Agent Skills Hub

advanced-evaluation

Implement production-grade LLM-as-a-judge pipelines for model evaluation, including pairwise comparison, direct scoring, bias mitigation, and rubric generation.

summarize-interview

Synthesize interview transcripts into a structured template including Jobs to Be Done (JTBD), satisfaction signals, and actionable items.

ruzzy

Coverage-guided fuzzer for Ruby code and C extensions, powered by libFuzzer and address sanitizers to detect memory corruption and undefined behavior.

protocol-reverse-engineering

Perform network protocol reverse engineering, including packet capture, traffic analysis, protocol dissection, and custom format documentation.

solana-vulnerability-scanner

Scans Solana programs (native/Anchor) for 6 critical vulnerabilities, including arbitrary CPI, improper PDA validation, and missing ownership checks, providing detailed fix recommendations.

mystery-novel-conventions

A framework for crafting suspense, detective, and mystery narratives, emphasizing fair play principles, clue placement, and plot structure.

image-enhancer

Enhance image quality, resolution, and sharpness for screenshots and digital media. Perfect for professional documentation, blogs, and presentations.

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.

docstring

Generate and update PyTorch-compliant function and method docstrings using reStructuredText/Sphinx conventions.

react-typescript

Production-grade React 19 and TypeScript patterns featuring hooks, state management, TanStack Query, form validation with Zod, and performance optimization workflows.

skill-reinforcement

An automated meta-learning skill that improves agent workflows by capturing patterns, failures, and shortcuts after each task execution.

AgentDB Learning Plugins

Create and train custom reinforcement learning plugins for autonomous agents using 9 core algorithms including Decision Transformer and Actor-Critic for self-optimizing behavior.