Automated README summary
Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude skill for cleaning up a Gmail inbox. You say "triage my inbox"; Claude fetches new mail, has a small model sort each message, archives the noise, and reports what still needs you. It never deletes, and one search undoes a run.
How it uses Jev
For each message, scripts/classify.py asks TypeSafe Jev five fixed questions over the sender, subject, date, existing labels and up to 800 characters of body. The first question picks one of ten categories; a table in the script turns the category into an action. The other four flag phishing, waiting replies, low confidence and near deadlines.
Primitives:choicescore
Technique worth stealing
Use a decisions model with fixed questions and a category-to-action table instead of asking a chat model to write an opinion.
Try it
git clone into ~/.claude/skills/inbox-classifier, export OPENROUTER_API_KEY, run scripts/classify.py --selftest.
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 material0.77
- Shows a System One patternnot found in the excerpt0.33
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolFound in material0.64
- Top-10 learning shortlist signalnot found in the excerpt0.21
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 2
- About JevFound in material0.96
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 13 Oct 2026.