toon
Skill0 starsChanged 29 days agoMITView on GitHub
Token-Oriented Object Notation (TOON) & Semantic HTML standard. Slashes token consumption by 55-80% compared to JSON/HTML for datasets, tables, and trackers, paired with zero-build semantic HTML browser rendering.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- sheikhsajid69/toon-skilltheir own version, first seen Jul 3, 2026
- MaGe1993/Claude-Code-Base-Harnesstheir own version, first seen Jun 14, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- sheikhsajid69/toon-skill★ 3same name
- MaGe1993/Claude-Code-Base-Harness★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 83
Never parse raw HTML tags for data: When reading companion .html files or documentation, extract strictly the <script id="data" …
- Very specific: line 103
Run toon sync filename.md to automatically generate the companion filename.html.
- Very specific: line 108
Run toon format filename.md to recompute array row counts [N].
- Very specific: line 109
Run toon sync filename.md to reflect changes in filename.html.
- Distinctive: line 115
When generating or styling companion HTML views:
- Very specific: line 116
Semantic Structure: Always use semantic HTML5 elements (<header>, <nav>, <main>, <article>, <section>, <aside>, <footer>, <figure>, …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
toon — Token-Oriented Object Notation & Semantic HTML Skill
TOON is a minimal, token-efficient data notation engineered specifically for AI agents, multi-agent systems, and developer documentation. It eliminates repetitive delimiters, structural tag bloat, and column drift, reducing LLM context window consumption by 55–80% compared to JSON and raw HTML, while pairing seamlessly with zero-build Semantic HTML5 browser rendering via toon-renderer.js.
1. Syntax Specification
metadata:
title: Production Cluster Overview
as_of: 2026-10-16
owner: Infrastructure Lead
services[3]{name,runtime,db,p99_ms,tier}:
auth-gateway,Go 1.22,Redis 7.2,14,Critical
billing-ledger,Laravel 11,PostgreSQL 16,38,Critical
event-indexer,Node.js 20,ClickHouse,45,Standard
checklist[3]:
- P99 latency above 100ms triggers autoscaling.
- Double-entry ledger state machine verification required.
- Zero unencrypted inter-service traffic.
notes:
Indented narrative text or markdown-style descriptive paragraphs.Syntax Grammar
- Tabular Records:
- Header:
name[count]{col1,col2,...}: - Explicit row count
[count]guarantees validation and prevents truncation hallucinations. - Column names defined once in
{...}. - Rows are indented with 2 spaces and comma-delimited.
- Cells containing commas must use semicolons (
;) or quotation marks.
- Header:
- Lists:
- Header:
name[count]: - Items indented with 2 spaces and prefixed with
-.
- Header:
- Key-Value Metadata:
- Indented
key: valuepairs under a rootmetadata:block.
- Indented
- Text / Notes:
- Header:
name: - Freeform indented text or markdown paragraphs.
- Header:
2. Dual-Mode Architecture
TOON combines lean AI model context consumption with rich, responsive human viewing:
┌───────────────────────────────┐
│ document.md │
│ (Contains ```toon``` block) │
└───────────────┬───────────────┘
│
toon sync ▼
┌───────────────────────────────┐
│ document.html │
│ (Semantic HTML5 container │
│ + <script type="text/toon">│
└───────────────┬───────────────┘
│
┌──────────────────┴──────────────────┐
▼ ▼
[ Browser User View ] [ AI Model Ingestion ]
- Semantic HTML layout - Extracts only ```toon```
- Responsive cards & tables - 55-80% token reduction
- Zero-build client rendering - Zero parsing hallucinations
- Modern accessible styling - Maximum reasoning context3. Agent Operational Protocols
Protocol A: Ingesting Context (Reading)
- Never parse raw HTML tags for data: When reading companion
.htmlfiles or documentation, extract strictly the<script id="data" type="text/toon">payload or thetoonblock in.md. - Ignore layout boilerplate: Discard UI markup, navigational wrappers, and styles to keep your context window lean.
Protocol B: Generating New Documents
- Draft
filename.mdfollowing the standard template:# Document Title > **Browser Viewable HTML:** [`filename.html`](filename.html) > **as_of:** YYYY-MM-DD > **owner:** Name --- ## TOON Specification (Token-Oriented Object Notation) ```toon [TOON DATA] - Run
toon sync filename.mdto automatically generate the companionfilename.html. - Validate syntax using
toon validate filename.md.
Protocol C: Modifying Existing Files
- Edit the
toonblock in.mddirectly. - Run
toon format filename.mdto recompute array row counts[N]. - Run
toon sync filename.mdto reflect changes infilename.html.
4. Semantic HTML Requirement
When generating or styling companion HTML views:
- Semantic Structure: Always use semantic HTML5 elements (
<header>,<nav>,<main>,<article>,<section>,<aside>,<footer>,<figure>,<figcaption>,<time>,<data>) rather than unsemantic<div>/<span>containers. - Client Rendering: Link
toon-renderer.jsandstyle.cssfor instant client-side rendering with dark/light theme support.
5. CLI Tooling Reference
# Validate syntax and row count integrity
toon validate <file.md|file.html>
# Automatically recount rows and format blocks
toon format <file.md|file.html>
# Generate / update companion HTML view
toon sync <file.md>Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

