How do I install the Toon Formatter skill?

Run npx skillmds@latest add majiayu000/toon-formatter-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Toon Formatter safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Toon Formatter?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Toon Formatter free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Toon Formatter?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Toon Formatter by majiayu000 — Agent Skill

Name: Toon Formatter
Rating: 4.2 (5 reviews)
Author: majiayu000

Toon Formatter

AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transaction", "metric", "analytics", "API", "database", "query", "TOON".

majiayu000 Updated Sep 9, 2026 567 repo stars

File contents

TOON v2.0 Formatter

AGGRESSIVELY apply TOON format to save 30-60% tokens on structured data.

When to Use

YES - Use automatically:

Arrays with ≥5 similar items
Tables, logs, events, transactions, analytics
API responses with ≥60% field uniformity
Database results, metrics, benchmarks

NO - Keep as JSON:

Small arrays (<5 items)
Deeply nested or non-uniform data
Narrative text, instructions

Quick Reference

Tabular (uniform objects):

[3]{id,name,role}:
  1,Alice,admin
  2,Bob,user
  3,Carol,user

Inline (primitives ≤10):

tags[4]: js,react,node,api

Delimiters: comma (default), tab [N\t], pipe [N|]

Key folding (nested objects):

server.host: localhost
server.port: 8080

Binary Encoder (20x faster)

# Encode JSON to TOON
.claude/skills/toon-formatter/bin/toon encode data.json

# With options
.claude/skills/toon-formatter/bin/toon encode data.json --delimiter tab --key-folding

# Check if TOON recommended
.claude/skills/toon-formatter/bin/toon check data.json

# Decode TOON to JSON
.claude/skills/toon-formatter/bin/toon decode data.toon

Commands

/toon-encode <file> - JSON to TOON
/toon-decode <file> - TOON to JSON
/toon-validate <file> - Validate TOON
/analyze-tokens <file> - Compare savings
/convert-to-toon <file> - Full conversion workflow

Documentation

Complete Guide: docs/toon-guide.md
Build Instructions: docs/INSTALL.md
Source Code: src/toon.zig
Spec: https://github.com/toon-format/spec

---name: toon-formatter-2description: AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transaction", "metric", "analytics", "API", "database", "query", "TOON".--- # TOON v2.0 Formatter **AGGRESSIVELY** apply TOON format to save 30-60% tokens on structured data. ## When to Use **YES - Use automatically:** - Arrays with ≥5 similar items - Tables, logs, events, transactions, analytics - API responses with ≥60% field uniformity - Database results, metrics, benchmarks **NO - Keep as JSON:** - Small arrays (<5 items) - Deeply nested or non-uniform data - Narrative text, instructions ## Quick Reference **Tabular** (uniform objects): ``` [3]{id,name,role}: 1,Alice,admin 2,Bob,user 3,Carol,user ``` **Inline** (primitives ≤10): ``` tags[4]: js,react,node,api ``` **Delimiters:** comma (default), tab `[N\t]`, pipe `[N|]` **Key folding** (nested objects): ``` server.host: localhost server.port: 8080 ``` ## Binary Encoder (20x faster) ```bash # Encode JSON to TOON .claude/skills/toon-formatter/bin/toon encode data.json # With options .claude/skills/toon-formatter/bin/toon encode data.json --delimiter tab --key-folding # Check if TOON recommended .claude/skills/toon-formatter/bin/toon check data.json # Decode TOON to JSON .claude/skills/toon-formatter/bin/toon decode data.toon ``` ## Commands - `/toon-encode <file>` - JSON to TOON - `/toon-decode <file>` - TOON to JSON - `/toon-validate <file>` - Validate TOON - `/analyze-tokens <file>` - Compare savings - `/convert-to-toon <file>` - Full conversion workflow ## Documentation - **Complete Guide:** `docs/toon-guide.md` - **Build Instructions:** `docs/INSTALL.md` - **Source Code:** `src/toon.zig` - **Spec:** https://github.com/toon-format/spec

Frequently asked questions