scripts/note-to-blog.py  (collect / convert / state subcommands)

Phase 1          Phase 2         Phase 3            Phase 4              Phase 5
 Collect   ──▶   Evaluate  ──▶   Interact    ──▶   Execute        ──▶   Summary
 (script)        (LLM)          (user)             (Agent Teams)         (report)
                                 ├─ select          ├─ Fast track
                                 ├─ skip            └─ Deep track
                                 └─ assign track

python3 scripts/note-to-blog.py collect \
  --note-repo "~/Library/Mobile Documents/iCloud~md~obsidian/Documents/Note/" \
  --blog-content "repos/bokushi/src/content/" \
  --project-paths \
    "~/.claude/projects/-Users-sueharakyoko-code-nini-dev" \
    "~/.claude/projects/-Users-sueharakyoko-code-nini-dev-repos-bokushi" \
  --history-file "~/.claude/history.jsonl"

[
  {
    "type": "single",
    "path": "Areas/大模型(LLM)/关于后LLM时代的代码Review.md",
    "title": "关于后 LLM 时代的代码 Review 的看法",
    "score": 92,
    "collection": "blog",
    "effort": "小",
    "session_activity": "★★★",
    "duplicate_risk": "none",
    "reason": "结构完整、有真实案例、观点独特"
  },
  {
    "type": "cluster",
    "hub_title": "优雅的哲学",
    "hub_path": "Areas/生活(Life)/优雅的哲学-v2.0.md",
    "related_count": 9,
    "score": 88,
    "collection": "blog",
    "effort": "大",
    "theme_summary": "关于如何优雅地生活的哲学思考，散落在多篇笔记中",
    "reason": "主题深度足够，需要整合多篇笔记"
  }
]

undefined

For cluster entries, show the hub title and related note count.

python3 scripts/note-to-blog.py state skip "<path>" --reason "<reason>" \
  --note-repo "~/Library/Mobile Documents/iCloud~md~obsidian/Documents/Note/"

确认选择：
  Fast track:
    1. 后LLM时代代码Review → blog/
    3. SSH私钥加密 → til/
  Deep track:
    2. 优雅的哲学 (9篇关联) → blog/

开始处理？

总编 (Main Agent)
├── Task Agent 1: 文章 A (fast track)
├── Task Agent 2: 文章 B (fast track)
└── Task Agent 3: 主题簇 C (deep track)

python3 "<absolute-path-to-skill>/scripts/note-to-blog.py" convert "<full-path-to-note>"

{
  "status": "done",
  "note_path": "<relative note path>",
  "draft_path": "<collection>/<slug>.md",
  "description": "<generated description>",
  "issues": ["<any issues found>"],
  "suggestions": ["<improvement suggestions>"]
}

undefined

**Step 3 — Return a result object**:

```json
{
  "status": "done",
  "note_path": "<hub note path>",
  "related_paths": ["<related note paths>"],
  "report": "<full research report markdown>",
  "suggested_collection": "<blog/til/monthly>"
}

python3 scripts/note-to-blog.py state draft "<note_path>" \
  --target "<collection>/<slug>.md" \
  --note-repo "~/Library/Mobile Documents/iCloud~md~obsidian/Documents/Note/"

Fast Track 完成：
  ✓ 后LLM时代代码Review → repos/bokushi/src/content/blog/llm-code-review.md
    - 转换正常，无问题
    - 建议：可补充最新的 AI code review 工具对比
  ✓ SSH私钥加密 → repos/bokushi/src/content/til/ssh-key-encryption.md
    - 发现 1 个 TODO 标记需要手动处理

Deep Track 完成：
  📋 优雅的哲学 (9篇关联)
    - 研究报告已生成
    - 建议大纲：4 部分，来源涵盖 7 篇笔记
    - 下一步？
      a) 按大纲写作（调用 Agent 生成初稿）
      b) 修改大纲
      c) 暂不处理

状态更新：
  drafted: 2 篇
  下次 collect 时这些笔记将不再出现在候选列表中。

草稿均为 hidden: true，需要手动 review 后改为 false 发布。
建议使用 /writing-proofreading 进行审校。

发布后运行 state publish 更新状态：
  python3 scripts/note-to-blog.py state publish "<note_path>" --note-repo "..."