闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > perplexity-agent
p

Perplexity搜索代理

技能标识：perplexity-agent

Search the web using the Perplexity Agent API. Provides real-time information, news, and grounded answers with citations. Use when the user asks for: (1) Current events or news, (2) Information retrieval from the web, (3) Real-time data search, (4) In-depth research using web results.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.0.0
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

Perplexity搜索代理

Perplexity 智能搜索代理

使用 Perplexity 智能搜索代理 API 执行实时网络搜索并获取基于事实的答案。

工作流程

执行网络搜索的步骤：

  1. 1. 识别用户的研究或搜索查询。
  2. 使用该查询运行 scripts/search.py 脚本。
  3. 将 JSON 响应中的 answer 呈现给用户。

示例

搜索最新人工智能发展：
python3 scripts/search.py 人工智能领域的最新发展是什么？

重要说明

  • - 需要在环境中设置 PERPLEXITYAPIKEY。
  • 使用 pro-search 预设以获得高质量、经过研究的结果。
  • 返回包含 success、answer 以及所使用的 model 的 JSON 对象。

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 perplexity-agent-1776062045 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 perplexity-agent-1776062045 技能

通过命令行安装

skillhub install perplexity-agent-1776062045

下载

⬇ 下载 perplexity-agent v1.0.0（免费）

文件大小: 1.9 KB | 发布时间: 2026-4-15 13:52

v1.0.0 最新 2026-4-15 13:52
Initial release of perplexity-agent skill:

- Enables real-time web searches using the Perplexity Agent API.
- Provides answers with citations for news, current events, and in-depth research.
- Requires setting a PERPLEXITY_API_KEY environment variable.
- Utilizes the 'pro-search' preset for high-quality results.
- Returns results as a JSON object with keys: success, answer, and model.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部