Skip to content
Back to search

system-atlas

An agent skill that turns an architecture discussion into an explorable isometric atlas: one data file, an interactive map and a generated SYSTEM.md

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/inkboard--system-atlas/badge.svg)](/listings/inkboard--system-atlas)

HTML

<a href="/listings/inkboard--system-atlas"><img src="/api/listings/inkboard--system-atlas/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

The [`skills` CLI](https://github.com/vercel-labs/skills) installs into Claude Code, Cursor, Copilot, Codex, Gemini, Cline, Amp and others:

npx skills add inkboard/system-atlas

Or drop `skills/system-atlas/` into your agent's skills directory by hand — for Claude Code that is `~/.claude/skills/system-atlas/` (personal) or `.claude/skills/system-atlas/` (per project).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 92 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # System Atlas
  2. **An agent skill that turns an architecture discussion into something you can click around.**
  3. ![A walkthrough of a real system atlas](./demo.gif)
  4. *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.*
  5. [![skills.sh](https://skills.sh/b/inkboard/system-atlas)](https://skills.sh/inkboard/system-atlas)
  6. ```bash
  7. npx skills add inkboard/system-atlas
  8. ```
  9. ## Why
  10. 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.
  11. ## What you get
  12. - **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.
  13. - **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.
  14. - **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.
  15. - **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.
  16. - **Question tracking by ID** — every open question gets a stable `Q-<code><n>` 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.
  17. - **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.
  18. - **The process, not just the renderer** — the skill carries the design language and the session lessons that produced it, so the agent knows the order to work in and the corrections to skip.
  19. ## Using it
  20. Ask for one in plain language. The skill triggers on things like:
  21. > "make me an atlas of this pipeline"
  22. > "map the system so we can talk about it"
  23. > "I want a diagram I can click around and poke holes in"
  24. > "walk me through how this fits together"
  25. > "update the atlas — we dropped the nightly job and picked a different vendor"
  26. Then the agent works in this order:
  27. 1. **Read the inputs before drawing** — the vision doc, the repo's real surfaces, the framework's docs. Boxes that don't map to something real are worse than no boxes.
  28. 2. **Discuss before drawing** — propose the structure in chat, mapped to the runtime's actual primitives, and ask only the questions it cannot derive from the repo.
  29. 3. **Build the first atlas**, then **cut it into chapters** — the first version is always "hard to parse"; progressive disclosure is the fix, and it is the default here.
  30. 4. **Generate the text twin** and keep the glossary (`CONTEXT.md`) and ADRs beside it.
  31. 5. **Run feedback rounds by question ID** — record the person's actual words, resolve with a date, and sweep every file after a rejection. A banner on a stale section is not enough.
  32. 6. **Rebuild and republish after every change.** An atlas that is out of date is worse than no atlas.
  33. ## How it works
  34. ```
  35. <atlas home>/data.mjs ← the only file you edit
  36. <atlas home>/build.mjs ← bun build.mjs
  37. <atlas home>/template.html ← the renderer
  38. ↓
  39. atlas.html + SYSTEM.md ← both generated, never hand-edited
  40. ```
  41. `data.mjs` holds the structures (position, footprint, role shape, prose, steps, questions), the flows as hop lists with payloads, the chapters with what each reveals, and the decisions. `build.mjs` writes both views from it. `assets/data.example.mjs` is a working starter with every field documented — copy it, fill it in, run the build, and you have an atlas.
  42. Where the atlas lives depends on your repo's docs policy. Repos that commit design docs can keep it at `docs/<system>/atlas/`; repos that deliberately commit only ADRs and a glossary should keep it in a git-ignored scratch directory and attach the generated `SYSTEM.md` to the spec issue instead. The skill asks before committing anything.
    • Dismissed after review: Contains a <system> block, a common wrapper for instructions hidden in a tool description
    • Line 60 on GitHub
  43. The map is a single self-contained HTML file, so publishing it is whatever the person can open: a hosted HTML artifact if your agent can publish one, a static server (`npx serve`, `python3 -m http.server`), or your repo's pages host. The rule is one URL, republished in place.
  44. ## What's in the repo
  45. | Path | What it is |
  46. |---|---|
  47. | `skills/system-atlas/SKILL.md` | The skill: when to use it, the process, what done looks like |
  48. | `skills/system-atlas/assets/template.html` | The atlas renderer |
  49. | `skills/system-atlas/assets/build.mjs` | `data.mjs` → `atlas.html` + `SYSTEM.md` |
  50. | `skills/system-atlas/assets/data.example.mjs` | Documented starter data — copy to `data.mjs` |
  51. | `skills/system-atlas/references/design-language.md` | Layout, palette, isometric grammar, role shapes, copy rules, the chapter recipe |
  52. | `skills/system-atlas/references/process-and-lessons.md` | How the first session went, the subagent deep-dive pattern, and the things that bit |
  53. | `skills/system-atlas/evals/evals.json` | Three eval prompts: a new atlas, an update, and a small greenfield one |
  54. ## Installing
  55. The [`skills` CLI](https://github.com/vercel-labs/skills) installs into Claude Code, Cursor, Copilot, Codex, Gemini, Cline, Amp and others:
  56. ```bash
  57. npx skills add inkboard/system-atlas
  58. ```
  59. Or drop `skills/system-atlas/` into your agent's skills directory by hand — for Claude Code that is `~/.claude/skills/system-atlas/` (personal) or `.claude/skills/system-atlas/` (per project).
  60. ## Credits
  61. The visual grammar takes after the "codebase as interactive isometric diagram" style — khaki paper, black hatched structures, an index on the left, a reading panel on the right, and data packets you can catch. The process rules are the corrections from a real design session, kept in the order they were earned.
  62. ## License
  63. MIT — see [LICENSE](./LICENSE).
skills/system-atlas/assets/data.example.mjs · Bundled script · 87 lines · 1 finding marked
  1. // Single source of truth for one atlas. Copy to <atlas home>/data.mjs and edit.
  2. // Build: bun <atlas home>/build.mjs → writes ../SYSTEM.md and ../atlas.html
  3. // The atlas home is docs/<system>/atlas/ in repos that commit design docs, or a
    • Note: Usual in code (tag names in paths and patterns): Contains a <system> block, a common wrapper for instructions hidden in a tool description
    • Line 3 on GitHub
  4. // git-ignored scratch directory in repos that only commit ADRs + CONTEXT.md.
  5. export const META = {
  6. title: 'Example Agent', // "<title> Atlas" in the tab; "<title> — System Definition" in SYSTEM.md
  7. artifactUrl: '', // fill after first publish; keep it stable across rebuilds
  8. sourcePath: 'docs/example/atlas/data.mjs',
  9. buildCmd: 'bun docs/example/atlas/build.mjs',
  10. stats: [{ k: 'System', v: 'example · v0' }, { k: 'Model roles', v: '2' }], // static top-strip stats; chapter/shown/questions are added automatically
  11. intro: `_**This file is the living source of truth for the design.** The interactive atlas is built from the same data._`,
  12. onePara: `One paragraph a newcomer can read in 30 seconds: what the system is, what the loop is, what is not built yet.`,
  13. costModel: ['Optional: cost assumptions and a table. Leave [] to omit.'],
  14. deepDive: '', // optional: summary + links to research/
  15. platformGives: 'What the runtime/framework provides for free.',
  16. weOwn: 'What we have to build ourselves.',
  17. filesystem: `apps/example/\n agent/…`,
  18. };
  19. // Decisions render as the SYSTEM.md table and as chapter-10's "Decisions locked" list.
  20. export const DECISIONS = [
  21. { axis: 'Runtime', decision: 'What and why, in one line', adr: '[0001](./adr/0001-slug.md)' },
  22. ];
  23. export const GROUPS = [
  24. { id: 'loop', title: 'The main loop' },
  25. { id: 'mem', title: 'Memory' },
  26. { id: 'sup', title: 'Supporting the loop' },
  27. { id: 'off', title: 'Not yet switched on' },
  28. ];
  29. // Structure = one isometric box. Fields:
  30. // id/code: 1–2 letters shown on the box · name · short (≤14 chars, canvas label) · group
  31. // gx,gy: grid position · w,d: footprint · h: height px · kind: box|tall|store|cards|slab|screen|gate|job
  32. // ghost: true → dashed "designed for, not built"
  33. // one: one-sentence summary (shown first) · what: plain description · how: implementation (may use <code>, <mark>)
  34. // steps: [[name, desc], …] → the "go inside" view
  35. // cond: questions — string (open) | {q, r} (resolved, r = answer + date) | {q, to} (routed to a named next step)
  36. export const NODES = [
  37. { id: 'U', code: 'U', name: 'Web chat', short: 'WEB CHAT', group: 'loop', gx: 1.5, gy: 7.5, w: 2, d: 2, h: 44, kind: 'screen',
  38. one: 'The page where you talk to the agent.',
  39. what: 'Plain-language description for a non-engineer.',
  40. how: 'Implementation with <code>identifiers</code> and <mark>key phrases</mark>.',
  41. steps: [['Open', 'Create or continue a session.'], ['Stream', 'Render deltas.']],
  42. cond: ['Where does the page live?', { q: 'Auth scheme?', r: 'Reuse existing session JWT (2026-01-01).' }] },
  43. { id: 'I', code: 'I', name: 'Root agent', short: 'AGENT', group: 'loop', gx: 10, gy: 2.5, w: 3, d: 3, h: 64, kind: 'tall',
  44. one: 'The brain — one durable conversation per person.', what: '…', how: '…', steps: [['turn.started', '…'], ['Model call', '…'], ['Tools', '…'], ['Stream', '…']], cond: [] },
  45. { id: 'M', code: 'M', name: 'Memory', short: 'MEMORY', group: 'mem', gx: 6.5, gy: 9.5, w: 3, d: 3, h: 24, kind: 'store',
  46. one: 'What the agent knows about you.', what: '…', how: '…', steps: [['Write', '…'], ['Read', '…']], cond: [{ q: 'Vendor?', to: 'Memory deep dive' }] },
  47. { id: 'P', code: 'P', name: 'Proactive', short: 'PROACTIVE', group: 'off', ghost: true, gx: 12.5, gy: -1, w: 2, d: 2, h: 34,
  48. one: 'Later: the agent reaches out on a schedule.', what: '…', how: '…', steps: [['Tick', '…']], cond: ['Notification etiquette.'] },
  49. ];
  50. // Flows for the final "whole system" chapter. Hop = [from, to, label, payload, bend('xy'|'yx')]
  51. export const FLOWS = [
  52. { id: 'turn', name: 'One turn', hops: [
  53. ['U', 'I', 'user message', { message: 'can you move my 3pm?' }, 'yx'],
  54. ['I', 'M', 'recall', { query: 'move my 3pm', k: 12 }, 'xy'],
  55. ['M', 'I', 'memories', { hits: 2 }, 'xy'],
  56. ['I', 'U', 'message.appended', { delta: 'Sure —' }, 'yx'],
  57. ] },
  58. ];
  59. // Chapters = progressive disclosure. Each reveals a few structures and runs ONE small flow among revealed ones.
  60. // The last chapter has reveal: [] and flow: null → shows everything with a flow picker.
  61. export const CH = [
  62. { id: 'you', title: 'You and the agent', reveal: ['U', 'I'],
  63. lede: `Strip everything away and this is the system: you type, it answers.`,
  64. story: `<p>Two or three sentences. <mark>Highlight</mark> the one idea this chapter adds.</p>`,
  65. flow: [['U', 'I', 'user message', { message: '…' }], ['I', 'U', 'reply', { delta: '…' }]] },
  66. { id: 'know', title: 'Knowing you', reveal: ['M'],
  67. lede: `Before answering, the agent recalls what it knows about you.`,
  68. story: `<p>…</p>`,
  69. flow: [['U', 'I', 'user message', { message: '…' }], ['I', 'M', 'recall', { k: 12 }], ['M', 'I', 'memories', { hits: 2 }], ['I', 'U', 'reply', { delta: '…' }]] },
  70. { id: 'later', title: 'Later', reveal: ['P'],
  71. lede: `Designed for, not switched on.`, story: `<p>…</p>`,
  72. flow: [['P', 'I', 'scheduled turn', { kind: 'morning_brief' }]] },
  73. { id: 'all', title: 'The whole system', reveal: [],
  74. lede: `Everything at once, for free exploration.`,
  75. story: `<p>Choose which flow runs (bottom left). Hover anything; click to pin; → goes inside. The <mark>Open questions</mark> tab lists every question by ID.</p>`,
  76. flow: null },
  77. ];
  78. // "How it's built" tab with nothing selected (HTML).
  79. export const HOW_HTML = `<div class="eyebrow">Example · v0</div><h1 class="t">How it's built</h1><div class="sub">the shape and what sits around it</div>
  80. <h3 class="sec">Filesystem</h3><pre>apps/example/…</pre>`;

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.