Automated README summary
Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A public web app that critiques YouTube thumbnails and slides. Users paste a TypeSafe API key, and the page sends each image to Jev for atomic judgments, then combines them into a 0–100 score with flags and a headline box.
How it uses Jev
For each image, about ten atomic questions run in parallel against Jev: Scores for readability, clutter, contrast, face/text density; Nouls for focal point, phone legibility, busy background, headline presence; a Choice for the first fix; and a Box around the headline when the headline Noul is at least 0.50. The page combines the results into a weighted 0–100 score.
Primitives:choicescorenoul
Technique worth stealing
Combine parallel atomic Jev judgments with renormalised reference weights into a single score, flagging low-confidence results without changing the number.
Try it
npm install && npm test && npm run build && npm run serve, then open http://127.0.0.1:4173
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.95
- Shows a System One patternFound in material0.65
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.65
- Top-10 learning shortlist signalnot found in the excerpt0.34
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale0.88 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 22 Oct 2026.