Not in the top 1,000 by GitHub stars
inkboard/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
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/system-atlas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
f7005f275861 → f7005f275861
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → f7005f275861
No earlier version was observed for comparison.
Heat
1.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- system-atlas
skills/system-atlas
How it works
system-atlas
When your agent uses it
Build and maintain an explorable, progressively-disclosed isometric "atlas" of a system's architecture — an interactive page (hover to read, click to pin, go inside for steps, moving data packets you can inspect, chapters that reveal the system a few structures at a time) plus a generated text twin (SYSTEM.md) and question tracking by ID, all from one data file in the repo. Use this whenever someone wants to discuss, design, review, or explain an architecture visually — "make an atlas", "map the system", "make the architecture explorable", "visualize the codebase/agent/pipeline so we can talk about it", "a diagram I can click around", "walk me through how it fits together", or when an architecture discussion is producing a pile of open questions that need tracking across feedback rounds. Also use it to update an existing atlas after decisions change.
What it loads into context
Frontmatter
189 tokensAlways available to the agent
SKILL.md
2,111 tokensWhen the skill is activated
Reference documents
2,402 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to reach for it — and when not
- Process
- Publishing the map
- What done looks like
- Verify before publishing
- Files in this skill
Scripts executed separately
assets/build.mjsassets/data.example.mjs
Files
SKILL.mdcore9,350 bytesSKILL.mdcore9,350 bytesassets/build.mjsruns5,680 bytesassets/data.example.mjsruns5,894 bytesassets/template.htmlasset38,247 bytesevals/evals.jsonasset2,171 bytesreferences/design-language.mddoc4,644 bytesreferences/process-and-lessons.mddoc5,037 bytes
Read SKILL.md
# System Atlas
An atlas is one data file that renders two views: an **interactive isometric map** (a single self-contained HTML file), and a **generated text twin** (`SYSTEM.md`) with the decisions table, every structure, the flows, and the open questions by ID. The data file is the only thing anyone edits; both views rebuild from it. It sits beside a hand-written glossary (`CONTEXT.md`) and ADRs.
The reason for this shape: an architecture discussion produces 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. The map is for them; the text twin is for the repo and for you next session; the single source is what keeps the two honest.
This skill was distilled from building a real agent-architecture atlas across one long design session and several rounds of feedback. The user's corrections from that session are the rules below; `references/process-and-lessons.md` has the story.
## When to reach for it — and when not
Use it when the system is new enough that vocabulary, decisions, and questions are still moving, and there will be more than one feedback round. Don't use it for a finished system that only needs a README, or for one diagram in a PR.
## Process
View the complete source on GitHubSkills included
- system-atlas
Repository facts
- License
- MIT
- Created
- Aug 20, 2026
- Last pushed
- Sep 1, 2026
- Forks
- 16
- Open issues
- 0
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
skills/system-atlas/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 9 network referencesin 1 file: system-atlas/assets/template.html:2
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: system-atlas/assets/build.mjs:1 system-atlas/assets/data.example.mjs:1
- No access to secrets
- No requests to vote in Hot
Show all 11 signals by file
skills/system-atlas/assets/build.mjs
- Executable scriptline 1
Executable file
skills/system-atlas/assets/data.example.mjs
- Executable scriptline 1
Executable file
skills/system-atlas/assets/template.html
- Network accessline 2
<meta charset="utf-8"> <title>__TITLE__</title> <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:ital,wght@0,400;0,500;0,600;1,400&display=swap"> - Network accessline 3
<title>__TITLE__</title> <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:ital,wght@0,400;0,500;0,600;1,400&display=swap"> <style> - Network accessline 4
<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:ital,wght@0,400;0,500;0,600;1,400&display=swap"> - Network accessline 136
<nav id="index" aria-label="Structures"></nav> <div id="canvasWrap"> <svg id="svg" xmlns="http://www.w3.org/2000/svg"> - Network accessline 137
<div id="canvasWrap"> <svg id="svg" xmlns="http://www.w3.org/2000/svg"> <defs> - Network accessline 138
<svg id="svg" xmlns="http://www.w3.org/2000/svg"> - Network accessline 172
const byId = Object.fromEntries(NODES.map(n=>[n.id,n])); const center = n => [n.gx+n.w/2, n.gy+n.d/2]; const NS='http://www.w3.org/2000/svg'; - Network accessline 173
const center = n => [n.gx+n.w/2, n.gy+n.d/2]; const NS='http://www.w3.org/2000/svg'; const el=(t,a={},...kids)=>{const e=document.createElementNS(NS,t);for(const k in a)e.setAttribute(k,a[k]);kids.forEach(k=>e.appendChild(k));return e;}; - Network accessline 174
const NS='http://www.w3.org/2000/svg';
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 2 facts
- Executable script in a comment of a file that runssystem-atlas/assets/build.mjs:1Low confidence
- Executable script in a comment of a file that runssystem-atlas/assets/data.example.mjs:1Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/system-atlas/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/system-atlas/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/system-atlas/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/system-atlas/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/system-atlas/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/system-atlas/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.