An AI-powered web search tool providing three levels of depth—quick search, logical reasoning, and exhaustive research—directly through the Perplexity API.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install perplexity-deep-search
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install perplexity-deep-search using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Perplexity Deep Search skill brings the power of real-time web intelligence to your AI coding agent. By leveraging specialized models like sonar-pro and sonar-reasoning-pro, this Openclaw Skills entry enables agents to ground their responses in up-to-date facts and verified citations.
This integration allows developers and researchers to bypass manual browsing by automating the retrieval of high-signal information. Whether you need a quick summary of current events or a multi-step logical analysis of complex technical architectures, this skill provides a structured interface for high-quality information retrieval directly within your development environment.
To use this skill within the Openclaw Skills ecosystem, ensure you have curl and jq installed.
Set your API key as an environment variable:
export PERPLEXITY_API_KEY="your_api_key_here"
Alternatively, you can store the key in a local configuration file for persistence:
mkdir -p ~/.config/perplexity
echo "your_key_here" > ~/.config/perplexity/api_key
chmod 600 ~/.config/perplexity/api_key
The skill organizes its output based on the selected mode and provided flags. It supports structured parameters to narrow the scope of the search.
| Option | Description | Values |
|---|---|---|
| --mode | Selection of search depth | search, reason, research |
| --recency | Temporal filter for results | hour, day, week, month |
| --domains | Domain-specific filtering | Comma-separated domains |
| --lang | Output language | en, pt, es, etc. |
| --json | Data output format | Boolean (on/off) |
Loading
An automated cycling performance analyst that tracks Strava rides and provides deep technical insights.

A powerful automation tool for requesting and managing movies and TV shows via Jellyseerr for self-hosted media servers.

A robust email validation tool that identifies and blocks temporary or disposable email addresses via the AntiTempMail API.

A specialized skill for retrieving real-time U.S. sales tax rates and jurisdictional breakdowns via the ZipTax API.

A high-performance search skill for querying Google Search, News, and Local listings with precise regional and language targeting.

A utility to instantly retrieve the public IPv4 and IPv6 address of the environment running your AI agent.








































