Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An unofficial community skill that teaches coding agents to design for TypeSafe AI's Jev, a System One model returning typed answers with calibrated probabilities. It bundles guidance plus links to 150+ community projects sorted by pattern, each with a code sketch, for agents like Claude Code, Codex, Antigravity CLI, Muse, and Muse Code.
How it uses Jev
The README describes Jev as answering typed questions (Choice, Score, Noul) with a value and calibrated probability, usually in 100 to 200 ms. It does not specify which decisions the skill's own code makes or how results are wired into code; it only says the skill teaches agents to design for Jev and can check designs against the live API when TYPESAFE_API_KEY is set.
Primitives:choicescorenoul
Technique worth stealing
Design for Jev as a typed-decision model: send content plus typed questions and read back values with calibrated probabilities, not generated text.
Try it
Install via the Claude Code, Codex, Antigravity CLI, Muse, or Muse Code commands in the README; optionally set TYPESAFE_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 patternunclear0.58
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolnot found in the excerpt0.17
- Top-10 learning shortlist signalunclear0.40
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 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 19 Oct 2026.