Agent Skills Hub

deep-reading-analyst

A comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models like SCQA, First Principles, and Systems Thinking.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

rag-engineer

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

text-to-sql

Convert natural language queries to safe, optimized SQL. Automates database interactions with schema awareness and parameterized query generation.

web-research

Query the Pollinations text API with web-search enabled models like Gemini and Perplexity for grounded, real-time research.

prompt-writing

Create, refine, and optimize high-quality YAML prompts for AI assistants using structure guidelines, template patterns, and quality standards.

notebooklm

Query Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Features persistent authentication, library management, and automated browser-based document retrieval.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

memory-systems

Guides agent memory system implementation, compares frameworks (Mem0, Zep, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention.

paperbanana

Generate publication-quality statistical plots from CSV or JSON data files using AI-driven automated visualization.

context-engineering-collection

A structured repository of Agent Skills for context engineering, multi-agent architectures, and production-grade agent system optimization.

sequential-thinking

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