Guide for understanding and working with the Oqto platform - a self-hosted AI agent workspace. Use when explaining Oqto architecture, API usage, session management, CLI tools (oqto, oqtoctl, agntz, byt), configuration, or when helping users interact with the platform's features including chat, file browser, terminal, voice mode, and memory system.
Design and implement delightful, scriptable command-line tools: subcommands, composable stdin/stdout/stderr, stable --json/--yaml, great help/errors, safe destructive ops, config precedence (flags>env>config), TTY-aware color/progress, completions, and tests.
This skill should be used to create high quality pdf documents based on predefined templates. When the user asks for a document, you can list all available templates and brands and ask the user for the content to put into the template. You only edit the toml templates, not the .typ files. The toml/typ pair compile into a professional looking pdf via tmpltr.
Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.
This skill conducts discovery conversations to understand user intent and agree on approach before taking action. It should be used when the user explicitly calls /interview, asks for recommendations, needs brainstorming, wants to clarify, or when the request could be misunderstood. Prevents building the wrong thing by uncovering WHY behind WHAT.
Create valid code for generating mermaid diagrams
Toolkit for spreadsheet work—building files with formulas and formatting, analyzing data, modifying existing workbooks while preserving formulas, creating visualizations, and recalculating. Use for .xlsx, .xlsm, .csv, .tsv files and similar formats.
Controls browser instances for web testing, form filling, screenshots, and data extraction. Use when the user asks to browse a website, navigate web pages, fill forms, take screenshots, or test web applications. The agent can start its own browser session or control one started by the user.