Agent Skills Hub

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.

rag-engineer

Architect and optimize production-grade RAG systems. Master embedding models, vector databases, chunking strategies, and retrieval pipelines for high-accuracy LLM applications.

obsidian-get

Read the full text content of a specific note from an Obsidian knowledge base or vault.

anthropic-api

Expert guidance for building production-ready applications with Anthropic's Claude API. Covers SDKs, prompt caching, batch processing, streaming, tool use, and cost optimization strategies.

citation-management

Comprehensive citation management: search academic databases, extract metadata from DOIs/PMIDs/arXiv, validate references, and generate perfectly formatted BibTeX for scientific manuscripts.

excel-export-validator

Validates Excel exports for Customer Feedback Analyzer with 7 specific view sheets, 36 columns, and precise color-coded formatting. Ensures zero errors in customer-facing deliverables.

discovery.problem_framing

Frame core customer problems, supporting evidence, and success hypotheses to ensure discovery work is grounded in data before solutioning begins.

article-analysis

Analyze and summarize web content like articles, newsletters, and blog posts into structured markdown reports. Perfect for content consumption, knowledge management, and research.

common

Infrastructure for cross-product HealthSim data persistence, entity correlation via SSN, and DuckDB database operations.

gdoc

Reliably read and extract content from publicly shared Google Docs using curl for full document retrieval.

transcribee

Transcribe YouTube videos and local audio/video files with high-precision speaker diarization. Supports major formats for ready-to-use LLM analysis.

sequential-thinking

Structured reasoning tool for complex problem decomposition, step-by-step analysis, consistency verification, and evidence-based synthesis with confidence scoring.