아키텍처 토론을 클릭해서 돌아다닐 수 있는 것으로 바꾸는 에이전트 스킬.

위 사진: 이 기술로 만든 실제 생산 에이전트 시스템 아틀라스 — 챕터마다 몇 개의 구조물을 보여주고, 마우스를 올리면 구조물을 읽고, 내부에 들어가면 실행 과정을 보여줍니다.

왜

아키텍처 논의는 어떤 문서보다 더 빠르게 의사결정, 질문, 어휘를 생성하며, 당신이 논의하는 사람은 시스템을 읽는 것이 아니라 보고 싶어 합니다. 그래서 당신은 다이어그램을 그렸고, 일주일 후 그 다이어그램은 거짓입니다. 아틀라스는 다이어그램 대신 문제의 형태를 고정합니다: 저장소 내 한 데이터 파일이 단일 소스이며, 항상 일치하는 두 뷰를 렌더링합니다 — 마우스로 탐색하는 상호 등각 투영 지도와 안정적인 ID로 의사결정 테이블, 모든 구조, 흐름, 모든 미해결 질문을 담은 **생성된 텍스트 쌍(SYSTEM.md)입니다. 지도는 사람 앞에 놓는 것이고; 텍스트는 저장소와 다음 세션에서 읽는 것입니다; 두 가지 모두 같은 파일에서 생성되기 때문에 설계 업데이트는 한 번의 수정과 재구성이며, 시스템이 틀릴 수 있는 부분은 정확히 한 곳입니다.

System Atlas

An agent skill that turns an architecture discussion into something you can click around.

Above: a real atlas of a production agent system, built with this skill — chapters reveal the system a few structures at a time, hovering reads a structure, and going inside one shows its steps in execution.

npx skills add inkboard/system-atlas

Why

Architecture discussions produce decisions, questions, and vocabulary faster than any one document can hold, and the person you are discussing with wants to see the system, not read it. So you draw a diagram, and a week later the diagram is a lie. An atlas fixes the shape of that problem rather than the diagram: one data file in the repo is the single source, and it renders two views that always agree — an interactive isometric map you explore with a mouse, and a generated text twin (SYSTEM.md) that carries the decisions table, every structure, the flows, and every open question by stable ID. The map is what you put in front of a person; the text is what the repo and your next session read; because both are generated from the same file, updating the design is one edit and a rebuild, and there is exactly one place where the system can be wrong.

What you get

• An interactive isometric map — hover a structure to read it, click to pin it, arrow-right to go inside and see its steps in execution, pan and zoom the whole thing. One self-contained HTML file, no build step, no runtime dependencies.
• Progressive-disclosure chapters — a whole system at once reads as noise. Each chapter reveals at most three new structures and runs one small data flow that only touches what you have already seen; the last chapter shows everything with a flow picker.
• Moving data packets you can inspect — the dots travelling the hops are real requests. Click one and the panel shows its route and a representative JSON payload, so “how does a turn actually work” has a visual answer.
• A generated text twin — SYSTEM.md, rebuilt from the same data: the decisions table with ADR links, every structure’s what/how/steps, the flow tables, and the question index.
• Question tracking by ID — every open question gets a stable Q- and a state: open, resolved (with the answer and the date), or routed to a named next step. You can run several rounds of feedback against it without losing track of what was asked or who answered it.
• Role shapes and readable labels — the brain, the stores, the tool decks, the gates and the scheduled jobs each get their own isometric form and a name tag on the canvas, so the map is legible without a key.