Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Navigate the Dynamo codebase and produce architecture briefings. Use this skill when learning Dynamo for the first time, when you get a Jira ticket and don't know where to start, when you need to understand how Dynamo's architecture fits together, or when onboarding a teammate. Also use for questions like "where does node evaluation happen?" or "how does the DesignScript engine work?"
Explore and understand the OxyGent framework structure, components, and implementation patterns.
Query msgvault email archive analytics via SQL views. Use when: querying email history, analyzing senders/domains/labels, thread analysis, attachment stats, messages per month, sender graphs, domain breakdowns, email analytics. Triggers on: msgvault, email archive, email search, email analytics, sender analysis, domain analysis.
Choose optimal external AI models for code analysis, bug investigation, and architectural decisions. Use when consulting multiple LLMs via claudish, comparing model perspectives, or investigating complex Go/LSP/transpiler issues. Provides empirically validated model rankings (91/100 for MiniMax M2, 83/100 for Grok Code Fast) and proven consultation strategies based on real-world testing.
Use this when the user wants to deeply understand something through guided questioning. Trigger phrases include: "quiz me", "help me understand", "Socratic", "teach me", "walk me through with questions", "test my understanding", or when the user asks for an explanation and would benefit more from guided discovery than a direct answer.
RLM-style large-codebase comprehension — build a mental map of any codebase by dispatching sub-agents to explore regions without bloating main context
Read X (Twitter) via xurl — search posts, fetch threads, read profiles, and read long-form articles
Web extraction engine for LLMs and agents. Scrape, crawl, extract, summarize, search, map, diff, monitor, research, and analyze any URL into clean Markdown, text, or JSON, including pages that block bots or render with JavaScript. Use when you need reliable web content, the built-in web_fetch fails, or you need structured data extraction from web pages.
Search the public web for current information through the configured Tavily or Brave provider.