Skills
.Work. You
Rest

tml

Community

Token-efficient API schemas for AI agents

Software Engineering#openapi#token-optimization#agent-tools#tool-manifest#llm-agents#api-schema#tml
Authormaf404
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill solves the problem of verbose API schemas wasting tokens and confusing AI agents. Traditional formats like OpenAPI JSON use excessive tokens and reduce tool selection accuracy, making it expensive and unreliable for agents to discover and call APIs.

Core Features & Use Cases

  • TML Source Format: Human-readable, editable tool definitions with intent descriptions, auth declarations, and structured parameters.
  • .min Index Format: Ultra-compiled, token-optimized one-line-per-tool format that agents can parse instantly.
  • OpenAPI Conversion: Automatically compile existing OpenAPI specs into TML and .min formats.
  • Use Case: A developer building an AI agent that needs to call the GitHub API can convert the OpenAPI spec to a .min file, reducing token usage from 1047 to 243 tokens while maintaining 100% tool selection accuracy.

Quick Start

Use the tml skill to convert an OpenAPI spec into a .min tool registry file for AI agents.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: tml
Download link: https://github.com/maf404/tml/archive/main.zip#tml

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 537,000+ vetted skills library on demand.