Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Eyedot turns uploaded study material into a self-exam that grades written answers point by point, shows which ideas were missed, and provides a mistake log and weak-point review. For learners and agents.
How it uses Jev
Jev grades written answers: one noul per rubric point, where the probability is the point score. Code weights and combines these probabilities. Judgment strength is |p−0.5|×2. Weakly judged key points become 'needs review' with a score range, excluded from mastery.
Primitives:noul
Technique worth stealing
Decompose grading into atomic checkable questions, decide each with a decision model, combine probabilities in code.
Try it
npm install && npm run dev (offline demo mode without keys) or use the Agent Skill CLI.
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 projectFound in material0.87
- Shows a System One patternFound in material0.95
- Describes handling uncertaintyFound in material0.71
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolFound in material0.78
- Top-10 learning shortlist signalunclear0.57
- Is a replica of the modelnot found in the excerpt0.18
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 2
- About JevFound in material0.97
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 6 Oct 2026.