Maksim-Burtsev

High-compression professional communication mode. Use when the user wants fewer tokens, less reading, no filler, compact coding-agent status, terse technical answers, or low-cognitive-load collaboration without reducing effort, validation, proactivity, or…

Architecture-level design review of a code change: module boundaries, dependency direction, data model, error paths, cost of the next change — never naming, formatting, or anything a linter catches. Use when the user invokes /punchcard, says 'punchcard…

Visual-first, note-ready teaching across any domain. Use for ANY non-trivial request to explain, teach, or unpack how or why something works — a mechanism, system, pipeline, data flow, process, game strategy, or concept — even when the user does not mention…

Measure how efficiently the user supervises their parallel AI coding agents, from local Claude Code session logs. Use when they ask how they are doing with agents, about agent productivity or idle time, how many agents to run in parallel, why parallel…

Visual-first, note-ready teaching for non-trivial explanation or learning requests across any domain. Use when the user asks to explain, teach, compare, justify a decision, show how/why something works, create a конспект, схема, diagram, mental model, flow,…