← 返回 Skills 市场
Verified Research Engine (Web + Academic + Confidence Score)
作者
chaimengphp
· GitHub ↗
· v1.0.1
· MIT-0
839
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install openclaw-aisa-search
功能描述
Intelligent search for agents. Multi-source retrieval across web, scholar, Tavily, and Perplexity Sonar models.
安全使用建议
This skill is a straightforward client for the AIsa search API. Before installing, confirm you trust the AIsa service (api.aisa.one), and only provide an API key with appropriate scope/limits. Be aware the agent will make outbound HTTPS requests using your AISA_API_KEY (which could incur usage/costs and transmit query text). If you need stricter control, create a scoped API key or monitor API usage and logs. You can also review the included scripts (search_client.py) yourself — they are small and only call the documented endpoints. If you want to be extra cautious, run the client in a restricted environment or with a key limited to read-only/search-only permissions.
功能分析
Type: OpenClaw Skill
Name: openclaw-aisa-search
Version: 1.0.1
The skill provides a legitimate search interface for OpenClaw agents, integrating with the AIsa API (api.aisa.one) to provide web, academic, and AI-powered search results (Perplexity Sonar). The Python client in `scripts/search_client.py` is well-structured, using standard libraries for network requests and parallel execution without any signs of malicious behavior, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
The name/description promise multi-source search (web, scholar, Tavily, Perplexity Sonar). The skill only requires curl, python3, and a single AISA_API_KEY — all of which are necessary and proportional for calling the external AIsa APIs described.
Instruction Scope
SKILL.md instructs the agent to call documented AIsa endpoints and to set AISA_API_KEY. The included Python client only issues HTTPS requests to api.aisa.one and does not read unrelated system files, other environment variables, or send data to unexpected endpoints.
Install Mechanism
There is no install spec (instruction-only) and the packaged code is a client script. No downloads or extract steps are performed, which minimizes on-disk installation risk.
Credentials
Only one credential (AISA_API_KEY) is required and it directly maps to the described external API usage. No additional secrets, config paths, or unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled (always:false) and does not request elevated persistent system presence. Autonomous invocation is allowed (platform default) but is not combined with other concerning privileges.
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 openclaw-aisa-search - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-aisa-search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
v1.0.1
**Adds Perplexity Sonar answer-generation endpoints and removes deprecated full text/smart search.**
- Integrated new Perplexity Sonar family endpoints (sonar, sonar-pro, sonar-reasoning-pro, sonar-deep-research) for answer generation with citations.
- Removed deprecated `/search/full` and `/search/smart` endpoints from docs and workflow.
- Updated documentation and examples to focus on Perplexity Sonar APIs for advanced, citation-rich searches and deep research reports.
- Adjusted quick start and Python client instructions to cover new endpoints and usage.
- Slight metadata update: new emoji and clarified description.
- All other structured search (web, scholar, Tavily) endpoints remain supported.
v1.0.0
Initial release of OpenClaw Search – unified multi-source search with confidence scoring.
- Intelligent search across web, academic, and Tavily sources in one API.
- Two-phase retrieval: parallel multi-stream discovery and meta-analysis with confidence scoring.
- Rich API and Python client for web, scholar, smart, and Tavily operations.
- Confidence rubric evaluates credibility, consensus, and source quality.
- Extensive examples and documentation for research, market intelligence, and more.
元数据
常见问题
Verified Research Engine (Web + Academic + Confidence Score) 是什么？
Intelligent search for agents. Multi-source retrieval across web, scholar, Tavily, and Perplexity Sonar models. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 839 次。
如何安装 Verified Research Engine (Web + Academic + Confidence Score)？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-aisa-search」即可一键安装，无需额外配置。
Verified Research Engine (Web + Academic + Confidence Score) 是免费的吗？
是的，Verified Research Engine (Web + Academic + Confidence Score) 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Verified Research Engine (Web + Academic + Confidence Score) 支持哪些平台？
Verified Research Engine (Web + Academic + Confidence Score) 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 Verified Research Engine (Web + Academic + Confidence Score)？
由 chaimengphp（@chaimengphp）开发并维护，当前版本 v1.0.1。
推荐 Skills