TypeSafe Agent Skills

Agent skills for building with TypeSafe: typed decisions and probabilities from System One models.

You can read SKILL.md on GitHub or fetch its raw Markdown.

Install

Claude Code plugin

Run in your terminal:

claude plugin marketplace add typesafe-ai/skills
claude plugin install typesafe@typesafe-ai

Other agents via skills.sh

npx skills add typesafe-ai/skills --skill typesafe-ai

Select your agent when prompted. Installation is project-local by default; add -g to install globally.

See the installation guide for a prompt to copy to your agent, manual installation, and updates.

Use

Ask your agent, for example:

Use TypeSafe to route incoming support tickets by department, with human review for uncertain decisions.

In Claude Code, you can explicitly invoke the plugin skill with /typesafe:typesafe-ai.

Skill	Purpose
typesafe-ai	Design TypeSafe integrations: state and questions, request composition, live probing, and pointers to current docs

License

MIT.