Agent Skills Hub

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

dev

Development and maintenance of the PWAFire library: build PWA API modules, handle feature detection, manage testing, and contribute to codebase following strict sync/async patterns and error handling requirements.

speak

Local text-to-speech conversion using Kokoro TTS. Generate audio, read text aloud, and handle multilingual speech synthesis directly in your terminal.

error-handling

Implement robust backend error handling with custom classes, middleware, structured logging, and recovery patterns.

Investigating Code Patterns

Systematically trace code flows, locate implementations, diagnose performance issues, and map system architecture to understand complex codebases.

java

Java development skill for writing clean, maintainable code using SOLID principles, pragmatic abstraction, and self-documenting practices.

lgtm

Launch lgtm TUI to review markdown files, code plans, or documentation with line-by-line commenting, syntax highlighting, and collaborative feedback workflows.

agents

Build AI agents with tool calling and multi-step reasoning. Generate, manage, and orchestrate custom skill files for Claude Code, Cursor, Cline, and other AI assistants to standardize your development workflows.

dependency-analysis

Analyze Kubernetes controller code to generate contract-compliant dependency graph artifacts for the Kamera coverage strategy.

language-learning

AI language tutor for personalized learning through conversation, grammar lessons, vocabulary drills, and flashcards. Supports 100+ languages including Spanish, French, Japanese, and Mandarin.

claude-code

Standardized skill for Claude Code agents to dynamically query OpenRouter model recommendations and metadata via the Claudish CLI.

kreuzberg

High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.