ai-llm-patterns
Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
460 skills found
Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.
Automated video report generation for troubleshooting, using Remotion to render provided video URLs.
Automated text-to-image rendering engine for social media posts, article covers, and long-form threads. Supports X-style, WeChat, and poster templates with high-precision text formatting and highlights.
Analyze periodic signals in unevenly sampled astronomical time series data using the Lomb-Scargle periodogram method with the lightkurve library.
Automated generation of project documentation from codebase analysis, ensuring accuracy, consistency, and alignment with VilnaCRM architecture patterns.
Initiates automated reverse engineering by discovering codebase architecture, layers, and technology stacks to facilitate system modernization or documentation.
Professional-grade spreadsheet automation for Claude: create, edit, analyze, and visualize Excel and CSV files with rigorous formula integrity and financial formatting standards.
Identify, categorize, and troubleshoot flaky tests by analyzing CI history, execution patterns, and code structure to improve test suite reliability.
User research and insight synthesis for product teams. Plan studies, analyze interviews and usability tests, and generate evidence-based, prioritized design recommendations.
Automates the triage, prioritization, and feedback process for new MultiQC module requests by analyzing repository activity, community engagement, and technical feasibility.
Explains complex concepts using master teaching frameworks like Feynman, Socratic, and Cognitive Load theory to ensure deep, clear understanding.
Reliably read and extract content from publicly shared Google Docs using curl for full document retrieval.