skills.rest
Shubh2310-developer
Shubh2310-developerCOMMUNITY
Explore all skills by this author →
GitHub

perplexity

Routes generic web search and research queries to Perplexity Search or Ask with token-limited defaults.

2|Updated Jan 10, 2026
Search Tags:#research#web search#mcp#perplexity#token budget#ai search#tool routing
One-click install
npx skills add https://github.com/Shubh2310-developer/ENGUNITYCORE --skill perplexity-shubh2310-developer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: perplexity
Source: https://github.com/Shubh2310-developer/ENGUNITYCORE/tree/main/.claude/skills/perplexity
Command: npx skills add https://github.com/Shubh2310-developer/ENGUNITYCORE --skill perplexity-shubh2310-developer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents wasted tokens and wrong tool choices when handling web search requests by defining exactly when to use Perplexity Search, Perplexity Ask, or a different specialized tool like Context7, Graphite MCP, or Nx MCP. ## Core Features & Use Cases - Tool selection chain: Enforces a priority order (Context7, Graphite MCP, Nx MCP, then Perplexity) so library docs and workspace questions never hit the wrong API. - Token budget control: Mandates conservative defaults (max_results: 3, max_tokens_per_page: 512) to avoid context bloat from oversized search results. - Research cost guardrail: Prohibits the expensive perplexity_research tool (30-50k tokens) and delegates deep research to the /research agent instead. - Use Case: When a user says "find postgres migration best practices", the skill routes to Perplexity Search with limited results; when they ask about React hooks docs, it redirects to Context7 instead. ## Quick Start Ask the assistant to search for a current topic, such as "search for the latest microservices trends", and it will apply the correct Perplexity tool with conservative limits.

Frequently Asked Questions about perplexity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I use Perplexity Search without wasting tokens?▼

Call perplexity_search with max_results set to 3 and max_tokens_per_page set to 512 instead of the default 10 results. Only increase limits when the user explicitly needs comprehensive results or the initial search returned nothing useful.

When should I use Perplexity Ask instead of Perplexity Search?▼

Use Perplexity Ask when you need a conversational explanation synthesized from web sources, such as explaining how postgres advisory locks work. Use Perplexity Search when you need to find resources, URLs, tutorials, or current best practices.

Should I use Perplexity or Context7 for library documentation?▼

Use Context7 MCP for all library and framework documentation, such as React hooks or Next.js routing docs. Perplexity is only for generic searches and should never be used when a specialized documentation tool applies.

Why is the perplexity_research tool prohibited?▼

The perplexity_research tool costs 30-50k tokens per call, making it extremely expensive. Use the researcher agent via /research instead, which provides multi-source synthesis with citations for complex questions.

What is the correct tool selection order for web queries?▼

Follow this priority: Context7 MCP for library docs, Graphite MCP for gt CLI, Nx MCP for workspace questions, then Perplexity Search, Perplexity Ask, the researcher agent, and finally WebSearch as a last resort.

Related Skills

Explore More Software Engineering Skills→
zjunlpzjunlp
1.1k

webshop-query-interpreter

Convert natural language shopping queries into structured product search parameters.

Official
Intermediate
gagan114662gagan114662

web-search

Search the web, evaluate sources, and synthesize findings with cited URLs.

Community
Intermediate
pedronauckpedronauck
601

perplexity

Routes web search and research queries to Perplexity Search or Ask with token-budget limits.

Community
Intermediate
faisalanjumfaisalanjum
3

perplexity-research

Generate detailed multi-source research reports using Perplexity's sonar-deep-research model.

Community
Advanced