voidlight00/jev-for-claude/jev-judge
Claude Code and agent skill by voidlight00/jev-for-claude
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Run an explicit typed Jev evaluation using a caller-supplied payload.
Install
npx vskill@latest install voidlight00/jev-for-claude/jev-judgeSKILL.md
Prepare or run a Jev judgment for: $ARGUMENTS
- Confirm the state and each question are appropriate to send to an external service.
- Use a minimal explicit JSON payload with
model: "jev-latest"and typednoul,choice, orscorequestions. - Never collect a payload from conversation transcripts, settings, dotenv files, or unrelated repository files.
- Show the payload scope before any network call.
- Run
node "${CLAUDE_PLUGIN_ROOT}/scripts/jev-evaluate.mjs" --allow-network --file <payload>only when the user explicitly authorizes the call andTYPESAFE_API_KEYis already present in the process environment. - Report returned typed answers as probabilistic judgments, not facts.
Never call the API automatically. Do not print the API key or HTTP error bodies.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/jev-judge/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/voidlight00/jev-for-claude/jev-judge)