Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
82
75%
Does it follow best practices?
Impact
95%
2.11xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/perplexity-search/SKILL.mdModel selection by query complexity
LiteLLM install command
0%
100%
API key env var name
0%
100%
No hardcoded API key
100%
50%
Model ID format
0%
100%
Synthesis uses sonar-pro-search
0%
100%
Mechanism uses sonar-reasoning-pro
0%
100%
Lookup uses sonar
0%
100%
Default temperature 0.2
0%
100%
Default max_tokens 4000
0%
100%
JSON output saved
100%
100%
requirements_note.txt present
0%
100%
Query design and structure for research
Time constraints in queries
40%
100%
Source quality specification
40%
100%
Specific vs vague queries
100%
100%
Desired output format in queries
62%
100%
sonar-pro as default model
100%
100%
sonar-pro-search for comparative analysis
0%
100%
sonar-reasoning-pro for mechanisms
0%
100%
sonar for simple lookups
100%
100%
Calculations excluded
100%
100%
Code execution excluded
25%
0%
query_playbook.md produced
100%
100%
Batch search automation with rate limiting
Uses search_with_perplexity function
0%
83%
Sleep delay between requests
100%
100%
uv pip install in setup
0%
100%
OPENROUTER_API_KEY env var
100%
100%
No hardcoded credentials
100%
100%
Correct model ID format
0%
100%
Default model sonar-pro
0%
100%
Results saved as JSON
100%
100%
Token usage in saved results
100%
100%
topics_config.json produced
100%
100%
Config-driven topic list
100%
100%
b58ad7e
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.