今日热榜中文
← Back to plugins

Task skills

TypeSafe Agent Skills (Jev)

typesafe-ai/skills

Help your AI build software that uses Jev for classification, ranking, and choosing the next step.

View source code ↗Project website ↗Setup and usage guide ↗

Introduction

Prepared by 今日热榜 from public project documentation

Use this TypeSafe-maintained skill when building software that routes support requests, screens information, or chooses from a defined set of actions. It guides your assistant to current documentation and helps compose typed decisions from models such as Jev into code. The results are choices or probabilities rather than chat responses. Installing the skill does not replace your assistant or grant API access. Prepare a skill-capable assistant; actual Jev calls require your own TypeSafe account and key, with service usage charged separately.

Get started

Check the requirements, then choose your AI assistant to see the setup steps.

What you need
  • Codex, Claude Code, or Cursor with skill support.
  • Skills CLI requires Node.js and npm; actual Jev calls also require a TypeSafe account and API key.
Costs
Skill files are MIT-licensed; TypeSafe API and assistant usage are separate costs, not free Jev access.
Required permissions
Installation adds a skill or plugin. Actual API calls send selected text and state to TypeSafe; keep keys in your own runtime and server-side in web applications.
CodexManual configuration needed

The README provides a Skills CLI setup path; select Codex.

Setup steps

  1. Open the Install section of the official README.
  2. Use the documented Skills CLI to select the typesafe-ai skill and target Codex.
  3. Start a new session and plan a classification task first; prepare your account and key before actual API calls.

Check that setup worked

Ask it to design routing for a few fictional support tickets and separate code rules from Jev decisions; planning does not require an API call.

Official sources

Claude CodeOfficial setup documented

The official README provides Claude Code plugin setup.

Setup steps

  1. Open the Install section of the official README.
  2. Follow the Claude Code plugin section to install the typesafe plugin.
  3. Start a new session and plan a classification task first; prepare your account and key before actual API calls.

Check that setup worked

Ask it to design routing for a few fictional support tickets and separate code rules from Jev decisions; planning does not require an API call.

Official sources

CursorManual configuration needed

The README provides a Skills CLI setup path; select Cursor.

Setup steps

  1. Open the Install section of the official README.
  2. Use the documented Skills CLI to select the typesafe-ai skill and target Cursor.
  3. Start a new session and plan a classification task first; prepare your account and key before actual API calls.

Check that setup worked

Ask it to design routing for a few fictional support tickets and separate code rules from Jev decisions; planning does not require an API call.

Official sources

Official sources

Setup guidance reviewed 2026-10-13 · Based on public documentation; not individually installed and tested here.

Ways to use it

  • Compose classification, routing, and ranking decisions in code
  • Use official documentation to integrate Jev and the TypeSafe API
  • Plan verification or human review for uncertain results

The project’s original description

Agent skills for building with TypeSafe's System One API

More projects of this type

These other listed projects can help you compare use cases and setup requirements.

  • Superpowers — Give AI a development workflow for clarifying requirements, planning, coding, and checking results.
  • Marketing Skills — Give AI workflows for website copy, SEO reviews, and conversion improvements.
  • Obsidian Skills — Give AI Obsidian guidance for linked notes, properties, canvases, and database-style views.

Sources and ranking

This directory lists AI development plugins with public source code and a clear purpose. Browse by task, then open an introduction to learn what a project does, who it is for, and what you need to get started. It covers selected projects, not every AI plugin.

How do the three plugin types differ?

Tool connections (MCP) let AI assistants use external tools such as browsers, code repositories and databases. MCP is the protocol used for these connections.

Reusable skills give a compatible AI assistant instructions and guidance for a particular task.

Editor plugins run inside the software you use to write code, adding AI chat, completions or suggested edits.

How does “Most starred” work?

Projects are sorted by their total GitHub stars. Stars indicate interest; they are not downloads, active users or quality scores. A skill pack counts as one project. Daily star growth is not shown without historical records.

What does “Recently updated” mean?

It uses the most recent code push, which may not be a new release. The 7-day filter checks that project update time; ranking still uses all-time stars. Each introduction shows when its star count was collected. Failed updates keep the last saved data.

Introductions are based on public project documentation. These projects have not each been installed and tested here. Check the project documentation for setup, compatibility and service costs. Refreshing this list only reads saved data; it does not start collection.

UTC+8