init: edu-content 内容库骨架（L1-L4 四层数据模型 + B类迁移 + lint/CI 工具）

INDEX.json

@@ -0,0 +1,47 @@
+{
+  "generated_at": "2026-08-22",
+  "repo": "edu-content",
+  "model": "L1 source registry (git) + L2 raw (OSS edu-raw/) + L3 structured (git)",
+  "oss": {
+    "bucket": "edu-content-hy",
+    "region": "oss-cn-heyuan",
+    "prefixes": [
+      "edu-raw/",
+      "edu-derived/"
+    ]
+  },
+  "redline": "restricted / internal-only / unknown 数据永不可进 derived，永不可对外产品使用",
+  "sources": {
+    "domains": {
+      "internal": 4,
+      "china": 8,
+      "exams": 4
+    },
+    "n_sources": 16,
+    "license_breakdown": {
+      "internal-only": 4,
+      "official-free": 3,
+      "cc-nc-education": 6,
+      "cc-by": 1,
+      "unknown": 2
+    }
+  },
+  "structured": {
+    "datasets": {
+      "exams/pet/vocab/b1-preliminary-vocab.jsonl": 3164,
+      "exams/pet/questions/cepoc-b1-preliminary.jsonl": 21,
+      "exams/ket/vocab/a2-key-vocab.jsonl": 1738,
+      "exams/ket/questions/cepoc-a2-key.jsonl": 6
+    },
+    "n_records": 4929,
+    "license_breakdown": {
+      "cc-nc-education": 27
+    }
+  },
+  "entrypoints": {
+    "human": "README.md",
+    "machine": "INDEX.json",
+    "license": "LICENSES.md",
+    "conventions": "docs/conventions.md"
+  }
+}