perplexity-search

Name: perplexity-search
Author: LeonChaoX

698stars61forks

How to install perplexity-search?

leonchaox/qinyan-academic-skills/perplexity-search

$npx -y skills add LeonChaoX/qinyan-academic-skills --skill perplexity-search

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# Perplexity Search
2
3	## Overview
4
5	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.
6
7	This skill provides access to all Perplexity models through OpenRouter, requiring only a single API key (no separate Perplexity account needed).
8
9	## When to Use This Skill
10
11	Use this skill when:
12	- Searching for current information or recent developments (2024 and beyond)
13	- Finding latest scientific publications and research
14	- Getting real-time answers grounded in web sources
15	- Verifying facts with source citations
16	- Conducting literature searches across multiple domains
17	- Accessing information beyond the model's knowledge cutoff
18	- Performing domain-specific research (biomedical, technical, clinical)
19	- Comparing current approaches or technologies
20
21	Do not use for:
22	- Simple calculations or logic problems (use directly)
23	- Tasks requiring code execution (use standard tools)
24	- Questions well within the model's training data (unless verification needed)
25
26	## Quick Start
27
28	### Setup (One-time)
29
30	1. Get OpenRouter API key:
31	- Visit https://openrouter.ai/keys
32	- Create account and generate API key
33	- Add credits to account (minimum $5 recommended)
34
35	2. Configure environment:
36	```bash
37	# Set API key
38	export OPENROUTER_API_KEY='sk-or-v1-your-key-here'
39
40	# Or use setup script
41	python scripts/setup_env.py --api-key sk-or-v1-your-key-here
42	```
43
44	3. Install dependencies:
45	```bash
46	uv pip install litellm
47	```
48
49	4. Verify setup:
50	```bash
51	python scripts/perplexity_search.py --check-setup
52	```
53
54	See `references/openrouter_setup.md` for detailed setup instructions, troubleshooting, and security best practices.
55
56	### Basic Usage
57
58	Simple search:
59	```bash
60	python scripts/perplexity_search.py "What are the latest developments in CRISPR gene editing?"
61	```
62
63	Save results:
64	```bash
65	python scripts/perplexity_search.py "Recent CAR-T therapy clinical trials" --output results.json
66	```
67
68	Use specific model:
69	```bash
70	python scripts/perplexity_search.py "Compare mRNA and viral vector vaccines" --model sonar-pro-search
71	```
72
73	Verbose output:
74	```bash
75	python scripts/perplexity_search.py "Quantum computing for drug discovery" --verbose
76	```
77
78	## Available Models
79
80	Access models via `--model` parameter:
81
82	- sonar-pro (default): General-purpose search, best balance of cost and quality
83	- sonar-pro-search: Most advanced agentic search with multi-step reasoning
84	- sonar: Basic model, most cost-effective for simple queries
85	- sonar-reasoning-pro: Advanced reasoning with step-by-step analysis
86	- sonar-reasoning: Basic reasoning capabilities
87
88	Model selection guide:
89	- Default queries → `sonar-pro`
90	- Complex multi-step analysis → `sonar-pro-search`
91	- Explicit reasoning needed → `sonar-reasoning-pro`
92	- Simple fact lookups → `sonar`
93	- Cost-sensitive bulk queries → `sonar`
94
95	See `references/model_comparison.md` for detailed comparison, use cases, pricing, and performance characteristics.
96
97	## Crafting Effective Queries
98
99	### Be Specific and Detailed
100
101	Good examples:
102	- "What are the latest clinical trial results for CAR-T cell therapy in treating B-cell lymphoma published in 2024?"
103	- "Compare the efficacy and safety profiles of mRNA vaccines versus viral vector vaccines for COVID-19"
104	- "Explain AlphaFold3 improvements over AlphaFold2 with specific accuracy metrics from 2023-2024 research"
105
106	Bad examples:
107	- "Tell me about cancer treatment" (too broad)
108	- "CRISPR" (too vague)
109	- "vaccines" (lacks specificity)
110
111	### Include Time Constraints
112
113	Perplexity searches real-time web data:
114	- "What papers were published in Nature Medicine in 2024 about long COVID?"
115	- "What are the latest developments (past 6 months) in large language model efficiency?"
116	- "What was announced at NeurIPS 2023 regarding AI safety?"
117
118	### Specify Domain and Sources
119
120	For high-quality results, mention source preferences:
121	- "According to peer-reviewed publications in high-impact journals..."
122	- "Based on FDA-approved treatments..."
123	- "From clinical trial registries like clinicaltrials.gov..."
124
125	### Structure Complex Queries
126
127	Break com

People who liked this also viewed

6 picks

Type

perplexity-search

698stars61forks

View on GitHub

How to install perplexity-search?

leonchaox/qinyan-academic-skills/perplexity-search

$npx -y skills add LeonChaoX/qinyan-academic-skills --skill perplexity-search

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Perplexity Search
2
3	## Overview
4
5	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.
6
7	This skill provides access to all Perplexity models through OpenRouter, requiring only a single API key (no separate Perplexity account needed).
8
9	## When to Use This Skill
10
11	Use this skill when:
12	- Searching for current information or recent developments (2024 and beyond)
13	- Finding latest scientific publications and research
14	- Getting real-time answers grounded in web sources
15	- Verifying facts with source citations
16	- Conducting literature searches across multiple domains
17	- Accessing information beyond the model's knowledge cutoff
18	- Performing domain-specific research (biomedical, technical, clinical)
19	- Comparing current approaches or technologies
20
21	Do not use for:
22	- Simple calculations or logic problems (use directly)
23	- Tasks requiring code execution (use standard tools)
24	- Questions well within the model's training data (unless verification needed)
25
26	## Quick Start
27
28	### Setup (One-time)
29
30	1. Get OpenRouter API key:
31	- Visit https://openrouter.ai/keys
32	- Create account and generate API key
33	- Add credits to account (minimum $5 recommended)
34
35	2. Configure environment:
36	```bash
37	# Set API key
38	export OPENROUTER_API_KEY='sk-or-v1-your-key-here'
39
40	# Or use setup script
41	python scripts/setup_env.py --api-key sk-or-v1-your-key-here
42	```
43
44	3. Install dependencies:
45	```bash
46	uv pip install litellm
47	```
48
49	4. Verify setup:
50	```bash
51	python scripts/perplexity_search.py --check-setup
52	```
53
54	See `references/openrouter_setup.md` for detailed setup instructions, troubleshooting, and security best practices.
55
56	### Basic Usage
57
58	Simple search:
59	```bash
60	python scripts/perplexity_search.py "What are the latest developments in CRISPR gene editing?"
61	```
62
63	Save results:
64	```bash
65	python scripts/perplexity_search.py "Recent CAR-T therapy clinical trials" --output results.json
66	```
67
68	Use specific model:
69	```bash
70	python scripts/perplexity_search.py "Compare mRNA and viral vector vaccines" --model sonar-pro-search
71	```
72
73	Verbose output:
74	```bash
75	python scripts/perplexity_search.py "Quantum computing for drug discovery" --verbose
76	```
77
78	## Available Models
79
80	Access models via `--model` parameter:
81
82	- sonar-pro (default): General-purpose search, best balance of cost and quality
83	- sonar-pro-search: Most advanced agentic search with multi-step reasoning
84	- sonar: Basic model, most cost-effective for simple queries
85	- sonar-reasoning-pro: Advanced reasoning with step-by-step analysis
86	- sonar-reasoning: Basic reasoning capabilities
87
88	Model selection guide:
89	- Default queries → `sonar-pro`
90	- Complex multi-step analysis → `sonar-pro-search`
91	- Explicit reasoning needed → `sonar-reasoning-pro`
92	- Simple fact lookups → `sonar`
93	- Cost-sensitive bulk queries → `sonar`
94
95	See `references/model_comparison.md` for detailed comparison, use cases, pricing, and performance characteristics.
96
97	## Crafting Effective Queries
98
99	### Be Specific and Detailed
100
101	Good examples:
102	- "What are the latest clinical trial results for CAR-T cell therapy in treating B-cell lymphoma published in 2024?"
103	- "Compare the efficacy and safety profiles of mRNA vaccines versus viral vector vaccines for COVID-19"
104	- "Explain AlphaFold3 improvements over AlphaFold2 with specific accuracy metrics from 2023-2024 research"
105
106	Bad examples:
107	- "Tell me about cancer treatment" (too broad)
108	- "CRISPR" (too vague)
109	- "vaccines" (lacks specificity)
110
111	### Include Time Constraints
112
113	Perplexity searches real-time web data:
114	- "What papers were published in Nature Medicine in 2024 about long COVID?"
115	- "What are the latest developments (past 6 months) in large language model efficiency?"
116	- "What was announced at NeurIPS 2023 regarding AI safety?"
117
118	### Specify Domain and Sources
119
120	For high-quality results, mention source preferences:
121	- "According to peer-reviewed publications in high-impact journals..."
122	- "Based on FDA-approved treatments..."
123	- "From clinical trial registries like clinicaltrials.gov..."
124
125	### Structure Complex Queries
126
127	Break com

People who liked this also viewed

6 picks

Type