Toolverse
All skills
Security

perplexity-architecture-variants

by jeremylongshore

Choose and implement Perplexity validated architecture blueprints for different scales.\nUse when designing new Perplexity integrations, choosing between monolith/service/microservice\narchitectures, or planning migration paths for Perplexity applications.\nTrigger with phrases

Installation

Pick a client and clone the repository into its skills directory.

Installation

Quick info

Author
jeremylongshore
Category
Security
GitHub repo

About this skill

Choose and implement Perplexity validated architecture blueprints for different scales.\nUse when designing new Perplexity integrations, choosing between monolith/service/microservice\narchitectures, or planning migration paths for Perplexity applications.\nTrigger with phrases like \

How to use

  1. Zainstaluj umiejętność w swoim środowisku Claude Code, Codex lub OpenClaw, upewniając się, że masz dostęp do narzędzi Read i Grep.

  2. Wyzwól umiejętność frazami takimi jak "architektura perplexity", "blueprint perplexity", "jak strukturyzować perplexity" lub "layout projektu perplexity" — system automatycznie rozpozna Twoje zapytanie.

  3. Przejrzyj macierz decyzyjną, aby wybrać wariant odpowiadający Twojemu wolumenowi zapytań: dla mniej niż 500 zapytań dziennie wybierz Direct Search Widget, dla 500–5K zapytań wybierz Cached Layer, a dla powyżej 5K zapytań wybierz Research Pipeline.

  4. Dla wybranego wariantu umiejętność dostarczy kod startowy — na przykład dla Direct Widget otrzymasz gotowy endpoint Express/Next.js integrujący Perplexity Sonar API z obsługą cytowań.

  5. Dostosuj kod do Twojej aplikacji, ustawiając zmienną środowiskową PERPLEXITY_API_KEY i dostosowując parametry żądania (model, max_tokens) do Twoich potrzeb.

  6. Wdróż wybrany wariant i monitoruj koszty oraz opóźnienia — umiejętność zawiera szacunki kosztów miesięcznych dla każdej architektury, aby pomóc Ci zaplanować skalowanie.

Related skills

academic-researcher

by Shubhamsaboo

Academic research assistant for literature reviews, paper analysis, and scholarly writing.\nUse when: reviewing academic papers, conducting literature reviews, writing research summaries,\nanalyzing methodologies, formatting citations, or when user mentions academic research,

Security
1260

brand-voice

by anthropics

Apply and enforce brand voice, style guide, and messaging pillars across content. Use when reviewing content for brand consistency, documenting a brand voice, adapting tone for different audiences, or checking terminology and style guide compliance.

Security
48158

python-expert

by Shubhamsaboo

Senior Python developer expertise for writing clean, efficient, and well-documented code.\nUse when: writing Python code, optimizing Python scripts, reviewing Python code for best practices,\ndebugging Python issues, implementing type hints, or when user mentions Python, PEP 8,

Security
2777

obsidian

by gapmiss

Comprehensive guidelines for Obsidian.md plugin development including all 27 ESLint rules, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, and submission requirements. Use when working with Obsidian plugins, main.ts files,

Security
14111

qmd

by tobi

Search personal markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in

Security
1951

architect-review

by sickn33

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural

Security
2773