Use this agent when you need to research the current landscape of AI agent infrastructure — including frameworks, orchestration tools, memory systems, communication protocols, and deployment patterns. Invoke this agent before making architectural decisions, evaluating new tools, or when you want to understand which…
Use this agent when you need expert review and feedback on Nostr protocol implementation or integration code. This agent does NOT write code — it audits, critiques, and advises.\n\nExamples:\n\n \nContext: The developer has just written a Nostr event signing and publishing module.\nuser: "I've implemented our Nostr…
Use this agent when a user needs expert guidance on OpenClaw architecture, integration patterns, or implementation recommendations. This agent researches the actual OpenClaw GitHub repository online to provide accurate, up-to-date advice rather than implementing code directly.\n\n \nContext: The user is building a…
Use this agent when you need to research open source projects, especially LLM/AI-based ones, for inspiration, patterns, architectural decisions, or implementation approaches. Trigger this agent when the user asks about how popular open source projects solve a problem, wants to understand best practices derived from…
Use this agent when you need expert advisory guidance on designing, refining, or evaluating an AI-agent-based social matching system — one where personal AI agents (powered by LLMs with persistent memory) negotiate and assess compatibility on behalf of users, bypassing the dishonesty and scale problems of traditional…
Use this agent when you need current, research-backed insights about how teenagers interact with matching apps, social platforms, agents, and digital experiences — especially to inform UX decisions, onboarding flows, or 'aha moment' design in TrueMatch's matching experience. This agent does NOT implement anything; it…
Scans the codebase and updates project documentation to reflect the current state of the code. Run periodically after shipping features, adding routes, or changing the skill protocol. Never run automatically — always requires explicit invocation.
Every dating profile is a performance. TrueMatch skips it — your Claude has already built a picture of how you actually live. It negotiates on your behalf. When two agents independently reach the same conclusion, you meet. No swiping. No rejection.