← 返回 Skills 市场
test
作者
Dang Trung Kien
· GitHub ↗
· v1.0.0
· MIT-0
131
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ken-test
功能描述
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
使用说明 (SKILL.md)
Baidu Search
Search the web via Baidu AI Search API.
Prerequisites
API Key Configuration
This skill requires a BAIDU_API_KEY to be configured in OpenClaw.
If you don't have an API key yet, please visit: https://console.bce.baidu.com/ai-search/qianfan/ais/console/apiKey
For detailed setup instructions, see: references/apikey-fetch.md
Usage
python3 skills/baidu-search/scripts/search.py '\x3CJSON>'
Request Parameters
| Param | Type | Required | Default | Description |
|---|---|---|---|---|
| query | str | yes | - | Search query |
| count | int | no | 10 | Number of results to return, range 1-50 |
| freshness | str | no | Null | Time range, two formats: format one is ”YYYY-MM-DDtoYYYY-MM-DD“, and format two includes pd, pw, pm, and py, representing the past 24 hours, past 7 days, past 31 days, and past 365 days respectively |
Examples
# Basic search
python3 scripts/search.py '{"query":"人工智能"}'
# Freshness first format "YYYY-MM-DDtoYYYY-MM-DD" example
python3 scripts/search.py '{
"query":"最新新闻",
"freshness":"2025-09-01to2025-09-08"
}'
# Freshness second format pd、pw、pm、py example
python3 scripts/search.py '{
"query":"最新新闻",
"freshness":"pd"
}'
# set count, the number of results to return
python3 scripts/search.py '{
"query":"旅游景点",
"count": 20,
}'
Current Status
Fully functional.
安全使用建议
This skill's code looks straightforward and implements Baidu web search, but there are a few red flags to check before installing:
- Verify the author/source: package metadata and owner IDs differ from the embedded _meta.json and the registry slug; confirm you trust the publisher before giving it your BAIDU_API_KEY.
- Confirm dependencies: the script requires the Python 'requests' library but the skill doesn't declare or install it. Install it in a controlled environment (e.g., pip install requests) or run in an isolated container.
- Review duplicates: the same files appear in multiple places in the package; confirm this isn't accidental tampering.
- Protect your API key: the skill expects BAIDU_API_KEY and suggests adding it to ~/.openclaw/openclaw.json. Consider whether you want the key in that file (it persists on disk) or prefer setting it in a session-scoped environment instead.
- Run in isolation first: execute the script manually with a throwaway API key or in a sandbox to confirm behavior (it only contacts qianfan.baidubce.com and prints returned references).
If you cannot verify the publisher or the packaging anomalies, avoid installing or provide the skill with a limited/testing API key until you are comfortable.
功能分析
Type: OpenClaw Skill
Name: ken-test
Version: 1.0.0
The skill is a legitimate implementation of a Baidu AI Search interface. The core logic in `scripts/search.py` safely parses JSON input, validates search parameters (query, count, freshness), and communicates exclusively with the official Baidu API endpoint (qianfan.baidubce.com) using an environment-provided API key. The documentation in `SKILL.md` and `references/apikey-fetch.md` provides standard setup and usage instructions without any evidence of prompt injection or malicious intent.
能力评估
Purpose & Capability
The declared purpose (Baidu web search) matches the code: the Python script calls the Baidu qianfan web_search endpoint using BAIDU_API_KEY. However the package metadata is inconsistent: top-level name/slug/owner (registry metadata shows 'test' / 'ken-test' / owner kn7akw...) differs from embedded _meta.json entries (slug 'baidu-search', different ownerId), and files are duplicated under baidu-search-1.1.2 as well as top-level. These packaging/name/owner mismatches are unexpected and should be validated.
Instruction Scope
Runtime instructions and the script stay within the described purpose: they parse a JSON query, build a request body, and call Baidu's API. The instructions only reference BAIDU_API_KEY and a suggested OpenClaw config path (~/.openclaw/openclaw.json) for storing the key. There is no code that reads unrelated system files or exfiltrates data to unexpected endpoints.
Install Mechanism
No install spec (instruction-only) so nothing arbitrary gets downloaded at install time. However the Python script imports the third-party 'requests' library but the skill does not declare this dependency or provide an install step; that is an omission which may cause runtime failures. File duplication (same script repeated in two paths) is also unusual and worth confirmation.
Credentials
The only required environment variable is BAIDU_API_KEY (declared as primaryEnv) which is proportionate to a Baidu search integration. The script reads only BAIDU_API_KEY from the environment and nothing else.
Persistence & Privilege
The skill does not request 'always: true' and does not attempt to modify other skills or system-wide settings. The README suggests editing the OpenClaw config to add the API key, which is typical for credential setup and within scope.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ken-test - 安装完成后，直接呼叫该 Skill 的名称或使用
/ken-test触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of baidu-search skill.
- Enables web search via Baidu AI Search API for live information, documentation, or research topics.
- Requires configuration of a BAIDU_API_KEY environment variable.
- Supports advanced search features, including adjustable result count (1–50) and time range filtering.
- Provides detailed usage instructions and example commands.
- Fully functional and ready for use.
元数据
常见问题
test 是什么？
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 131 次。
如何安装 test？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ken-test」即可一键安装，无需额外配置。
test 是免费的吗？
是的，test 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
test 支持哪些平台？
test 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 test？
由 Dang Trung Kien（@dtkien182）开发并维护，当前版本 v1.0.0。
推荐 Skills