Claude skill
Building with Typesafe Jev
Building with Typesafe Jev is a Claude skill in the Building With Typesafe Jev plugin. Use when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action)…
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
Use when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action), when brainstorming where AI could fit in an app, when an LLM call exists only to pick a label, score, or yes/no, or when code uses TypeSafe AI, Jev, System One, typesafe-sdk, or @typesafe-ai/sdk.
The skill's instructions (about 1,943 words) cover:
- Overview
- Test against the live API when you can
- Pick the primitive
- Rules
- Using the numbers
- When an answer is wrong
- Common mistakes
How to use it
- Building with Typesafe Jev comes inside the Building With Typesafe Jev plugin, so you get it by installing that plugin. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- Ask Claude for the task. When your request matches the skill's description, Claude loads it.
- To pick it yourself in Claude chat, type
/or click + and choose building-with-typesafe-jev. In Claude Code and Cowork, type:/building-with-typesafe-jev:building-with-typesafe-jev
Source
- Plugin
- Building With Typesafe Jev
- SKILL.md
- View on GitHub
- Repo stars
- 156
- Repo last pushed
- Oct 1, 2026
- Checked
- Nov 16, 2026