A new data format called TOON helps AI prompts use fewer tokens. Tokens are the parts of text that language models process. Fewer tokens means lower costs and faster responses. TOON is a compact way to write JSON data.
This format combines two simple styles. It uses indentation like YAML for nested objects. It uses a table-like layout for lists of similar items. The result is about 40 percent fewer tokens than regular JSON. Your AI model gets the same information in a smaller package.
Anyone who sends data to a language model can benefit. Developers can convert their JSON files to TOON easily. The tool works from the command line or as a code library. It makes your prompts leaner without losing accuracy.
Global
mkdir -p ~/.claude/skills/toon-formatProject
mkdir -p .claude/skills/toon-formatSource Repository
Cavemanjuliusbrussee/caveman
Talk like a smart caveman to save tokens without losing technical accuracy
Cavemanmattpocock/skills
Caveman mode for AI cuts token count 75% without losing technical accuracy
Enhance Promptgoogle-labs-code/stitch-skills
Turn vague UI ideas into clear, polished prompts with design system consistency
Humanizer Zhop7418/humanizer-zh
Remove AI writing patterns to make your text sound natural and human
Gws Modelarmorgoogleworkspace/cli
Filter harmful user content automatically with Google Model Armor for safety
Prompt Engineering Patternswshobson/agents
Master advanced prompt engineering patterns to get reliable and powerful AI outputs every time
Context Engineeringaddyosmani/agent-skills
Optimize your agent's context to improve output quality and focus
Writetw93/waza
Rewrite your prose to sound human and natural every time