Jev Decision
Fast structured decisions via 9router System One (Jev jev-1.13). Use for routing, task classification, delegation, review/test/UI gates. Returns typed choice/noul/score with probabilities, not text. Triggers: jev, systemone, triage, route, delegation gate, review gate, test scope.
Install
npx skills add PanPanFR/oh-my-openkilo --skill jev-decisiongit clone --depth 1 https://github.com/PanPanFR/oh-my-openkilo.git /tmp/oh-my-openkilo
mkdir -p ~/.claude/skills
cp -r /tmp/oh-my-openkilo/skills/jev-decision ~/.claude/skills/jev-decisionPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Jev Decision (System One, via 9router)
Jev is a decision-only model. It never generates text or code. It scores a `state` string against typed `questions` and returns calibrated answers in ~100-500ms. Use it at decision points; keep the chat LLM for generation.
- Endpoint: `POST <baseURL>/systemone` (configured via `providers.9router.settings.baseURL` in opencode.json, or `JEV_ENDPOINT` env var)
- Model: `openrouter/typesafe/jev-1.13` (verified live 2026-09-23, context 200k)
- Auth: `Authorization: Bearer <9router key>` (same key as `providers.9router.settings.apiKey`)
- Wrapper: `node ~/.config/opencode/skills/jev-decision/scripts/jev-decide.mjs -Preset <name> -State "<state>"` (recommended, ~50ms startup) or pwsh `node ~/.config/opencode/skills/jev-decision/scripts/jev-decide.mjs -Preset <name> -State "<state>"`
- State structure: `Goal: <request> | Files: <git status --short> | Diff: <git diff --stat> | Risks: <known risks>`. Dense, structured facts maximize confidence.
- Pure Q&A / read-only chat: skip Jev entirely.
- State with quotes/newlines/backticks: pipe via stdin to node script, or pass `-StateFile <path>` (CLI quoting breaks otherwise)
## Question schema (verified against live endpoint)
- `choice`: `{ "type": "choice", "instructions": "...", "criteria": { "<opt>": "<what it means>" } }` -> `{ "choice": "<opt>", "probabilities": {...}, "confidence": 0..1 }`Details
- Skill name
jev-decision- Repository
- PanPanFR/oh-my-openkilo
- Path
skills/jev-decision/SKILL.md- License
- MIT
- Repo updated
- 2 November 2026
FAQ
What does the Jev Decision skill do?
Fast structured decisions via 9router System One (Jev jev-1.13). Use for routing, task classification, delegation, review/test/UI gates. Returns typed choice/noul/score with probabilities, not text. Triggers: jev, systemone, triage, route, delegation gate, review gate, test scope.
How do I install the Jev Decision skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add PanPanFR/oh-my-openkilo --skill jev-decision. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Jev Decision popular?
It lives in PanPanFR/oh-my-openkilo, which has 9 GitHub stars and 1 forks.
Related skills
Adaptive
9PanPanFR/oh-my-openkilo
Instructions to make or update an app's UI so that it adapts to different Android devices including phones, tablets, foldables, laptops, desktop, TV, Auto, and XR. It includes how to handle different window sizes, pointing devices (such as mouse) and text entry devices (such as keyboard) using the Compose MediaQuery API, and how to preserve UI, navigation, scroll, and media playback state across configuration changes (such as folding/unfolding a foldable, rotating a device, or resizing a window). It also covers multi-pane layouts using Navigation3 Scenes, adaptive UI components (such as button
Agentmemory
9PanPanFR/oh-my-openkilo
Index for agentmemory internals: how it is wired into a host agent, its architecture and ports, configuration flags, capture hooks, MCP tool surface, and REST fallback. Use when installing or debugging agentmemory itself, when a memory tool name or parameter is unclear, or when capture is not recording. For normal recall and save work, use agentmemory-ops instead.
Agentmemory History
9PanPanFR/oh-my-openkilo
Read past work: resume the last session, recap recent sessions, list agent-linked commits, trace a line back to the session that wrote it, or compact the current conversation for handoff. Use when the user says "where were we", "resume", "recap", "session history", "what did we do", "why is this code here", "who wrote this", or "handoff".
Playwright CLI
9PanPanFR/oh-my-openkilo
Use when automating browser interactions, E2E tests, web scraping, snapshotting, request mocking, or Playwright test generation/debug. Triggers on "open browser", "click button", "fill form", "take screenshot", "run playwright test", "playwright-cli", "@playwright/cli", or tasks needing persistent browser sessions.
Pilot Quality Assurance Pipeline Setup
9TeoSlayer/pilot-skills
Deploy a quality assurance pipeline with 3 agents that automate test generation, execution, and reporting. Use this skill when: 1. User wants to set up an automated QA or testing pipeline 2. User is configuring an agent as part of a test automation workflow 3. User asks about automating test generation, execution, or quality reporting across agents Do NOT use this skill when: - User wants to run a single test suite (use pilot-task-parallel instead) - User wants a one-off alert notification (use pilot-alert instead)
Testing Setup
9PanPanFR/oh-my-openkilo
Analyze and create a testing strategy for Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.