Skill UI

Expert guidance for building production-grade stateful, multi-actor AI agents with LangGraph, covering graph construction, state management, cycles and branching, checkpoint persistence, human-in-the-loop patterns, and the ReAct agent workflow.

LEX is a structured truth engine designed to eliminate legal hallucinations by grounding AI agents in verified government references and legislation across 29+ jurisdictions (including US, EU, and CA). It provides deterministic context for comparing legal requirements, drafting compliant business, and employment documents, ensuring high jurisdictional accuracy.

Architecture and integration sketches for LLM applications, covering RAG retrieval, tool dispatch, agent loops, caching, privacy boundaries and verification requirements before production use.

Expert guidance for building production-grade AI agents with LangChain 0.1+ and LangGraph, covering architecture, memory, RAG, tools, deployment, and evaluation.

Conduct authorized security assessments for LLM applications and AI agents. Covers prompt injection, tool abuse, RAG exposure, memory poisoning, and system prompt extraction following OWASP LLM/ASI Top 10 guidelines. Includes red-teaming, vulnerability mapping, and compliance engineering for AI systems to ensure safety and robustness.

Loki Mode is a multi-agent autonomous startup system designed to execute workflows from PRD to production without human intervention. It integrates research-enhanced AI models including OpenAI SDK, DeepMind, Anthropic, and AWS Bedrock. This skill ensures zero human involvement in the deployment process while maintaining strict constraints on dependencies and response times.

Discover, find, compare, audit, repair, adapt, craft, run, debrief, and prepare repeatable AI-agent loops for publication. A comprehensive tool for managing bounded feedback loops in AI agent workflows.

Framework-agnostic long-term project memory for AI agents. Persists architecture decisions, conventions, and context as plain Markdown files in .lore/, enabling any agent to record, recall, audit, sync, and query project knowledge.

This skill applies behavioral economics principles, specifically prospect theory and framing effects, to craft messages that emphasize the risks of inaction. It helps identify scenarios where loss framing outperforms gain framing to create urgency without fear-mongering. The agent calibrates intensity based on audience risk tolerance and trust levels, ensuring consequences are concrete and credible. It is designed for copywriting, UX, pricing, and marketing communications where ethical persuasion is required to influence behavior effectively.

Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Python Agents SDK with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL-based authentication.

Build enterprise agents for Microsoft 365, Teams, and Copilot Studio with the Microsoft 365 Agents SDK in TypeScript/Node.js. Covers Express hosting, AgentApplication routing, streaming responses with Azure OpenAI, invoke activities, and Copilot Studio client and WebChat integration.

Design and implement complete machine learning pipelines using multi-agent orchestration following modern MLOps best practices. Covers data engineering, feature stores, model training, and production deployment. Ideal for building scalable, monitored, and reproducible ML systems in production environments.