Skip to content

Skill suggestion

TypeSafe's official cookbook for a two-stage skill-suggestion workflow that selects a skill and can reject the shortlist.

Articleproduction

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

This is a cookbook page in TypeSafe's documentation. According to the directory summary, it describes an official two-stage workflow for skill suggestion: first selecting candidate skills, then evaluating the shortlist, with the option to reject all of them.

No page content was fetched. Several community projects, such as SkillRanker, say they build on this recipe, using a broad comparison across many skills followed by a closer look at a shortlist with a real 'none of these' option.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich skill (or none) fits the current task?(inferred)—
Yes / noDoes this shortlisted skill actually fit?(inferred)—

How it works

  1. Compare all candidate skills broadly
  2. Shortlist the top candidates
  3. Evaluate each shortlisted skill, allowing rejection of all

Strengths

  • Official reference pattern
  • Explicit rejection option avoids forced picks

Caveats

  • Grounded only in a one-line summary

At a glance

Type
Article
Status
production
Has code
no
Has tests
no

Use cases and integrations

How curated lists describe it

  • Official two-stage workflow that selects a skill and can reject the shortlist.

    cobanov/awesome-jev

Frequently asked questions

What does the cookbook describe?

A two-stage workflow that selects a skill and can reject the shortlist.

Who uses it?

Community tools such as SkillRanker cite it as their basis.

Where is it?

docs.typesafe.ai/cookbooks/skill_suggestion.

Related projects

  • Claude skill that gives a ten-line gut-check on whether Jev could help with what you are building, citing tested patterns.

    Agent skillbetaMarkdown
  • Thirty worked Jev uses in ten levels, from a smart if statement to a pi coding agent that writes its own Jev questions.

    ProjectbetaTypeScript
  • Agent skill that makes a coding agent try Jev first for bounded judgments like classify, rank or gate, and log each attempt.

    Agent skillbetaPython
  • Independent Markdown reference on the Jev API, patterns and limits, written for engineers and coding assistants to build from.

    Service
  • Accenture thought piece and site on stack migration with Google Cloud, placing Jev as the System 1 layer that routes, classifies and gates.

    MCP serverdiscussionRust
  • Community directory of Jev apps, resources and runnable offline examples, with a guide skill and a searchable JevList web UI.

    Articleproduction