Measured guidance for writing Jev (System One) question maps and evaluating them: design rules backed by a 57-suite study, plus an offline audit that finds the defects static review misses.
Plugin jev from marketplace jev in BarakChamo/jev-kit. Commands read from the repo's manifest — 1 month ago.
jev-evalMeasure a Jev (TypeSafe System One) question map on labelled cases — build a test suite, run it through Jev, find the answers it got wrong while confident, fit a confidence threshold, and check whether a change really helped or whether Jev beats an LLM. Use when evaluating or benchmarking Jev, findi
jev-fitDecide whether a classification, extraction, triage, screening or gating decision should run on Jev (TypeSafe's System One typed evaluator) instead of an LLM, and predict the likely accuracy gap before building. Use when someone proposes using Jev / System One / a typed evaluator, asks "should this
jev-questionsWrite, review or fix Jev (TypeSafe System One) question maps — the state plus the typed noul / choice / score questions sent to the systemone API — using rules measured on 57 labelled suites and re-tested on agent-written maps. Use whenever writing or editing Jev questions, instructions, criteria or
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.
1 skill
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.
48 skills · hooks
Connect providers and targets, write eval suites, and set up or run red team scans with promptfoo
4 skills
Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.
1 MCP server
Verbatim Jev-guided compaction for Claude Code sessions.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.