TanStack/intent

A CLI for library maintainers to generate, validate, and ship Agent Skills alongside their npm packages.

What it solves

TanStack Intent allows library maintainers to create and distribute "Agent Skills" that can be used by AI agents. It solves the problem of how to make npm packages functionally accessible to AI agents in a standardized way, ensuring that the skills are versioned alongside the code and are auto-discoverable.

How it works

It is a CLI tool that enables maintainers to generate, validate, and ship these Agent Skills. It follows the open Agent Skills standard to ensure compatibility across different agentic systems.

Who it’s for

JavaScript and TypeScript library maintainers who want their packages to be usable by AI agents.

Highlights

  • Auto-discovery of skills
  • Versioning synchronized with npm package versions
  • Compatible with the open Agent Skills standard
  • CLI-driven generation and validation

Related

  • Project
    vercel-labs/skills

    A CLI for the open agent skills ecosystem that allows users to install and manage reusable instruction sets across various AI coding agents.

  • Project
    skilld-dev/skilld

    A curated registry and CLI for discovering, installing, and managing human-authored skills (standardized instructions) across multiple AI agents.

  • Project
    tiangolo/library-skills

    A tool that installs and manages official AI skills provided by libraries, ensuring AI agents use the most current and correct code patterns instead of outdated training data.

  • Project
    agentskills/agentskills

    A standardized, open format for packaging specialized knowledge and workflows into portable folders that AI agents can load on demand to gain domain expertise.