Agent Skills Hub

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.

langchain-architecture

Architect production-grade LLM applications using LangChain 1.x and LangGraph. Implement stateful AI agents, multi-step workflows, and custom memory systems for complex conversational and automation tasks.

scan-inbox

Intelligent Apple Mail inbox scanner that categorizes unread, actionable, and priority emails using automated keyword analysis.

memcontext-autopilot

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

fabric

Intelligent pattern selection for Fabric CLI, automatically choosing from 242+ specialized prompts for threat modeling, data analysis, summarization, and content creation.

synapse

Autonomous pattern detection and skill recommendation engine that monitors project memory, logs, and task lists to evolve your AI agent's capabilities automatically.

web-search-patterns

Advanced Gemini-powered web search plugin with smart caching, subagent context isolation, and automated query optimization.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.

ai-multimodal

Process and generate multimedia with Google Gemini. Analyze audio, images, videos, and PDFs with high-context windows. Supports transcription, visual QA, OCR, and AI-driven image creation.

drift

Frameworks and tools for AI agents exploring consciousness, identity, and persistent autonomy. Includes session handoff, memory infrastructure, and self-reflection protocols.

prompt-optimizer

Transforms vague or poorly structured prompts into optimized, high-performance instructions using proven prompt engineering principles for better AI model execution.

respond

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