What it is
A Chrome and Firefox extension that scores draft X posts and reply context before posting, rendering a scorecard with virality, funniness, informativeness, clarity, insult level, ragebait, cringe, "sounds AI-written", regret risk, typo detection, and likely crowd reaction, plus an overall verdict.
How it uses Jev
Jev evaluates the draft text (and reply_to/quoting context) against rubrics in one request, returning scores for each metric. The content script normalizes scores to 0–1 and combines them into a verdict. Optional media descriptions from OpenAI are passed as media.
Primitives:scorenoulchoice
Technique worth stealing
Send all rubric questions to Jev in one request so adding rubrics costs tokens but not latency.
Try it
Load unpacked in Chrome or temporary add-on in Firefox, configure TypeSafe API key, then type on x.com/compose/post.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.85
- Shows a System One patternno0.37
- Handles uncertaintyno0.06
- Measuredno0.05
- Runnableyes0.98
- Worth recommendingno0.32
- Model replicano0.04
- Problem scopescore on a 0–2 scale1.04
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.