xlink-iot-agent
Xlink IoT Agent - Query IoT devices and events via Xlink Gateway API. Provides device overview, device list, event instance queries, and alert statistics. Use when managing IoT devices and monitoring events on the XLink IoT platform.
Best use case
xlink-iot-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Xlink IoT Agent - Query IoT devices and events via Xlink Gateway API. Provides device overview, device list, event instance queries, and alert statistics. Use when managing IoT devices and monitoring events on the XLink IoT platform.
Teams using xlink-iot-agent 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/xlink-iot-agent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How xlink-iot-agent Compares
| Feature / Agent | xlink-iot-agent | 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?
Xlink IoT Agent - Query IoT devices and events via Xlink Gateway API. Provides device overview, device list, event instance queries, and alert statistics. Use when managing IoT devices and monitoring events on the XLink IoT platform.
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
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
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.
SKILL.md Source
# Xlink IoT Agent
Control and query IoT devices and events on the XLink IoT platform via GatewayAppClient with signature-based authentication.
## When to Use
### ✅ Use This Skill When
- Querying device status and statistics on XLink IoT platform
- Monitoring device alerts and events
- Batch querying device attributes (latest values or historical data)
- Remote control of IoT devices (invoking thing model services)
- Filtering device data by project/product
### ❌ Do Not Use This Skill For
- Other IoT platforms (AWS IoT, Azure IoT, Alibaba Cloud IoT, etc.)
- Direct local device control (not via XLink IoT platform)
- Historical weather data or severe weather alerts (use weather skill)
- Non-IoT related device management tasks
---
## Quick Start
### 1. Set Environment Variables
```bash
export XLINK_BASE_URL="https://api-gw.xlink.cn"
export XLINK_APP_ID="your-app-id"
export XLINK_APP_SECRET="your-app-secret"
export XLINK_API_GROUP="your-group-id"
```
### 2. Run Commands
```bash
cd /path/to/xlink-iot-agent
# Device overview
python scripts/xlink_api.py overview
# Pending events
python scripts/xlink_api.py event-instances --status 1 --limit 20
# Alert statistics (last 24 hours)
python scripts/xlink_api.py alert-statistics
# Device control
python scripts/xlink_api.py device-control \
--thing-id 10299402 \
--service device_attribute_set_service \
--input '{"PowerSwitch":true}'
```
---
## Core Commands
| Command | Function | Example |
|------|------|------|
| `overview` | Device overview statistics | `python scripts/xlink_api.py overview` |
| `device-list` | Device list query | `python scripts/xlink_api.py device-list --limit 20` |
| `device-trend` | Device statistics trend | `python scripts/xlink_api.py device-trend --start-time "2026-03-17T00:00" --end-time "2026-03-24T23:59"` |
| `device-history` | Device attribute history snapshots | `python scripts/xlink_api.py device-history --device-ids 300513220,501548135` |
| `device-latest` | Device latest attributes | `python scripts/xlink_api.py device-latest --device-ids 300513220,501548135` |
| `device-control` | Device control | `python scripts/xlink_api.py device-control --thing-id 10299402 --service device_attribute_set_service --input '{"PowerSwitch":true}'` |
| `alert-overview` | Alert overview | `python scripts/xlink_api.py alert-overview` |
| `alert-statistics` | Alert time-series statistics | `python scripts/xlink_api.py alert-statistics --interval hour` |
| `event-instances` | Event instance query | `python scripts/xlink_api.py event-instances --status 1 --limit 20` |
---
## Common Query Examples
### Device Overview
```bash
python scripts/xlink_api.py overview
```
Output:
```
==================================================
📊 XLINK Device Overview
==================================================
📱 Total Devices: 7823
🟢 Online: 143 (1.8%)
✅ Activated: 6756 (86.4%)
⚫ Offline: 7680
⏸️ Not Activated: 1067
```
### Pending Events
```bash
python scripts/xlink_api.py event-instances --status 1 --limit 20
```
### Alert Overview
```bash
python scripts/xlink_api.py alert-overview
```
### Device List (with Filtering)
```bash
# Filter by project
python scripts/xlink_api.py device-list \
--query '{"logic":"AND","device":{"project_id":{"$eq":"XJA1JJAJA"}}}' \
--limit 20
# JSON output
python scripts/xlink_api.py device-list --limit 20 --json
```
### Device Control
```bash
# Set attributes
python scripts/xlink_api.py device-control \
--thing-id 10299402 \
--service device_attribute_set_service \
--input '{"ColorTemperature": 8}'
# With command cache (10 minutes)
python scripts/xlink_api.py device-control \
--thing-id 10299402 \
--service device_attribute_set_service \
--input '{"Brightness": 100}' \
--ttl 600
```
**Control Response Codes:**
| Code | Description |
|------|-------------|
| `200` | ✅ Success - device responded |
| `202` | ⏸️ Device offline - command not sent |
| `408` | ⚠️ Connection closed - device sleeping |
| `503` | ❌ Control failed |
---
## Python API
```python
import sys
sys.path.insert(0, "scripts")
from xlink_api import XlinkIoTClient
# Initialize (reads from environment variables)
client = XlinkIoTClient()
# Device overview
overview = client.get_device_overview(project_id="ab582")
# Device list
devices = client.get_device_list(limit=50)
# Alert statistics
alerts = client.get_alert_statistics(interval="hour")
# Event instances
events = client.get_event_instances(status=[1], limit=20)
# Device control
result = client.control_device(
thing_id="10299402",
service="device_attribute_set_service",
input_params={"PowerSwitch": True}
)
```
---
## Detailed Documentation
Complete CLI command reference, parameter descriptions, and API documentation:
- [`references/cli-reference.md`](references/cli-reference.md) - Complete CLI command reference
- [`references/api-auth.md`](references/api-auth.md) - Authentication mechanism and security
- [`references/api-doc.md`](references/api-doc.md) - Complete API documentation
- [`references/response-schema.md`](references/response-schema.md) - Response format definitions
---
## Error Handling
| Status | Description | Solution |
|------|------|----------|
| `401 Unauthorized` | Invalid credentials | Check App ID/Secret |
| `403 Forbidden` | Access denied | Verify Group ID and permissions |
| `404 Not Found` | Resource not found | Check endpoint path or resource ID |
| `429 Too Many Requests` | Rate limited | Implement exponential backoff retry |
| `500 Server Error` | Server error | Retry later |
---
## Best Practices
1. **Use pagination** - For large datasets, use `--offset` and `--limit`
2. **Filter early** - Apply filters (status, device, time) to reduce data transfer
3. **Cache results** - Device status changes infrequently; cache for 30-60 seconds
4. **Handle rate limits** - Implement exponential backoff for 429 errors
5. **JSON output for scripting** - Use `--json` for programmatic parsing
6. **Debug mode** - Use `--debug` for troubleshootingRelated 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