What is perplexity-search?

AI-powered web search, research, and reasoning via Perplexity.

What modes are available?

Quick answer (--ask), direct search (--search), AI-synthesized research (--research), chain-of-thought (--reason), and deep comprehensive research (--deep).

Do I need an API key?

Yes. Set PERPLEXITY_API_KEY in your environment or in ~/.claude/.env.

perplexity-search

npx machina-cli add skill parcadei/Continuous-Claude-v3/perplexity-search --openclaw

Files (1)

SKILL.md

3.1 KB

Perplexity AI Search

Web search with AI-powered answers, deep research, and chain-of-thought reasoning.

When to Use

Direct web search for ranked results (no AI synthesis)
AI-synthesized research with citations
Chain-of-thought reasoning for complex decisions
Deep comprehensive research on topics

Models (2025)

Model	Purpose
`sonar`	Lightweight search with grounding
`sonar-pro`	Advanced search for complex queries
`sonar-reasoning-pro`	Chain of thought reasoning
`sonar-deep-research`	Expert-level exhaustive research

Usage

Quick question (AI answer)

uv run python scripts/mcp/perplexity_search.py \
    --ask "What is the latest version of Python?"

Direct web search (ranked results, no AI)

uv run python scripts/mcp/perplexity_search.py \
    --search "SQLite graph database patterns" \
    --max-results 5 \
    --recency week

AI-synthesized research

uv run python scripts/mcp/perplexity_search.py \
    --research "compare FastAPI vs Django for microservices"

Chain-of-thought reasoning

uv run python scripts/mcp/perplexity_search.py \
    --reason "should I use Neo4j or SQLite for small graph under 10k nodes?"

Deep comprehensive research

uv run python scripts/mcp/perplexity_search.py \
    --deep "state of AI agent observability 2025"

Parameters

Parameter	Description
`--ask`	Quick question with AI answer (sonar)
`--search`	Direct web search - ranked results without AI synthesis
`--research`	AI-synthesized research (sonar-pro)
`--reason`	Chain-of-thought reasoning (sonar-reasoning-pro)
`--deep`	Deep comprehensive research (sonar-deep-research)

Search-specific options

Parameter	Description
`--max-results N`	Number of results (1-20, default: 10)
`--recency`	Filter: `day`, `week`, `month`, `year`
`--domains`	Limit to specific domains

Mode Selection Guide

Need	Use	Why
Quick fact	`--ask`	Fast, lightweight
Find sources	`--search`	Raw results, no AI overhead
Synthesized answer	`--research`	AI combines multiple sources
Complex decision	`--reason`	Chain-of-thought analysis
Comprehensive report	`--deep`	Exhaustive multi-source research

Examples

# Find recent sources on a topic
uv run python scripts/mcp/perplexity_search.py \
    --search "OpenTelemetry AI agent tracing" \
    --recency month --max-results 5

# Get AI synthesis
uv run python scripts/mcp/perplexity_search.py \
    --research "best practices for AI agent logging 2025"

# Make a decision
uv run python scripts/mcp/perplexity_search.py \
    --reason "microservices vs monolith for startup MVP"

# Deep dive
uv run python scripts/mcp/perplexity_search.py \
    --deep "comprehensive guide to building feedback loops for autonomous agents"

API Key Required

Requires PERPLEXITY_API_KEY in environment or ~/.claude/.env.

Source

git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/perplexity-search/SKILL.mdView on GitHub

Overview

Perplexity AI Search enables AI-assisted web searching, deep research, and reasoning using Perplexity-powered results. It supports quick AI answers, AI-synthesized research with citations, and exhaustive multi-source investigations to inform decisions.

How This Skill Works

Different modes map to dedicated Perplexity models: sonar for grounding and quick answers, sonar-pro for ranked searches and deep dives, sonar-reasoning-pro for chain-of-thought reasoning, and sonar-deep-research for exhaustive studies. You invoke the shared CLI with flags --ask, --search, --research, --reason, or --deep to perform tasks, optionally tuning with --max-results and --recency. An API key PERPLEXITY_API_KEY is required.

When to Use It

Direct web search for ranked results (no AI synthesis)
AI-synthesized research with citations
Chain-of-thought reasoning for complex decisions
Deep comprehensive research on topics
Find recent sources using recency filters

Quick Start

Step 1: Set PERPLEXITY_API_KEY in your environment or in ~/.claude/.env
Step 2: Pick a mode: --ask, --search, --research, --reason, or --deep
Step 3: Run a sample command, for example: uv run python scripts/mcp/perplexity_search.py --search SQLite graph database patterns --max-results 5 --recency week

Best Practices

Clearly select the task mode before running (use --ask, --search, --research, --reason, or --deep).
Use --max-results and --recency to control scope and freshness.
Cross-verify AI-synthesized results with primary sources and cite them where possible.
Narrow the search domain with --domains to focus on trusted sources.
Use --reason only for decisions that benefit from explicit chain-of-thought; avoid unnecessary reasoning.

Example Use Cases

Find recent sources on a topic like OpenTelemetry AI agent tracing with --search and --recency month --max-results 5
Get AI synthesis on best practices for AI agent logging 2025 using --research
Compare FastAPI vs Django for microservices with --research
Decide between Neo4j and SQLite for a small graph under 10k nodes using --reason
Deep dive into state of AI agent observability 2025 with --deep

Frequently Asked Questions

Add this skill to your agents