DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to build a Jev pull request grader in Codex with Building with Typesafe Jev

Install the skill in Codex to build a Score-based check that grades pull requests.

Who it is forAn engineering lead who wants an automated first pass on pull requests and works in Codex.

The problemAsking a model for a free-text verdict gives results that are hard to threshold or compare across runs.

The outcomeCodex builds a Score question on a scale from the spec being ignored to the spec being met, with a threshold that sends weak pull requests to a human.

What you need first

  • A coding agent that loads skills, such as Claude Code, Codex, Antigravity CLI, Muse Code, or an agent that reads SKILL.md
  • Git or a web browser to reach the GitHub repository
  • A TypeSafe AI API key from console.typesafe.ai, needed only for the optional live check

Steps

  1. Run codex plugin marketplace add aaddrick/building-with-typesafe-jev
  2. Run codex plugin add building-with-typesafe-jev@building-with-typesafe-jev
  3. Start a new Codex thread so the skill can load.
  4. Ask Codex to build a pull request grader that uses a Jev Score question and flags low scores for human review.

Prompt for your agent

In this repo, use the building-with-typesafe-jev skill to write a script that sends a pull request diff and its spec to Jev as a Score question on a described scale, then flags results below a threshold. Show the question text and the threshold. Verify the script handles the Score result as a value on the scale you defined.

Caveat. The skill gives design guidance only, so the grader still needs its own tests and a human check on flagged results.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page