← Back to Skills Marketplace
367
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install turing-tavily-web-search
Description
Search the web via the Turing Tavily proxy. Use when the user asks to search the web, look up real-time information, research current events, or needs up-to-...
Usage Guidance
Do not install blindly. Before using: (1) Confirm you trust the Turing Tavily proxy domain (default https://live-turing.cn.llm.tcljd.com) because your API key will be sent there. (2) Verify or update the registry metadata to declare TURING_API_KEY, TURING_CLIENT, and TURING_ENVIRONMENT so you know what secrets are required. (3) Check that the script's expected config location (~/.openclaw/openclaw.json) is acceptable to you — the script reads that file for credentials. (4) Ensure Python's 'requests' is available or install it in an isolated environment. (5) If you have doubts about the endpoint or owner, review the script yourself or run the skill in a locked-down container; do not provide production API keys until you are confident.
Capability Analysis
Type: OpenClaw Skill
Name: turing-tavily-web-search
Version: 1.0.0
The skill provides a legitimate interface for performing web searches via a Turing Tavily proxy. The Python script (scripts.py) correctly handles JSON input, retrieves necessary API credentials from the local OpenClaw configuration file (~/.openclaw/openclaw.json), and communicates with the designated API endpoint (live-turing.cn.llm.tcljd.com). No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
The code and SKILL.md implement a web search via a Turing Tavily proxy and require TURING_API_KEY, TURING_CLIENT, TURING_ENVIRONMENT — these credentials are proportional to the stated purpose. However, the registry-level metadata provided earlier declares no required env vars or primary credential, which is inconsistent with the skill's actual behavior.
Instruction Scope
SKILL.md instructs running the bundled script and configuring credentials in ~/.openclaw/openclaw.json (skills.entries.turing-skills.env). The script only reads that file and sends search queries to the Turing proxy; it does not attempt to read other system files. This scope is appropriate, but the reliance on a user config file (instead of environment variables at runtime) should be noted.
Install Mechanism
There is no install spec (lowest install risk) and no network-downloaded code. However, the bundled script uses the Python 'requests' package but the skill does not declare this dependency; runtime failures or unexpected local installs may occur if 'requests' is missing.
Credentials
The script requires TURING_API_KEY (Bearer token), TURING_CLIENT, and TURING_ENVIRONMENT, plus an optional TURING_API_BASE. Those are appropriate for calling the proxy API, but the registry metadata omitted these requirements. The mismatch between declared and actual credential needs is a red flag that could lead to misconfiguration or inadvertent secret exposure.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent system privileges. It only reads its own config file (~/.openclaw/openclaw.json) and does not write system-wide settings or modify other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install turing-tavily-web-search - After installation, invoke the skill by name or use
/turing-tavily-web-search - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of web search integration via Turing Tavily proxy.
- Search the web using the Turing Tavily proxy by running a Bash script; no manual HTTP requests needed.
- Supports single or batch queries, result count limits, and domain filtering.
- Returns AI-generated summaries and detailed result metadata (title, URL, content snippet, publication date).
- API credentials (TURING_API_KEY, TURING_CLIENT, TURING_ENVIRONMENT) required for setup.
- Detailed configuration and usage examples included in documentation.
Metadata
Frequently Asked Questions
What is Turing Tavily Web Search?
Search the web via the Turing Tavily proxy. Use when the user asks to search the web, look up real-time information, research current events, or needs up-to-... It is an AI Agent Skill for Claude Code / OpenClaw, with 367 downloads so far.
How do I install Turing Tavily Web Search?
Run "/install turing-tavily-web-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Turing Tavily Web Search free?
Yes, Turing Tavily Web Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Turing Tavily Web Search support?
Turing Tavily Web Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Turing Tavily Web Search?
It is built and maintained by CAPREaaa (@capreaaa); the current version is v1.0.0.
More Skills