← Back to Skills Marketplace
300
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install turing-baidu-web-search
Description
Search the web via the Turing Baidu proxy. Use when the user asks to search the web in Chinese, look up real-time information from Chinese sources, research...
Usage Guidance
This skill's code and README legitimately call a Turing Baidu proxy and need three Turing credentials. However, the registry metadata incorrectly lists no required credentials — that mismatch is the main red flag. Before installing: verify the skill owner/source (homepage is docs.turing.cn but owner is unknown), confirm where you will store the TURING_API_KEY/CLIENT/ENV (the script reads ~/.openclaw/openclaw.json), and ensure those tokens are scoped and revocable. Consider testing in a sandbox with a limited-scope test key first. If you rely on the registry entry, ask the publisher to correct the advertised required env vars so the permissions are explicit. If you do not trust the owner, do not provide production credentials.
Capability Analysis
Type: OpenClaw Skill
Name: turing-baidu-web-search
Version: 1.0.0
The skill is a legitimate implementation for performing Baidu web searches via the Turing proxy API. The Python script (scripts.py) correctly retrieves credentials from the standard OpenClaw configuration file and makes authenticated requests to the specified API endpoint (live-turing.cn.llm.tcljd.com). The code logic is transparent, lacks obfuscation, and strictly follows the functionality described in SKILL.md.
Capability Assessment
Purpose & Capability
The SKILL.md and scripts.py both require TURING_API_KEY, TURING_CLIENT, and TURING_ENVIRONMENT and call a Turing Baidu proxy endpoint — that matches the declared purpose. However, the registry metadata (top-level requirements) lists no required env vars or primary credential, creating an incoherence between what the skill actually needs and what the registry advertises.
Instruction Scope
Runtime instructions are narrowly scoped: run the bundled script with a JSON argument and supply Turing credentials via openclaw.json. The script only reads ~/.openclaw/openclaw.json for its config and does HTTP POSTs to the declared Turing proxy endpoint. It does not access other system files or network endpoints. The only scope oddity is that SKILL.md says 'do NOT construct HTTP requests manually' and mandates using the bundled script — reasonable but restrictive.
Install Mechanism
No install spec or remote downloads; the skill is instruction + a small local Python script. There is no external installer or archive extraction, which is low-risk.
Credentials
The credentials requested in SKILL.md and scripts.py (TURING_API_KEY, TURING_CLIENT, TURING_ENVIRONMENT, optional TURING_API_BASE) are proportional to a proxy search API. Concern arises because the registry metadata does not declare these required credentials, and the script expects them in ~/.openclaw/openclaw.json rather than (or in addition to) process environment — this mismatch could surprise users and lead to misplaced secrets. No unrelated secrets are requested.
Persistence & Privilege
always:false (default) and the skill does not modify other skills or system-wide settings. Autonomous invocation (disable-model-invocation:false) is the platform default; combined with credential access this increases blast radius but is expected for a web-search skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install turing-baidu-web-search - After installation, invoke the skill by name or use
/turing-baidu-web-search - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Baidu Web Search skill via Turing Baidu proxy.
- Enables web search in Chinese, with up-to-date Baidu results.
- Use the included script for all API interactions; no manual HTTP requests needed.
- Supports search queries, adjustable result count, and recency filters (week, month, semiyear, year).
- Returns results with title, URL, snippet, date, and type.
- Requires TURING_API_KEY, TURING_CLIENT, and TURING_ENVIRONMENT for configuration.
Metadata
Frequently Asked Questions
What is Turing Baidu Web Search?
Search the web via the Turing Baidu proxy. Use when the user asks to search the web in Chinese, look up real-time information from Chinese sources, research... It is an AI Agent Skill for Claude Code / OpenClaw, with 300 downloads so far.
How do I install Turing Baidu Web Search?
Run "/install turing-baidu-web-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Turing Baidu Web Search free?
Yes, Turing Baidu Web Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Turing Baidu Web Search support?
Turing Baidu Web Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Turing Baidu Web Search?
It is built and maintained by CAPREaaa (@capreaaa); the current version is v1.0.0.
More Skills