-d "client_secret=CLIENT_SECRET" \
-d "code=AUTH_CODE" \
-d "grant_type=authorization_code" \
-d "redirect_uri=https://www.google.com"
```
### 3. Store Credentials
Store in 1Password or environment variables:
**1Password** (recommended):
Create an item with fields: `project_id`, `client_id`, `client_secret`, `refresh_token`
**Environment variables:**
```bash
export NEST_PROJECT_ID="your-project-id"
export NEST_CLIENT_ID="your-client-id"
export NEST_CLIENT_SECRET="your-client-secret"
export NEST_REFRESH_TOKEN="your-refresh-token"
```
## Usage
### List devices
```bash
python3 scripts/nest.py list
```
### Thermostat
```bash
# Get status
python3 scripts/nest.py get <device_id>
# Set temperature (Celsius)
python3 scripts/nest.py set-temp <device_id> 21 --unit c --type heat
# Set temperature (Fahrenheit)
python3 scripts/nest.py set-temp <device_id> 70 --unit f --type heat
# Change mode (HEAT, COOL, HEATCOOL, OFF)
python3 scripts/nest.py set-mode <device_id> HEAT
# Eco mode
python3 scripts/nest.py set-eco <device_id> MANUAL_ECO
```
### Cameras
```bash
# Generate live stream URL (RTSP, valid ~5 min)
python3 scripts/nest.py stream <device_id>
```
## Python API
```python
from nest import NestClient
client = NestClient()
# List devices
devices = client.list_devices()
# Thermostat control
client.set_heat_temperature(device_id, 21.0) # Celsius
client.set_thermostat_mode(device_id, 'HEAT')
client.set_eco_mode(device_id, 'MANUAL_ECO')
# Camera stream
result = client.generate_stream(device_id)
rtsp_url = result['results']['streamUrls']['rtspUrl']
```
## Configuration
The script checks for credentials in this order:
1. **1Password**: Set `NEST_OP_VAULT` and `NEST_OP_ITEM` (or use defaults: vault "Alfred", item "Nest Device Access API")
2. **Environment variables**: `NEST_PROJECT_ID`, `NEST_CLIENT_ID`, `NEST_CLIENT_SECRET`, `NEST_REFRESH_TOKEN`
## Temperature Reference
| Setting | Celsius | Fahrenheit |
|---------|---------|------------|
| Eco (away) | 15-17°C | 59-63°F |
| Comfortable | 19-21°C | 66-70°F |
| Warm | 22-23°C | 72-73°F |
| Night | 17-18°C | 63-65°F |
---
## Real-Time Events (Doorbell, Motion, etc.)
For instant alerts when someone rings the doorbell or motion is detected, you need to set up Google Cloud Pub/Sub with a webhook.
### Prerequisites
- Google Cloud CLI (`gcloud`) installed and authenticated
- Cloudflare account (free tier works) for the tunnel
- Clawdbot hooks enabled in config
### 1. Enable Clawdbot Hooks
Add to your `clawdbot.json`:
```json
{
"hooks": {
"enabled": true,
"token": "your-secret-token-here"
}
}
```
Generate a token: `openssl rand -hex 24`
### 2. Create Pub/Sub Topic
```bash
gcloud config set project YOUR_GCP_PROJECT_ID
# Create topic
gcloud pubsub topics create nest-events
# Grant SDM permission to publish (both the service account and publisher group)
gcloud pubsub topics add-iam-policy-binding nest-events \
--member="serviceAccount:sdm-prod@sdm-prod.iam.gserviceaccount.com" \
--role="roles/pubsub.publisher"
gcloud pubsub topics add-iam-policy-binding nest-events \
--member="group:sdm-publisher@googlegroups.com" \
--role="roles/pubsub.publisher"
```
### 3. Link Topic to Device Access
Go to [console.nest.google.com/device-access](https://console.nest.google.com/device-access) → Your Project → Edit → Set Pub/Sub topic to:
```
projects/YOUR_GCP_PROJECT_ID/topics/nest-events
```
### 4. Set Up Cloudflare Tunnel
```bash
# Install cloudflared
curl -L -o ~/.local/bin/cloudflared https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64
chmod +x ~/.local/bin/cloudflared
# Authenticate (opens browser)
~/.local/bin/cloudflared tunnel login
# Create named tunnel
~/.local/bin/cloudflared tunnel create nest-webhook
# Note the Tunnel ID (UUID) from output
```
Create `~/.cloudflared/config.yml`:
```yaml
tunnel: nest-webhook
credentials-file: /home/YOUR_USER/.cloudflared/TUNNEL_ID.json
ingress:
- hostname: nest.yourdomain.com
service: http://localhost:8420
- service: http_status:404
```
Create DNS route:
```bash
~/.local/bin/cloudflared tunnel route dns nest-webhook nest.yourdomain.com
```
### 5. Create Systemd Services
**Webhook server** (`/etc/systemd/system/nest-webhook.service`):
```ini
[Unit]
Description=Nest Pub/Sub Webhook Server
After=network.target
[Service]
Type=simple
User=YOUR_USER
Environment=CLAWDBOT_GATEWAY_URL=http://localhost:18789
Environment=CLAWDBOT_HOOKS_TOKEN=your-hooks-token-here
ExecStart=/usr/bin/python3 /path/to/skills/nest-devices/scripts/nest-webhook.py
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
```
**Cloudflare tunnel** (`/etc/systemd/system/cloudflared-nest.service`):
```ini
[Unit]
Description=Cloudflare Tunnel for Nest Webhook
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=YOUR_USER
ExecStart=/home/YOUR_USER/.local/bin/cloudflared tunnel run nest-webhook
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
```
Enable and start:
```bash
sudo systemctl daemon-reload
sudo systemctl enable --now nest-webhook cloudflared-nest
```
### 6. Create Pub/Sub Push Subscription
```bash
gcloud pubsub subscriptions create nest-events-sub \
--topic=nest-events \
--push-endpoint="https://nest.yourdomain.com/nest/events" \
--ack-deadline=30
```
### 7. Test
```bash
# Test webhook endpoint
curl https://nest.yourdomain.com/health
# Simulate doorbell event
curl -X POST http://localhost:8420/nest/events \
-H "Content-Type: application/json" \
-d '{"message":{"data":"eyJyZXNvdXJjZVVwZGF0ZSI6eyJuYW1lIjoiZW50ZXJwcmlzZXMvdGVzdC9kZXZpY2VzL0RPT1JCRUxMLTAxIiwiZXZlbnRzIjp7InNkbS5kZXZpY2VzLmV2ZW50cy5Eb29yYmVsbENoaW1lLkNoaW1lIjp7ImV2ZW50SWQiOiJ0ZXN0In19fX0="}}'
```
### Supported Events
| Event | Behaviour |
|-------|-----------|
| `DoorbellChime.Chime` | 🔔 **Alerts** — sends photo to Telegram |
| `CameraPerson.Person` | 🚶 **Alerts** — sends photo to Telegram |
| `CameraMotion.Motion` | 📹 Logged only (no alert) |
| `CameraSound.Sound` | 🔊 Logged only (no alert) |
| `CameraClipPreview.ClipPreview` | 🎬 Logged only (no alert) |
> **Staleness filter:** Events older than 5 minutes are logged but never alerted. This prevents notification floods if queued Pub/Sub messages are delivered late.
### Image Capture
When a doorbell or person event triggers an alert:
1. **Primary:** SDM `GenerateImage` API — fast, event-specific snapshot
2. **Fallback:** RTSP live stream frame capture via `ffmpeg` (requires `ffmpeg` installed)
### Environment Variables
| Variable | Required | Description |
|----------|----------|-------------|
| `CLAWDBOT_GATEWAY_URL` | No | Gateway URL (default: `http://localhost:18789`) |
| `CLAWDBOT_HOOKS_TOKEN` | Yes | Gateway hooks token for awareness notifications |
| `OP_SVC_ACCT_TOKEN` | Yes | 1Password service account token for Nest API credentials |
| `TELEGRAM_BOT_TOKEN` | Yes | Telegram bot token for sending alerts |
| `TELEGRAM_CHAT_ID` | Yes | Telegram chat ID to receive alerts |
| `PORT` | No | Webhook server port (default: `8420`) |
### Important Setup Notes
- **Verify the full Pub/Sub topic path** in Device Access Console matches your GCP project exactly: `projects/YOUR_GCP_PROJECT_ID/topics/nest-events`
- **Use a push subscription**, not pull — the webhook expects HTTP POST delivery
- **Test end-to-end** after setup: ring the doorbell and confirm a photo arrives. Don't rely on simulated POST requests alone.
---
## Limitations
- Camera event images expire after ~5 minutes (RTSP fallback captures current frame instead)
- Real-time events require Pub/Sub setup (see above)
- Quick tunnels (without Cloudflare account) have no uptime guarantee
- Some older Nest devices may not support all features
- Motion and sound events are intentionally not alerted to avoid notification fatigueRelated Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述