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

sources/exams/amc-past.yaml

@@ -0,0 +1,21 @@
+sources:
+  - id: amc-past
+    title: AMC 8 历年真题（含答案）
+    publisher: 美国数学协会 (MAA)
+    type: dataset
+    url: https://artofproblemsolving.com/wiki/index.php/AMC_8_Problems_and_Solutions
+    license: unknown
+    license_note: "AMC 真题版权归 MAA，公开传播受限；内部教研参考，禁止再分发/商用。待核查后定级"
+    fetch_method: manual-download
+    status: planned
+    items: []
+  - id: ccf-csp
+    title: CCF CSP-J/S 历年真题
+    publisher: 中国计算机学会 (CCF)
+    type: dataset
+    url: https://www.csp.thusaac.com/
+    license: official-free
+    license_note: "CCF 官方公开，允许教学使用"
+    fetch_method: manual-download
+    status: planned
+    items: []

sources/exams/cambridge-official.yaml

@@ -0,0 +1,45 @@
+sources:
+  - id: cambridge-official
+    title: 剑桥官方 KET/PET 样卷、词表与听力音频
+    publisher: Cambridge Assessment English / UCLES
+    type: dataset
+    url: https://www.cambridgeenglish.org/Images/
+    license: official-free
+    license_note: "官方免费发布，允许教学使用（样卷/词表/听力音频）"
+    fetch_method: manual-download
+    status: fetched
+    fetched_at: "2026-08-21"
+    items:
+      - id: a2-key-vocab
+        title: A2 Key 2020 词汇表 PDF
+        oss_key: edu-raw/exams/ket/vocab/cambridge-official/a2-key-vocabulary-list.pdf
+        sha256: null
+        size: null
+        media_type: application/pdf
+        fetch_date: "2026-08-21"
+        status: planned
+        note: "vocab JSONL (structured/exams/ket/vocab/) 由此清洗；待 oss_sync 上传"
+      - id: b1-preliminary-vocab
+        title: B1 Preliminary 词汇表 PDF
+        oss_key: edu-raw/exams/pet/vocab/cambridge-official/b1-preliminary-vocabulary-list.pdf
+        sha256: null
+        size: null
+        media_type: application/pdf
+        fetch_date: "2026-08-21"
+        status: planned
+      - id: a2-key-listening
+        title: A2 Key 听力音频
+        oss_key: edu-raw/exams/ket/audio/cambridge-official/a2-key-listening.mp3
+        sha256: null
+        size: null
+        media_type: audio/mpeg
+        fetch_date: "2026-08-21"
+        status: planned
+      - id: sample-papers
+        title: 官方样卷包（PDF/MP3/ZIP）
+        oss_key: edu-raw/exams/ket/sample_papers/cambridge-official/
+        sha256: null
+        size: null
+        media_type: application/zip
+        fetch_date: "2026-08-21"
+        status: planned

sources/exams/cepoc.yaml

@@ -0,0 +1,30 @@
+sources:
+  - id: cepoc
+    title: CEPOC 剑桥英语机读完形填空题库（KET/PET/FCE）
+    publisher: Cambridge ALTA, University of Cambridge
+    type: dataset
+    url: https://github.com/CambridgeALTA/cepoc
+    license: cc-nc-education
+    license_note: "研究/教育用途，非商业（见仓库 licence.txt）"
+    fetch_method: git-clone
+    status: fetched
+    fetched_at: "2026-08-21"
+    items:
+      - id: cepoc-ket-json
+        title: KET.json（6套68空）
+        oss_key: edu-raw/exams/ket/questions/cepoc/KET.json
+        sha256: null
+        size: null
+        media_type: application/json
+        fetch_date: "2026-08-21"
+        status: planned
+        note: "latin1 编码；清洗为 qb-1.1 落 structured/exams/ket/questions/cepoc-a2-key.jsonl"
+      - id: cepoc-b1-json
+        title: B1 Preliminary.json（含 FCE 36套360空）
+        oss_key: edu-raw/exams/pet/questions/cepoc/B1-Preliminary.json
+        sha256: null
+        size: null
+        media_type: application/json
+        fetch_date: "2026-08-21"
+        status: planned
+        note: "清洗为 qb-1.1 落 structured/exams/pet/questions/cepoc-b1-preliminary.jsonl"