Agent Skills Hub

token-surgeon

Audit and optimize your AI prompts with Token Surgeon. Detect 10 common waste patterns, calculate efficiency, and reduce token usage for better prompt performance.

dotnet-claude-code-skills

A suite of .NET engineering skills for Domain-Driven Design (DDD), EF Core persistence, BDD-style unit testing, and IDE-like semantic code understanding with Serena MCP.

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.

claude-review

Review Hyperlane documentation changes against project standards, ensuring compliance with architectural patterns and content guidelines.

stock-analyzer

Perform comprehensive technical analysis for stocks and ETFs using indicators like RSI, MACD, and Bollinger Bands to generate actionable trading signals and comparative reports.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

skill-customizer

Adapt existing skills to your unique workflow, or create new ones for repetitive, time-consuming tasks.

changelog

Automated runtime observability changelog for Claude Code development sessions, tracking file changes, test results, and git commits.

work-logs-knowledge-log

Outputs knowledge logs capturing project structure, implicit rules, and logic gaps during sessions.

doc-sync

Synchronizes and maintains CLAUDE.md and README.md documentation hierarchy across a repository to ensure consistent, just-in-time context for AI agents.

context-detection

Systematic project technology stack detection, framework-specific skill auto-loading, and multi-stack analysis for fullstack projects like React + Go.

swarm

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance for complex features, multi-step refactors, and long-running autonomous coding sessions.