Automated README summary
Automatically summarized from the README on 18 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An unofficial community skill for coding agents (Claude Code, Codex, Antigravity CLI, Muse, Muse Code) that teaches them to design for Jev rather than treat it as a chat model, with links to 150+ community projects sorted by shape and a code sketch for each.
How it uses Jev
The skill guides agents to send content plus typed questions to Jev and use the returned value and calibrated probability in code: Choice to pick one option from a list, Score to place content on a described scale, and Noul for the probability a yes/no statement is true. With TYPESAFE_API_KEY set, the agent can check its design against the live API before code reaches the project.
Primitives:choicescorenoul
Technique worth stealing
Design Jev calls as typed questions (Choice/Score/Noul) with calibrated probabilities rather than free-text generation, and validate the design against the live API when a key is available.
Try it
Install via the plugin marketplace command for your agent, e.g. claude plugin marketplace add aaddrick/building-with-typesafe-jev.
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 material0.84
- Shows a System One patternunclear0.56
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolnot found in the excerpt0.19
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 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 18 Oct 2026.