Automated README summary
Automatically summarized from the README on 26 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A GitHub Action that reviews repository files against user-authored yes/no questions. It is for teams wanting semantic CI gates on prompts, agent bundles, or other text artifacts without writing custom code.
How it uses Jev
Jev answers each configured question (with expected yes/no and threshold) over the selected files' text. The action passes only when every expected answer meets its probability threshold; failures can optionally trigger Jev-based source localization to annotate authored lines.
Primitives:choice
Technique worth stealing
Treat questions as properties that should hold, with per-question expected answers and probability thresholds, and gate CI on all of them passing.
Try it
Add a workflow step using sable-inc/jev-linter-action@v1 with model, glob, questions, and api-key inputs.
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 material0.94
- Shows a System One patternFound in material0.88
- Describes handling uncertaintyFound in material0.62
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalunclear0.52
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.27 / 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 26 Oct 2026.