slopcheck-jev
harshpuri84
A prose linter that catches AI writing tells. Regex settles the 18 a pattern can settle. Jev takes the 15 that need reading, as 15 Nouls in one call, 604 ms median. It ships as a Claude Code `Stop` hook that scores Claude's own output after every turn and warns rather than blocks.
- ライセンス
- MIT
- GitHub Stars
- 0
- ソース確認日
- —
Jev が判断する箇所
**Deleting a feature made it more accurate.** The first build made a second Jev call to pin each tell to a sentence. Removing it took precision from 0.80 to 0.95 and latency from 1,365 ms to 575 ms. Jev returns typed answers rather than text, so a quote has to come from a second round of typed questions about lines, and that round was where every defect lived. The README documents the two intermediate designs that were worse.
このプロジェクトの用途
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
確認の範囲
公開ソースと連携ロジックを確認済み。
ソースと実装
同じカテゴリのプロジェクト
SemDecide
sharziki · CLI・パイプライン
テキストや JSONL を判定・分類・採点・フィルタリングする Python CLI。
TypeSafe AI Playground
markjaquith · CLI・パイプライン
医療情報の検査、コメント確認、語調分析、業種・職業分類を試せる Rust CLI。
jev-cli
tumf · CLI・パイプライン
テキストや JSON を Jev で判断する CLI と stdio MCP サーバー。
jev-cli
jtsang4 · CLI・パイプライン
文章や JSON を入力し、Jev に分類・Yes/No・評価を質問する CLI。