Automated README summary
Automatically summarized from the README on 27 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A one-page portfolio/study project for developers: paste a code snippet and get an instant quality/red-flag triage from Jev, then optionally a detailed markdown review with fixes from Claude. Spring Boot backend, React frontend.
How it uses Jev
On Review, the backend asks Jev three questions in a single call: a 1–10 quality score, and yes/no red-flag checks for security and performance, each with a confidence value. QuickReviewService builds the question set and maps score/noul answers; the result is shown as a score plus red-flag badges.
Primitives:scorechoice
Technique worth stealing
Pair an instant calibrated-probability triage with an optional LLM deep-dive, proxying all AI calls through the backend.
Try it
Run backend/run-local.ps1, then cd frontend && npm install && npm run dev.
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 projectunclear0.52
- Shows a System One patternFound in material0.90
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.79
- Top-10 learning shortlist signalunclear0.51
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
- About JevFound in material0.98
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 27 Sept 2026.