Automated README summary
Automatically summarized from the README on 8 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Ten Grok Bot skills that route an agent's small decisions—search, mail, triage, routing—to TypeSafe's Jev decision model. For developers building Grok Bot agents who want typed, probabilistic decisions with fail-open fallbacks.
How it uses Jev
Each skill tells Grok Bot when to ask Jev, which exact `jev` command to run via its shell tool, what the reply means, and what to do when Jev is unavailable. Jev answers typed questions (pick one, score this, yes/no) about a piece of text and returns structured answers and probabilities; Choice and Score also include confidence.
Primitives:choicescorenoul
Technique worth stealing
Fail-open: every decision command has a conservative local fallback when keys or providers fail.
Try it
git clone https://github.com/fal3/grokbot-jev-skills ~/.local/share/grokbot-jev-skills && bash ~/.local/share/grokbot-jev-skills/install.sh
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 material0.90
- Shows a System One patternFound in material0.65
- Describes handling uncertaintyunclear0.60
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.85
- Top-10 learning shortlist signalunclear0.54
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.07 / 2
- About JevFound in material0.98
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 8 Oct 2026.