Automated README summary
Automatically summarized from the README on 28 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Go linter where rules are plain-English questions. Static analysis selects exact AST nodes; a decision model answers a closed question about each node with a probability, and semcheck reports those above a threshold.
How it uses Jev
For each node selected by a rule, semcheck asks Jev one Noul: the probability that the rule's question is true. If the probability of the answer in report_if exceeds min_confidence, a finding is reported. Jev reads the node with type notes and context (statement or function).
Primitives:noul
Technique worth stealing
Use deterministic AST matchers to select nodes, then ask a decision model a closed question about each node.
Try it
go install github.com/arturobermejo/semcheck/cmd/semcheck@latest; set TYPESAFE_API_KEY; run semcheck ./...
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 projectunclear0.57
- Shows a System One patternFound in material0.76
- Describes handling uncertaintyunclear0.58
- Reports measured numbersFound in material0.95
- Is a runnable toolFound in material0.92
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.12
- Solves a common problem (0–2)score on a 0–2 scale1.73 / 2
- About JevFound in material0.88
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 28 Sept 2026.