From perplexity
Searches web, answers queries conversationally, and researches deeply using Perplexity AI tools for generic topics. Auto-activates on 'search'/'find'; manual /perplexity or /research.
How this skill is triggered — by the user, by Claude, or both
Slash command
/perplexity:perplexityThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use ONLY when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7), gt CLI (use Graphite MCP), or workspace questions (use Nx MCP).
Use ONLY when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7), gt CLI (use Graphite MCP), or workspace questions (use Nx MCP).
Which Perplexity tool?
/research <topic>)NOT Perplexity - use these instead:
gt CLI → Graphite MCPWhen to use:
Default parameters (ALWAYS USE):
mcp__perplexity__perplexity_search({
query: "your search query",
max_results: 3, // Default is 10 - too many!
max_tokens_per_page: 512 // Reduce per-result content
})
When to increase limits: Only if:
// Increased limits (use sparingly)
mcp__perplexity__perplexity_search({
query: "complex topic",
max_results: 5,
max_tokens_per_page: 1024
})
When to use:
Usage:
mcp__perplexity__perplexity_ask({
messages: [
{
role: "user",
content: "Explain how postgres advisory locks work"
}
]
})
NOT for:
NEVER use: mcp__perplexity__perplexity_research
Use instead: Researcher agent (/research <topic>)
Priority order:
gt CLI mention✅ CORRECT - Use Perplexity Search:
✅ CORRECT - Use Perplexity Ask:
❌ WRONG - Use Context7 instead:
❌ WRONG - Use Graphite MCP instead:
❌ WRONG - Use Nx MCP instead:
3plugins reuse this skill
First indexed Jul 11, 2026
npx claudepluginhub vincent067/agent-toolkit --plugin perplexityUses Perplexity API for web-grounded AI search with source citations. Supports quick fact lookup, complex multi-step reasoning, and deep research via selectable models.
Routes research tasks to optimal tools via decision tree: Context7 for library docs, Perplexity Ask/Search/Research for Q&A/events/deep analysis, Firecrawl for URL scraping/mapping/extraction.
Performs AI-powered web searches with real-time, source-cited answers using Perplexity models via LiteLLM and OpenRouter. Use for current information, recent scientific literature, or facts beyond model training cutoff.