From the author
Use Jev, TypeSafe's System One classifier, whenever a coding task needs a classifier under the hood: labelling or routing many items (issues, files, log lines, test failures, commits, messages), yes/no checks with a calibrated probability (does this diff touch auth, is this claim supported by the log, is this failure flaky), scoring on ordered levels (severity, priority, quality), or ranking candidates by relevance (which file answers this question). Prefer it over eyeballing long lists, brittle regex heuristics, or one frontier-model call per item. Tools: jev_classify, jev_check, jev_score, jev_rank, jev_ask (MCP or native), with the `jev-code` CLI as a bash fallback. Also use when the user's own application needs a classifier, router, guardrail, or verifier built on TypeSafe's API or SDKs. Needs a TypeSafe, OpenRouter, or Vercel AI Gateway API key.
Install
npx skills add FrancoisChastel/jev-code --skill jev -a claude-code
Installs to .claude/skills/jev/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 82
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- jev-evalOneWave-AI/claude-skillsBuild and run a labelled eval set for a System One model (Jev, Von, or any typed-decision config), then sweep criteria wordings and thresholds against it. Use when a Jev/Von classification is wrong or unreliable, when choosing between the hosted API and a local open model, when tuning noul thresholds, or before shipping any typed-decision feature. Produces an accuracy-by-wording matrix and a calibrated threshold.Engineering★ 384
- building-with-typesafe-jevaaddrick/building-with-typesafe-jevUse when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action), when brainstorming where AI could fit in an app, when an LLM call exists only to pick a label, score, or yes/no, or when code uses TypeSafe AI, Jev, System One, typesafe-sdk, or @typesafe-ai/sdk.Planning★ 148
- jev-question-translatorlawve-ai/awesome-legal-skillsTurns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a battery of narrow questions that TypeSafe's Jev, a fast classifier that returns probabilities rather than prose, can answer reliably across many documents. The skill breaks conclusions such as negligence, felony murder, or standing into element-level questions, writes the governing rule into each question, and delivers the questions alone, in Jev's request format or in plain English. Built for legal work that asks the same questions of many texts: coding statutes across jurisdictions, coding opinions or case files for empirical research, checking contracts against a review checklist, screening intake narratives, and grading student work against a rubric. Use when asked to write Jev questions, build a classifier for legal documents, or turn a legal test into yes-or-no questions. Running the questions requires Jev access; writing them does not.Testing★ 900
- awesome-jevAbdelStark/awesome-typesafe-jevDiscover and compare Jev and TypeSafe SDKs, integrations, applications, and evaluations. Use when selecting public resources for a typed-decision workflow or checking what evidence exists for a Jev claim.Productivity★ 607
- building-with-jevnotque/vexjoy-agentWrite, compose, integrate, and improve programs that call Jev, TypeSafe's System One judgment model.Writing★ 443
- jev-integrateOneWave-AI/claude-skillsWire a System One model (Jev, or an open reproduction like Von) into a product feature — routing, guardrails, scoring, classification. Use when replacing an LLM call that returns a label rather than prose, when adding a typed decision to an agent loop, or when deciding between the hosted Jev API and a local open model. Covers question design, the eval-set-first workflow, threshold calibration, confidence gates, and the traps measured on real data.Design★ 384
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in