Paste the JSON an LLM actually returned and the JSON Schema you expected it to follow — see exactly which fields are missing, wrong-typed, or out of range. Supports a documented subset of JSON Schema (same as the JSON Schema → AI Prompt tool) — not full spec compliance, but enough to catch the mistakes models actually make. Runs entirely in your browser.
curl -sS -X POST https://devops.majbase.com/json-schema-validator/api -H "Content-Type: application/json" -d '{"instance":{"name":"Ivan","age":-5},"schema":{"type":"object","properties":{"name":{"type":"string"},"age":{"type":"integer","minimum":0}},"required":["name","age"]}}'Returns {"valid": bool, "errors": [{"path", "message"}, ...]}, or {"error": "..."}.
Want an AI agent (Claude Code, claude.ai, or anything else that supports the Agent Skills format) to use this tool for you on request? Download the skill below and add it:
~/.claude/skills/json-schema-validator/SKILL.md