Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

typesafe-ai/skills

Official TypeSafe agent skill and Claude Code plugin that teaches coding agents to design System One workflows with typed judgments.

Agent skillproductionMIT
View on GitHub ↗

Overview

typesafe-ai/skills is TypeSafe's official agent skills package. Its single skill, typesafe-ai, teaches a coding agent how to design TypeSafe workflows, find current docs and cookbooks, and compose typed judgments (Choice, Score, Noul) in code. You can then ask an agent something like "route incoming support tickets by department, with human review for uncertain decisions".

It installs as a Claude Code plugin from TypeSafe's marketplace, or into other agents via skills.sh with npx skills add. Per one list summary, the skill is a single SKILL.md of about 10 KB and installs across many agents, with clean security scan results. It is MIT licensed. Installation is project-local by default with an option to install globally, and the docs include a prompt to paste into an agent for manual setup and updates.

What the decision model decides

TypeQuestionAnswers
OtherGuides the agent in writing Choice, Score and Noul questions for the user's workflow—

How it works

  1. Install the plugin or skill into your coding agent.
  2. Ask the agent to build a workflow with TypeSafe.
  3. The skill guides question design, thresholds and review paths.
  4. The agent writes code calling System One.

Strengths

  • Official and maintained by TypeSafe.
  • Works in Claude Code, Codex and other skills-compatible agents.
  • Small, single-file skill.

Caveats

  • Teaches patterns; it does not make decisions itself.
  • Generated code still needs a TypeSafe key.

Getting started

claude plugin marketplace add typesafe-ai/skills && claude plugin install typesafe@typesafe-ai  (or npx skills add typesafe-ai/skills --skill typesafe-ai)

At a glance

Type
Agent skill
Status
production
Runtime
Claude Code plugin, agent skill
Has code
yes
License
MIT
Stars
2,685

Use cases and integrations

How curated lists describe it

  • Official tooling: installable agent skills package (`npx skills add typesafe-ai/skills`) that teaches agents the Jev workflow.

    yibie/awesome-jev

  • Official skill: primitives, patterns, and how to structure evaluations. Claude Code: `claude plugin marketplace add typesafe-ai/skills` then `claude plugin install typesafe@typesafe-ai`. Other agents: `npx skills add typesafe-ai/skills --skill typesafe-ai`.

    AnotiaWang/awesome-decision-models

  • Agent skills for building with TypeSafe's System One API

    wh000wh000/awesome-jev-live

  • `npx -y skills@latest add typesafe-ai/skills -s typesafe-ai -g -a '*' --copy -y` → installed to `~/.agents/skills/typesafe-ai/` (a single-file SKILL.md, 149 lines / 10 KB, covering 79 agents). Security assessment: Gen=Safe, Socket=0 alerts, Snyk=Low Risk. The only failed item was Eve (global installation unsupported, no impact).

    wh000wh000/awesome-jev-live

  • Official agent skills for building and evaluating System One workflows.

    cobanov/awesome-jev

  • Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

    hellogumbo/awesome-jev

Frequently asked questions

What does the skill do?

It teaches a coding agent TypeSafe primitives, patterns and how to structure evaluations.

How do I invoke it in Claude Code?

With /typesafe:typesafe-ai after installing the plugin.

Is it official?

Yes, it is published by TypeSafe.

Related projects

  • Building with Jev★ 155

    Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.

    Agent skillproduction
  • jev-agent-toolkit

    Portable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.

    MCP serverbetaTypeScript
  • jev-anything

    Independent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.

    Agent skillbeta
  • jev-mode (tiffygk)

    Claude Code and Codex skills plus a study course for building with Jev, including Jevaluate, which rates how well projects use Jev.

    Projectbeta
  • jev-skill (marcodicesare-dev)

    Community Jev skill for Claude Code and Codex: a guide, a dependency-free Python CLI and 5 measured question sets.

    Agent skillbetaPython
  • jev-pipeline-skill

    Agent skill and CLI that chains Jev question design: find decision calls, check fit, draft, lint, calibrate thresholds and plan a cascade.

    Agent skillprototypePython