Agent Skills Hub

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.

paper-plan

Generate a structured academic paper outline from research narrative, experiment data, and review conclusions.

Ralph-Loop-Ultra

Seamlessly toggle between live and mocked external dependencies using the Model Context Protocol (MCP) for autonomous development environments.

plantuml-manipulator

Structured batch manipulation, validation, and reporting for PlantUML sequence diagrams across multiple files.

github-wayback-recovery

Recover deleted GitHub repository content, issues, PRs, and files using Wayback Machine CDX API queries and web archive snapshots.

symbols

Token-efficient codebase navigation through intelligent symbol indexing, domain chunking, and architectural layer filtering. Reduce token usage by 60-95% when exploring or developing complex systems.

dumbwaiter-mcp

Provider-agnostic MCP skill for wait-for-change automation on PR events like status checks, merges, and comments.

meta-tags-optimizer

Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum CTR with A/B testing variations.

Security Code Review

Analyze source code for security vulnerabilities based on OWASP Top 10 guidelines and suggest remediation strategies.

Global Documentation

Ensures adherence to standardized global documentation patterns for technical projects, maintaining consistency across repositories and agent-based workflows.

tooling-setup

Production-ready scaffolding for React 19 projects using Vite, TypeScript, Biome, and Vitest. Provides strict configuration, linting, formatting, and testing infrastructure.