TacoSkill LAB
TacoSkill LAB
HomeSkillHubCreatePlaygroundSkillKit
© 2026 TacoSkill LAB
AboutPrivacyTerms
  1. Home
  2. /
  3. SkillHub
  4. /
  5. perplexity-search
Improve

perplexity-search

8.3

by K-Dense-AI

151Favorites
288Upvotes
0Downvotes

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.

search

8.3

Rating

0

Installs

AI & LLM

Category

Quick Review

Exceptional skill with comprehensive documentation. The description perfectly captures when and how to invoke the skill. Task knowledge is thorough with clear setup instructions, multiple usage examples, query optimization strategies, and programmatic access patterns. Structure is excellent with a logical flow from quick start to advanced usage, though SKILL.md is somewhat lengthy (could delegate more to reference files). Novelty is strong: accessing real-time web information with citations addresses a clear LLM limitation (knowledge cutoff), and the multi-model approach with cost optimization guidance provides meaningful value beyond what a CLI agent could easily accomplish.

LLM Signals

Description coverage10
Task knowledge10
Structure9
Novelty8

GitHub Signals

6,869
818
49
3
Last commit 1 days ago

Publisher

K-Dense-AI

K-Dense-AI

Skill Author

Related Skills

rag-architectprompt-engineerfine-tuning-expert

Loading SKILL.md…

Try onlineView on GitHub

Publisher

K-Dense-AI avatar
K-Dense-AI

Skill Author

Related Skills

rag-architect

Jeffallan

7.0

prompt-engineer

Jeffallan

7.0

fine-tuning-expert

Jeffallan

6.4

mcp-developer

Jeffallan

6.4
Try online