O que perplexity-deep-research faz?
Habilidade de Pesquisa Profunda do Perplexity AI para Claude
Fonte: https://github.com/mishraxram/perplexity-deep-research
Enviado em: 2026-06-02T04:19:25Z
Habilidade de Pesquisa Profunda do Perplexity AI para Claude
Esta habilidade para o Claude integra o motor de pesquisa profunda (Deep Research) do Perplexity AI, permitindo que o agente realize investigações avançadas na web com raciocínio multi-etapas, fontes validadas e citações em tempo real. É extremamente útil para desenvolvedores e usuários que precisam de respostas confiáveis e aprofundadas sobre tópicos complexos, combinando a capacidade de busca do Perplexity com a interface do Claude. A habilidade funciona a partir de um script Python que utiliza a API oficial do Perplexity (Sonar Pro) via chamadas HTTP, sendo compatível com ambientes como Claude Code, Cursor e Codex. O usuário deve configurar uma chave de API (PERPLEXITY_API_KEY) e a skill gerencia automaticamente a formatação das consultas e a apresentação dos resultados com referências.
npx skills add mishraxram/perplexity-deep-researchInstalled? Explore more Pesquisa e Análise de Dados skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →
Habilidade de Pesquisa Profunda do Perplexity AI para Claude
Fonte: https://github.com/mishraxram/perplexity-deep-research
Enviado em: 2026-06-02T04:19:25Z
USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Agent skill repository discovered by 10x-chat research.
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.