perplexity-search
Skill80 starsChanged 8 months agoMITView on GitHub
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.
- Reads credentials
- Installs packages
18 other projects use a version of this, 7 of them edited.
Adopted by
Most recently taken up by
- Ivan-propio/claude-skillsedited, first seen Nov 16, 2026
- runehub-ai/rune-hubtheir own version, first seen Nov 15, 2026
- BrightGold70/skillsedited, first seen Nov 8, 2026
- MarieLynneBlock/arcanum-artifexedited, first seen Nov 1, 2026
- parcadei/Continuous-Claudetheir own version, first seen Oct 17, 2026
- garri333/Skillsedited, first seen Oct 11, 2026
Other versions18 projects use a version of this.
Word for word · 1
- LeonChaoX/qinyan-academic-skills★ 910100% same
Edited · 7
- wu-yc/LabClaw★ 1.1k93% same
- ZanderRuss/obsidian-claude★ 1912% same
- MarieLynneBlock/arcanum-artifex★ 499% same
- BrightGold70/skills★ 193% same
- garri333/Skills★ 193% same
- yf8578/claude-skills-collection★ 193% same
- Ivan-propio/claude-skills★ 0100% same
Wrote their own version · 10
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- escapeWu/perplexity-ai★ 168same name
- runehub-ai/rune-hub★ 6same name
- SELAT-AI/selat-openclaw-skills★ 2same name
- SELAT-AI/selat-skills★ 2same name
- mfang0126/perplexity-toolkit★ 1same name
- baofeng-tech/agent-skills-so★ 0same name
- bokiko/continuous-claude-guide★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository180 other files it gives its agents.
- bgpt-paper-searchSkill
- biorxiv-databaseSkill
- citation-managementSkill
- literature-reviewSkill
- openalex-databaseSkill
- parallel-webSkill
- pubmed-databaseSkill
- pyzoteroSkill
- research-lookupSkill
- medical-imaging-reviewSkill
- paper-2-webSkill
- peer-reviewSkill
- research-proposalSkill
- scientific-writingSkill
- venue-templatesSkill
- generate-imageSkill
- infographicsSkill
- latex-postersSkill
- markdown-mermaid-writingSkill
- paper-slide-deckSkill
- pptx-postersSkill
- scientific-schematicsSkill
- scientific-slidesSkill
- scientific-visualizationSkill
- consciousness-councilSkill
- dhdna-profilerSkill
- hypothesis-generationSkill
- research-grantsSkill
- scholar-evaluationSkill
- scientific-brainstormingSkill
- scientific-critical-thinkingSkill
- what-if-oracleSkill
- anndataSkill
- arboretoSkill
- biopythonSkill
- bioservicesSkill
- cellxgene-censusSkill
- deeptoolsSkill
- etetoolkitSkill
- flowioSkill
- genimlSkill
- ggetSkill
- gtarsSkill
- lamindbSkill
- phylogeneticsSkill
- pydeseq2Skill
- pysamSkill
- scanpySkill
- scikit-bioSkill
- scveloSkill
- scvi-toolsSkill
- tiledbvcfSkill
- zarr-pythonSkill
- datamolSkill
- deepchemSkill
- diffdockSkill
- matchmsSkill
- medchemSkill
- molecular-dynamicsSkill
- molfeatSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
24 rules. 0 are common, 19 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
19
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 20
Use this skill when:
- Distinctive: line 41
Create account and generate API key
- Distinctive: line 42
Add credits to account (minimum $5 recommended)
- Very specific: line 193
Use perplexity_search.py as a module:
- Distinctive: line 226
Create a script for multiple queries:
- Very specific: line 254
Use sonar for simple fact lookups
- Very specific: line 255
Default to sonar-pro for most queries
- Distinctive: line 288
Wait a few seconds before retrying
- Distinctive: line 290
Add delays between requests in batch processing
- Distinctive: line 297
Add credits at https://openrouter.ai/account
- Very specific: line 308
Use with literature-review skill:
- Distinctive: line 309
Use Perplexity to find recent papers and preprints
- Distinctive: line 311
Verify citations and find related work
- Distinctive: line 318
Verify current state of the art
- Distinctive: line 319
Check latest terminology and conventions
- Distinctive: line 325
Search for latest research findings
- Distinctive: line 336
Verify claims with current evidence
- Distinctive: line 351
Upgrade for complexity: Use sonar-pro-search for multi-step analysis
- Distinctive: line 352
Downgrade for simplicity: Use sonar for basic facts
- Distinctive: line 353
Use reasoning models: When step-by-step analysis needed
- Very specific: line 358
Set token limits: Use --max-tokens to control costs
- Distinctive: line 359
Monitor usage: Check OpenRouter dashboard regularly
- Distinctive: line 365
Protect API keys: Never commit to version control
- Distinctive: line 366
Use environment variables: Keep keys separate from code
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Perplexity Search
Overview
Perform AI-powered web searches using Perplexity models through LiteLLM and OpenRouter. Perplexity provides real-time, web-grounded answers with source citations, making it ideal for finding current information, recent scientific literature, and facts beyond the model's training data cutoff.
This skill provides access to all Perplexity models through OpenRouter, requiring only a single API key (no separate Perplexity account needed).
When to Use This Skill
Use this skill when:
- Searching for current information or recent developments (2024 and beyond)
- Finding latest scientific publications and research
- Getting real-time answers grounded in web sources
- Verifying facts with source citations
- Conducting literature searches across multiple domains
- Accessing information beyond the model's knowledge cutoff
- Performing domain-specific research (biomedical, technical, clinical)
- Comparing current approaches or technologies
Do not use for:
- Simple calculations or logic problems (use directly)
- Tasks requiring code execution (use standard tools)
- Questions well within the model's training data (unless verification needed)
Quick Start
Setup (One-time)
- Get OpenRouter API key:
- Visit https://openrouter.ai/keys
- Create account and generate API key
- Add credits to account (minimum $5 recommended)
- Configure environment:
# Set API key export OPENROUTER_API_KEY='sk-or-v1-your-key-here' # Or use setup script python scripts/setup_env.py --api-key sk-or-v1-your-key-here - Install dependencies:
uv pip install litellm - Verify setup:
python scripts/perplexity_search.py --check-setup
See references/openrouter_setup.md for detailed setup instructions, troubleshooting, and security best practices.
Basic Usage
Simple search:
python scripts/perplexity_search.py "What are the latest developments in CRISPR gene editing?"Save results:
python scripts/perplexity_search.py "Recent CAR-T therapy clinical trials" --output results.jsonUse specific model:
python scripts/perplexity_search.py "Compare mRNA and viral vector vaccines" --model sonar-pro-searchVerbose output:
python scripts/perplexity_search.py "Quantum computing for drug discovery" --verboseAvailable Models
Access models via --model parameter:
- sonar-pro (default): General-purpose search, best balance of cost and quality
- sonar-pro-search: Most advanced agentic search with multi-step reasoning
- sonar: Basic model, most cost-effective for simple queries
- sonar-reasoning-pro: Advanced reasoning with step-by-step analysis
- sonar-reasoning: Basic reasoning capabilities
Model selection guide:
- Default queries →
sonar-pro - Complex multi-step analysis →
sonar-pro-search - Explicit reasoning needed →
sonar-reasoning-pro - Simple fact lookups →
sonar - Cost-sensitive bulk queries →
sonar
See references/model_comparison.md for detailed comparison, use cases, pricing, and performance characteristics.
Crafting Effective Queries
Be Specific and Detailed
Good examples:
- "What are the latest clinical trial results for CAR-T cell therapy in treating B-cell lymphoma published in 2024?"
- "Compare the efficacy and safety profiles of mRNA vaccines versus viral vector vaccines for COVID-19"
- "Explain AlphaFold3 improvements over AlphaFold2 with specific accuracy metrics from 2023-2024 research"
Bad examples:
- "Tell me about cancer treatment" (too broad)
- "CRISPR" (too vague)
- "vaccines" (lacks specificity)
Include Time Constraints
Perplexity searches real-time web data:
- "What papers were published in Nature Medicine in 2024 about long COVID?"
- "What are the latest developments (past 6 months) in large language model efficiency?"
- "What was announced at NeurIPS 2023 regarding AI safety?"
Specify Domain and Sources
For high-quality results, mention source preferences:
- "According to peer-reviewed publications in high-impact journals..."
- "Based on FDA-approved treatments..."
- "From clinical trial registries like clinicaltrials.gov..."
Structure Complex Queries
Break complex questions into clear components:
- Topic: Main subject
- Scope: Specific aspect of interest
- Context: Time frame, domain, constraints
- Output: Desired format or type of answer
Example: "What improvements does AlphaFold3 offer over AlphaFold2 for protein structure prediction, according to research published between 2023 and 2024? Include specific accuracy metrics and benchmarks."
See references/search_strategies.md for comprehensive guidance on query design, domain-specific patterns, and advanced techniques.
Common Use Cases
Scientific Literature Search
python scripts/perplexity_search.py \
"What does recent research (2023-2024) say about the role of gut microbiome in Parkinson's disease? Focus on peer-reviewed studies and include specific bacterial species identified." \
--model sonar-proTechnical Documentation
python scripts/perplexity_search.py \
"How to implement real-time data streaming from Kafka to PostgreSQL using Python? Include considerations for handling backpressure and ensuring exactly-once semantics." \
--model sonar-reasoning-proComparative Analysis
python scripts/perplexity_search.py \
"Compare PyTorch versus TensorFlow for implementing transformer models in terms of ease of use, performance, and ecosystem support. Include benchmarks from recent studies." \
--model sonar-pro-searchClinical Research
python scripts/perplexity_search.py \
"What is the evidence for intermittent fasting in managing type 2 diabetes in adults? Focus on randomized controlled trials and report HbA1c changes and weight loss outcomes." \
--model sonar-proTrend Analysis
python scripts/perplexity_search.py \
"What are the key trends in single-cell RNA sequencing technology over the past 5 years? Highlight improvements in throughput, cost, and resolution, with specific examples." \
--model sonar-proWorking with Results
Programmatic Access
Use perplexity_search.py as a module:
from scripts.perplexity_search import search_with_perplexity
result = search_with_perplexity(
query="What are the latest CRISPR developments?",
model="openrouter/perplexity/sonar-pro",
max_tokens=4000,
temperature=0.2,
verbose=False
)
if result["success"]:
print(result["answer"])
print(f"Tokens used: {result['usage']['total_tokens']}")
else:
print(f"Error: {result['error']}")Save and Process Results
# Save to JSON
python scripts/perplexity_search.py "query" --output results.json
# Process with jq
cat results.json | jq '.answer'
cat results.json | jq '.usage'Batch Processing
Create a script for multiple queries:
#!/bin/bash
queries=(
"CRISPR developments 2024"
"mRNA vaccine technology advances"
"AlphaFold3 accuracy improvements"
)
for query in "${queries[@]}"; do
echo "Searching: $query"
python scripts/perplexity_search.py "$query" --output "results_$(echo $query | tr ' ' '_').json"
sleep 2 # Rate limiting
doneCost Management
Perplexity models have different pricing tiers:
Approximate costs per query:
- Sonar: $0.001-0.002 (most cost-effective)
- Sonar Pro: $0.002-0.005 (recommended default)
- Sonar Reasoning Pro: $0.005-0.010
- Sonar Pro Search: $0.020-0.050+ (most comprehensive)
Cost optimization strategies:
- Use
sonarfor simple fact lookups - Default to
sonar-profor most queries - Reserve
sonar-pro-searchfor complex analysis - Set
--max-tokensto limit response length - Monitor usage at https://openrouter.ai/activity
- Set spending limits in OpenRouter dashboard
Troubleshooting
API Key Not Set
Error: "OpenRouter API key not configured"
Solution:
export OPENROUTER_API_KEY='sk-or-v1-your-key-here'
# Or run setup script
python scripts/setup_env.py --api-key sk-or-v1-your-key-hereLiteLLM Not Installed
Error: "LiteLLM not installed"
Solution:
uv pip install litellmRate Limiting
Error: "Rate limit exceeded"
Solutions:
- Wait a few seconds before retrying
- Increase rate limit at https://openrouter.ai/keys
- Add delays between requests in batch processing
Insufficient Credits
Error: "Insufficient credits"
Solution:
- Add credits at https://openrouter.ai/account
- Enable auto-recharge to prevent interruptions
See references/openrouter_setup.md for comprehensive troubleshooting guide.
Integration with Other Skills
This skill complements other scientific skills:
Literature Review
Use with literature-review skill:
- Use Perplexity to find recent papers and preprints
- Supplement PubMed searches with real-time web results
- Verify citations and find related work
- Discover latest developments post-database indexing
Scientific Writing
Use with scientific-writing skill:
- Find recent references for introduction/discussion
- Verify current state of the art
- Check latest terminology and conventions
- Identify recent competing approaches
Hypothesis Generation
Use with hypothesis-generation skill:
- Search for latest research findings
- Identify current gaps in knowledge
- Find recent methodological advances
- Discover emerging research directions
Critical Thinking
Use with scientific-critical-thinking skill:
- Find evidence for and against hypotheses
- Locate methodological critiques
- Identify controversies in the field
- Verify claims with current evidence
Best Practices
Query Design
- Be specific: Include domain, time frame, and constraints
- Use terminology: Domain-appropriate keywords and phrases
- Specify sources: Mention preferred publication types or journals
- Structure questions: Clear components with explicit context
- Iterate: Refine based on initial results
Model Selection
- Start with sonar-pro: Good default for most queries
- Upgrade for complexity: Use sonar-pro-search for multi-step analysis
- Downgrade for simplicity: Use sonar for basic facts
- Use reasoning models: When step-by-step analysis needed
Cost Optimization
- Choose appropriate models: Match model to query complexity
- Set token limits: Use
--max-tokensto control costs - Monitor usage: Check OpenRouter dashboard regularly
- Batch efficiently: Combine related simple queries when possible
- Cache results: Save and reuse results for repeated queries
Security
- Protect API keys: Never commit to version control
- Use environment variables: Keep keys separate from code
- Set spending limits: Configure in OpenRouter dashboard
- Monitor usage: Watch for unexpected activity
- Rotate keys: Change keys periodically
Resources
Bundled Resources
Scripts:
scripts/perplexity_search.py: Main search script with CLI interfacescripts/setup_env.py: Environment setup and validation helper
References:
references/search_strategies.md: Comprehensive query design guidereferences/model_comparison.md: Detailed model comparison and selection guidereferences/openrouter_setup.md: Complete setup, troubleshooting, and security guide
Assets:
assets/.env.example: Example environment file template
External Resources
OpenRouter:
- Dashboard: https://openrouter.ai/account
- API Keys: https://openrouter.ai/keys
- Perplexity Models: https://openrouter.ai/perplexity
- Usage Monitoring: https://openrouter.ai/activity
- Documentation: https://openrouter.ai/docs
LiteLLM:
- Documentation: https://docs.litellm.ai/
- OpenRouter Provider: https://docs.litellm.ai/docs/providers/openrouter
- GitHub: https://github.com/BerriAI/litellm
Perplexity:
- Official Docs: https://docs.perplexity.ai/
Dependencies
Required
# LiteLLM for API access
uv pip install litellmOptional
# For .env file support
uv pip install python-dotenv
# For JSON processing (usually pre-installed)
uv pip install jqEnvironment Variables
Required:
OPENROUTER_API_KEY: Your OpenRouter API key
Optional:
DEFAULT_MODEL: Default model to use (default: sonar-pro)DEFAULT_MAX_TOKENS: Default max tokens (default: 4000)DEFAULT_TEMPERATURE: Default temperature (default: 0.2)
Summary
This skill provides:
- Real-time web search: Access current information beyond training data cutoff
- Multiple models: From cost-effective Sonar to advanced Sonar Pro Search
- Simple setup: Single OpenRouter API key, no separate Perplexity account
- Comprehensive guidance: Detailed references for query design and model selection
- Cost-effective: Pay-as-you-go pricing with usage monitoring
- Scientific focus: Optimized for research, literature search, and technical queries
- Easy integration: Works seamlessly with other scientific skills
Conduct AI-powered web searches to find current information, recent research, and grounded answers with source citations.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

