Toolverse
All skills

llm-patterns

by alinaqi

AI-first application patterns, LLM testing, prompt management

Installation

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

Installation

Quick info

Author
alinaqi
Category
Data Science

About this skill

AI-first application patterns, LLM testing, prompt management

How to use

  1. Załaduj skill razem z plikami base.md i wybranym plikiem [language].md do swojego projektu Claude/Copilot. 2. Przejrzyj strukturę katalogów w src/core — prompts zawiera szablony dla klasyfikacji i ekstrakcji, llm zawiera klienta i schematy odpowiedzi, services zawiera logikę biznesową. 3. Utwórz typowany wrapper klienta LLM w core/llm/client.ts, definiując interfejs LLMCallOptions z polem prompt, schema (Zod), model i maxTokens. 4. Napisz szablony promptów w core/prompts dla swoich przypadków użycia (klasyfikacja, ekstrakcja, streszczanie), a następnie zdefiniuj schematy odpowiedzi w core/llm/schemas.ts. 5. Implementuj logikę biznesową w services, wywołując typowany klient LLM z promptem i schematem — model zwróci dane zgodne z Twoim typem TypeScript. 6. Dodaj testy LLM w tests/llm — użyj fixtures do zapisania rzeczywistych odpowiedzi modelu, evals do oceny jakości, mocks do testów jednostkowych bez kosztów API.

Related skills

market-research-reports

by davila7

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for

Data Science
16115

pdf

by anthropics

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Data Science
31144

pdf-processing

by Ming-Kai-LC

Comprehensive PDF processing techniques for handling large files that exceed Claude Code's reading limits, including chunking strategies, text/table extraction, and OCR for scanned documents. Use when working with PDFs larger than 10-15MB or more than 30-50 pages.

Data Science
23134

notebooklm

by leegonzales

Query Google NotebookLM for source-grounded, citation-backed answers from uploaded documents. Reduces hallucinations through Gemini's document-only responses. Browser automation with library management and persistent authentication.

Data Science
142112

stock-analyzer

by FrancyJGLisboa

Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.

Data Science
23128

prompt-optimizer

by solatis

Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.

Data Science
15109