Automated README summary
Automatically summarized from the README on 29 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-spec is a TypeScript CLI for developers who keep Markdown specifications. It checks code against the requirements in those specs and fails the build when they drift apart, fitting pre-commit hooks and CI gates.
How it uses Jev
For each requirement, jev-spec asks Jev one focused question (noul, or choice/score rubrics) over the specification and code of a target. Jev returns calibrated probabilities in one request per target; jev-spec compares them with your thresholds and exits 0, 1 or 2.
Primitives:noulchoicescore
Technique worth stealing
One narrow, literal yes/no question per requirement, gated by numeric thresholds instead of parsed prose.
Try it
npx jev-spec check; use --dry-run to validate setup without an API key.
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 material0.86
- Shows a System One patternFound in material0.78
- Describes handling uncertaintyFound in material0.64
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.60 / 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 29 Sept 2026.