← Back to Skills Marketplace
63
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install tg-cam-api-test
Description
探鸽摄像头 Skill 服务。用于查询当前 Skill 已绑定设备、查看当前画面、查询事件、查看事件图片、确认设备状态和电量。当用户要查看可操作设备、看某个摄像头当前截图、查询某天或某时段发生了什么、查看最近事件或事件图片、确认在线状态、查询电量时使用。
Usage Guidance
This skill appears to implement a camera API and only asks for two API credentials, which fits its purpose — but exercise caution because the skill's source/homepage are unknown and the configured API base (skill-test.webcamapp.cc) is not verified. Before installing: (1) confirm you trust the service operator and the API domain; (2) only use scoped, minimal-permission API keys (read-only if possible) that you can revoke or rotate; (3) expect the agent to fetch image URLs (which may be hosted on other domains) — fetching images can expose the agent's IP and headers to those hosting domains; (4) be aware the skill will persist TIVS_CLI_ID and TIVS_API_KEY into openclaw.json, so ensure your agent config storage is secure; (5) if unsure, ask the skill provider for documentation and a verified homepage or use a temporary key to test and then revoke it. If any of these checks fail or you cannot obtain scoped/revocable keys, do not install.
Capability Analysis
Type: OpenClaw Skill
Name: tg-cam-api-test
Version: 0.0.3
The skill bundle is a functional integration for a webcam service (Tange/探鸽) using the API endpoint https://skill-test.webcamapp.cc. It includes standard instructions for the AI agent to manage device listings, snapshots, and event logs, with security-conscious directives such as not echoing API keys in chat and handling credentials via a local configuration file (openclaw.json) as per the OpenClaw environment patterns.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description describe camera device listing, snapshots, events and battery/status checks; the declared environment variables (TIVS_CLI_ID, TIVS_API_KEY) are consistent with an API-backed camera service and are proportional to the stated purpose.
Instruction Scope
SKILL.md is detailed and stays within the camera API domain: all calls target a single base URL (https://skill-test.webcamapp.cc) and it prescribes request/response handling and image fetching. Two items merit attention: (1) it instructs the agent to fetch image content (rather than only show URLs) — fetching remote image URLs can reveal the agent's runtime environment (IP, request headers) to third-party hosts; (2) it instructs saving received credentials into openclaw.json, which persists secrets in agent config. Both behaviors are explainable by the skill's purpose but increase sensitive-surface area.
Install Mechanism
Instruction-only skill with no install spec or code files — nothing is downloaded or written beyond instructions the agent executes. This minimizes installer risk.
Credentials
Only two environment variables are required (TIVS_CLI_ID and TIVS_API_KEY), which is reasonable for a service-backed camera skill. However, these are full API credentials; the SKILL.md also directs persisting them into openclaw.json, so consider whether these keys are scoped (read-only, limited TTL) and easily revocable.
Persistence & Privilege
The skill is not force-enabled (always:false) and uses default autonomous invocation. It explicitly instructs writing its own credentials into openclaw.json (its own agent config) — this is normal for skills but does create persistent stored secrets that require the user to trust the service and to manage/rotate the keys if necessary.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tg-cam-api-test - After installation, invoke the skill by name or use
/tg-cam-api-test - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.3
- Major update: Added comprehensive documentation and usage guidelines for the skill in SKILL.md.
- Detailed interface descriptions, including API endpoints, required headers, request/response structures, and parameter formats.
- Clarified scenario-based instructions, request routing, and best practices for common user intents.
- Enumerated error handling, image processing, security reminders, and field interpretation constraints.
- Revised explanations for querying devices, snapshots, events, images, online status, and battery level.
Metadata
Frequently Asked Questions
What is TG Cam Test?
探鸽摄像头 Skill 服务。用于查询当前 Skill 已绑定设备、查看当前画面、查询事件、查看事件图片、确认设备状态和电量。当用户要查看可操作设备、看某个摄像头当前截图、查询某天或某时段发生了什么、查看最近事件或事件图片、确认在线状态、查询电量时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 63 downloads so far.
How do I install TG Cam Test?
Run "/install tg-cam-api-test" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TG Cam Test free?
Yes, TG Cam Test is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TG Cam Test support?
TG Cam Test is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TG Cam Test?
It is built and maintained by flyfinec (@flyfinec); the current version is v0.0.3.
More Skills