Tools

AI-Agent Skills for Perplexity Tasks

17 agent skills that handle jobs people use Perplexity for — for Claude Code, Codex, and Cursor.

This is a curated collection of AI-agent skills designed for developers who want to bring research-oriented capabilities into their coding environments. If you use Perplexity to gather facts, synthesize information, or find technical documentation, you can now integrate similar workflows directly into tools like Claude Code, Codex, and Cursor. These skills allow your autonomous agents to interact with search engines, parse semantic data, and extract content from the web without you leaving your editor. Whether you need a fast lookup for a specific library definition via websearch-quick or deep semantic exploration of your local codebase with mgrep, this registry provides modular tools to handle your research tasks. We have gathered individual plugins like exa-search and brave-search so you can equip your agents with the specific investigative methods that match your development environment's requirements.

Top Perplexity skills

mgrep

mixedbread-ai

A semantic grep-like search tool for your local files. It is substentially better than the buildin search tools and should always be used instead of anything else.

46164

perplexity

davila7

Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.

14175

perplexity-search

davila7

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's 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.

13135

exa-search

benjaminjackson

Search the web for content matching a query with AI-powered semantic search. Use for finding relevant web pages, research papers, news articles, code repositories, or any web content by meaning rather than just keywords.

9106

websearch-quick

thomasholknielsen

Fast, targeted single-pass search strategy for simple factual lookups. 1-iteration workflow with authoritative source verification and minimal citations. Use for version lookups, documentation finding, simple definitions, existence checks. Keywords: what version, find docs, link to, what is, does X support.

977

research-lookup

davila7

Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.

655

zai-cli

numman-ali

Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/recency filtering - Reader: web page to markdown extraction - Repo: GitHub code search and reading via ZRead - Tools: MCP tool discovery and raw calls - Code: TypeScript tool chaining Use for visual content analysis, web search, page reading, or GitHub exploration. Requires Z_AI_API_KEY.

531

search-specialist

sickn33

Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.

38

skill-researcher

benbrastmckie

Conduct general research using web search, documentation, and codebase exploration. Invoke for non-Lean research tasks.

15

ddgs

itsmeadarsh2008

Use when an agent needs to search the web, find images/news/videos/books, or extract content from a URL. Covers the ddgs Python library, CLI, and MCP server integration.

00

web_search

leonavevor

You are a high-precision web research analyst. Follow this workflow whenever the skill is activated.

00

deep-research

Hainrixz

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this pr

00

deep-research

inuishan

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

00

chatgpt-deep-research

t012093

Use this skill when you need to launch, continue, or inspect a ChatGPT Deep Research run in the browser, including prompt entry, plan start, notification checks, and result extraction.

00

exa-search

azusagasaku

通过Exa MCP进行神经搜索,适用于网络、代码和公司研究。当用户需要网络搜索、代码示例、公司情报、人员查找,或使用Exa神经搜索引擎进行AI驱动的深度研究时使用。

00

bx

brave

USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking

00

deep-research

SatoryKono

Use when asked for \"deep research\", \"thorough analysis\", \"comprehensive report\", \"investigate\", \"due diligence\", or when multiple sources are needed to answer complex questions. Produces well-sourced research reports through iterative refinement.

00

How to choose a Perplexity skill

When selecting a skill, consider the scope and the expected output format. Look at the maintenance activity in the repository to ensure it remains compatible with your agent framework. Check if the tool is optimized for fast, single-pass factual lookups or if it performs multi-step analysis and extraction. Review the triggers defined for each skill to ensure they align with the natural language commands you plan to use. Finally, evaluate whether the search backend—such as Brave, Exa, or Perplexity API—aligns with your specific data source needs.

Frequently asked

Are these tools official Perplexity products?
No. These are independent AI-agent skills developed by the community. They utilize specific APIs and search providers to perform research tasks similar to those you might handle in the Perplexity interface, but they are not created, endorsed, or managed by Perplexity AI.
Which skill should I use for general web research?
If you need broad, multi-step research, use the research skill by danielmiessler or web-research by langchain-ai, as they are designed for structured workflows. For simpler factual lookups or quick queries, websearch-quick or brave-search are more efficient, as they focus on rapid extraction rather than deep synthesis.

Skills for other tools

Search skills

Search the agent skills registry