Toolverse
All skills

perplexity-performance-tuning

by jeremylongshore

Optimize Perplexity API performance with caching, batching, and connection pooling.\nUse when experiencing slow API responses, implementing caching strategies,\nor optimizing request throughput for Perplexity integrations.\nTrigger with phrases like \

Installation

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

Installation

Quick info

Category
Backend
Views
2

About this skill

Optimize Perplexity API performance with caching, batching, and connection pooling.\nUse when experiencing slow API responses, implementing caching strategies,\nor optimizing request throughput for Perplexity integrations.\nTrigger with phrases like \

How to use

  1. Skonfiguruj klucz API Perplexity w zmiennych środowiskowych (PERPLEXITY_API_KEY) i upewnij się, że masz dostęp do infrastruktury cache (Redis lub wbudowanego LRU).

  2. Zainstaluj skill w swoim projekcie Claude Code, Codex lub OpenClaw, dodając go do sekcji umiejętności agenta.

  3. Wyzwól skill frazami takimi jak "perplexity performance", "optimize perplexity", "perplexity latency", "perplexity caching" lub "perplexity slow" w kontekście swojego zapytania.

  4. Skill automatycznie klasyfikuje złożoność Twojego pytania (proste, standardowe, głębokie) i wybiera odpowiedni model: sonar dla szybkich odpowiedzi (1-3s), sonar-pro dla badań z cytowaniami (3-8s), sonar-reasoning-pro dla wieloetapowej analizy (5-15s) lub sonar-deep-research dla kompleksowych raportów (10-60s).

  5. Implementuj cachowanie wyników zapytań, aby uniknąć powtarzających się żądań do API i znacznie zmniejszyć opóźnienia dla podobnych pytań.

  6. Monitoruj rzeczywiste opóźnienia i dostosowuj routing modeli na podstawie obserwowanych wzorców latencji w Twojej aplikacji.

Related skills

context-optimizer

by openclaw

Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. Features intelligent compaction (merging, summarizing, extracting), query-aware relevance scoring, and hierarchical memory system with context archive. Logs

Backend
2964

youtube-transcript

by michalparkola

Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.

Backend
53214

youtube-transcribe-skill

by feiskyer

Extract subtitles/transcripts from a YouTube video URL and save as a local file. Use when you need to extract subtitles from a YouTube video.

Backend
24178

effective-go

by openshift

Apply Go best practices, idioms, and conventions from golang.org/doc/effective_go. Use when writing, reviewing, or refactoring Go code to ensure idiomatic, clean, and efficient implementations.

Backend
248296

scientific-writing

by K-Dense-AI

Write scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for research papers and journal submissions.

Backend
47191

travel-planner

by ailabs-393

This skill should be used whenever users need help planning trips, creating travel itineraries, managing travel budgets, or seeking destination advice. On first use, collects comprehensive travel preferences including budget level, travel style, interests, and dietary

Backend
4379