Agent Skills Hub

personal-brand-agent

Autonomous multi-agent LinkedIn system using LangGraph and Claude Opus 4.5 for trend research, content creation, voice profiling, and analytics-driven optimization.

basic-usage

Essential guide to llmemory for document storage and search: installation, database setup with pgvector, document ingestion, hybrid/semantic retrieval, and building RAG systems with multi-tenant support.

godot-gdscript-patterns

Master Godot 4 GDScript patterns, including signal-based communication, state machines, scene architecture, and performance optimization for professional game development.

coding-tutor

Your personal AI coding tutor that creates customized tutorials based on your actual codebase, tracks your learning progress, and uses spaced repetition to ensure mastery.

code-auditing

A systematic code auditing framework for identifying technical debt, security vulnerabilities, dead code, and code quality issues in software projects.

configuring-connection-pools

Optimizes Prisma Client connection pool settings for production databases, serverless environments, and high-concurrency architectures to prevent connection exhaustion and performance bottlenecks.

flutter-performance-docs

A comprehensive optimization guide and best practices documentation for Flutter performance, covering build costs, rendering, list optimization, animations, and anti-patterns.

ruzzy

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

perf-analyzer

Synthesize performance profiling data into actionable recommendations and evidence-backed technical decisions.

kagent

Expert guide for kagent: the Kubernetes-native framework for building, deploying, and managing AI agents, MCP tools, and A2A protocols.

playwright-cli

Token-efficient CLI for browser automation, web testing, and agentic workflows using Playwright.

respond

Manually finalize and submit AI agent responses to Claude. Use when automatic synchronization fails or to manually curate findings.