auto backup 2026-07-02 11:00

skill-workshop/proposals.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposals-manifest.v1","updatedAt":"2026-07-01T23:52:24.428Z","proposals":[{"id":"jellyfin-nfo-builder-20260701-6434352e0d","kind":"create","status":"pending","title":"Create jellyfin-nfo-builder","description":"为剧集整理统一文件名、生成缺失的 Jellyfin .nfo 剧集元数据","skillName":"jellyfin-nfo-builder","skillKey":"jellyfin-nfo-builder","createdAt":"2026-07-01T23:52:24.406Z","updatedAt":"2026-07-01T23:52:24.406Z","scanState":"clean"},{"id":"weekly-report-g5-20260626-7595273f1d","kind":"create","status":"applied","title":"Create weekly-report-g5","description":"维云智造G5周报生成：整理每日工作→多段邮件(纯文本+HTML含签名图)→存入钉邮草稿箱","skillName":"weekly-report-g5","skillKey":"weekly-report-g5","createdAt":"2026-06-26T00:46:22.478Z","updatedAt":"2026-06-26T00:46:35.812Z","scanState":"clean"},{"id":"calibre-cleaner-20260624-0fc374efd7","kind":"update","status":"pending","title":"Update calibre-cleaner","description":"清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除","skillName":"calibre-cleaner","skillKey":"calibre-cleaner","createdAt":"2026-06-24T03:23:27.062Z","updatedAt":"2026-06-24T03:23:27.062Z","scanState":"clean"},{"id":"calibre-cleaner-20260624-cdbeb219a3","kind":"update","status":"applied","title":"Update calibre-cleaner","description":"清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除","skillName":"calibre-cleaner","skillKey":"calibre-cleaner","createdAt":"2026-06-24T03:03:28.166Z","updatedAt":"2026-06-24T03:03:30.915Z","scanState":"clean"},{"id":"calibre-cleaner-20260624-a441798af9","kind":"create","status":"applied","title":"Create calibre-cleaner","description":"清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除","skillName":"calibre-cleaner","skillKey":"calibre-cleaner","createdAt":"2026-06-24T02:29:02.278Z","updatedAt":"2026-06-24T02:29:27.227Z","scanState":"clean"},{"id":"calibre-title-cleaner-20260624-3760b64e8b","kind":"create","status":"applied","title":"Create calibre-title-cleaner","description":"清洗 Calibre 书库中损坏的 txt 文档书名（HTML标签/长文本/乱码/路径超限修复）","skillName":"calibre-title-cleaner","skillKey":"calibre-title-cleaner","createdAt":"2026-06-24T01:10:56.296Z","updatedAt":"2026-06-24T01:13:39.670Z","scanState":"clean"},{"id":"dianping-review-20260611-d402abec10","kind":"create","status":"pending","title":"Create dianping-review","description":"通过大众点评搜索查询餐厅、老店、美食推荐和评论","skillName":"dianping-review","skillKey":"dianping-review","createdAt":"2026-06-11T23:50:15.731Z","updatedAt":"2026-06-11T23:50:15.731Z","scanState":"clean"}]}

skill-workshop/proposals/calibre-cleaner-20260624-0fc374efd7/PROPOSAL.md

@@ -0,0 +1,451 @@
+---
+name: "calibre-cleaner"
+description: "清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除"
+status: proposal
+version: "v1"
+date: "2026-06-24T03:23:27.062Z"
+---
+
+# Calibre 书库清洗 Skill
+
+## 概述
+
+Calibre 书库整理三件套：
+
+1. **书名清洗** —— 修复从 txt 导入产生的 HTML 标签/长文本/乱码书名，截取前 20 个中文字符，移除网站链接
+2. **作者提取** —— 从书名或原始文件名 `data.name` 中自动提取作者名（匹配 `作者：xxx`、`-xxx`、`BY xxx` 等格式）
+3. **脏数据清理** —— 检测并删除内容损坏的 txt（中文 < 10%）、小于 10KB 的垃圾文件、Python 列表格式垃圾标题
+
+## 前置条件
+
+- 书库路径：`/home/yangxuan/calibre/books`
+- 元数据文件：`/home/yangxuan/calibre/books/metadata.db`
+- 运行前须停止其他 Calibre 进程（桌面版、Docker Calibre-Web）
+- 运行前 **必须备份** `metadata.db`
+
+---
+
+## 一、书名清洗 & 作者提取
+
+### `shorten(s, max_bytes=120)`
+
+将字符串截断到指定字节数，避免因 UTF-8 中文字符跨字节而损坏。
+
+```python
+def shorten(s, max_bytes=120):
+    encoded = s.encode('utf-8')
+    if len(encoded) <= max_bytes:
+        return s
+    try:
+        return encoded[:max_bytes].decode('utf-8')
+    except:
+        return encoded[:max_bytes-3].decode('utf-8', errors='ignore')
+```
+
+### `clean_title(title)`
+
+```python
+def clean_title(title):
+    t = title
+    # 移除 HTML 标签
+    t = re.sub(r'<[^>]+>', '', t)
+    # 替换 _BR_ / _BR 标记
+    t = re.sub(r'_BR_', ' ', t, flags=re.IGNORECASE)
+    t = re.sub(r'_BR(?![a-zA-Z])', ' ', t)
+    # 移除 _fontxxx_ / _imgxxx_ 标记
+    t = re.sub(r'_font[^_]*_', '', t)
+    t = re.sub(r'_img[^_]*_', '', t)
+    # 移除网站链接
+    t = re.sub(r'[\(（]www\.[^)）]+[\)）]', '', t)
+    t = re.sub(r'^[a-zA-Z0-9.-]+\.com@', '', t)
+    t = re.sub(r'[-–—][a-zA-Z0-9.-]+\.com$', '', t)
+    t = re.sub(r'【[^】]*?(?:下载|网站|书城|声明|提供)[^】]*】', '', t)
+    t = re.sub(r'[：:].*?(?:本文由|本电子书).*$', '', t)
+    t = re.sub(r'[/／]\s*www\.[^\s]+.*$', '', t)
+    t = re.sub(r'[，,。]?https?://[^\s\)）\]]+', '', t)
+    # 移除声明文字当书名
+    t = re.sub(r'^内容简介[】】]?', '', t)
+    # 移除作者/翻译标记（批量清洗时用）
+    t = re.sub(r'[　\s]*?(?:作者|翻译|原?作者)[：:].*$', '', t, flags=re.DOTALL)
+    # 移除 Unknown/未知 尾巴
+    t = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', t)
+    # 合并多余空格
+    t = re.sub(r'\s+', ' ', t).strip()
+    # 截取前 20 个中文字符（保留非中文直到第 20 个中文出现）
+    chinese_count = 0
+    pos = 0
+    for i, c in enumerate(t):
+        if '\u4e00' <= c <= '\u9fff':
+            chinese_count += 1
+            if chinese_count == 20:
+                pos = i + 1
+                break
+    if chinese_count > 20:
+        t = t[:pos]
+    # 超长截短
+    if len(t) > 100:
+        m = re.search(r'[\u4e00-\u9fff]{2,}', t)
+        if m:
+            t = t[m.start():]
+        t = t[:60].rstrip('，。；：、！？…\ufffd\'"').rstrip('.,;:!?\'').strip()
+    # 移除控制字符
+    t = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', t)
+    return shorten(t, 100).strip() or 'Unknown'
+```
+
+### 作者提取规则（从文件中同时匹配 title 和 data.name）
+
+优先从 `data.name`（原始文件名）提取，更准确：
+
+```python
+EXCLUDE_AUTHORS = {'正文', '内容简介', ''}
+
+def extract_author_from_name(file_name):
+    """从 data.name（原始文件名）提取作者"""
+    name = file_name
+    # 去掉尾巴
+    name = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', name)
+    # 匹配作者：xxx
+    m = re.search(r'作者[：:]\s*([^\s_）\)《\[【\]】\-,]+)', name)
+    if m:
+        candidate = m.group(1).strip()
+        if candidate not in EXCLUDE_AUTHORS and len(candidate) < 30:
+            return candidate
+    # 匹配翻译：xxx
+    m = re.search(r'翻译[：:]\s*([^\s_）\)《\[【\]】\-,]+)', name)
+    if m:
+        candidate = m.group(1).strip()
+        if len(candidate) < 20:
+            return candidate
+    # 匹配原作者：xxx
+    m = re.search(r'原?作者[：:]\s*([^\s_）\)《\[【\]】\-,]+)', name)
+    if m:
+        candidate = m.group(1).strip()
+        if len(candidate) < 30:
+            return candidate
+    return None
+
+def extract_author_from_title(title):
+    """从 title 提取作者（降级方案，仅在 data.name 无用时）"""
+    m = re.search(r'作者[：:]\s*([^\s,，、\)）《\[]+)', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS and not re.match(r'^第\d+[章节]', name):
+            return name
+    m = re.search(r'翻译[：:]\s*([^\s,，、\)）《\[]+)', title)
+    if m:
+        return m.group(1).strip()
+    m = re.search(r'\b[Bb][Yy]\s+([^\s,，、\)）《\[]+)', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS:
+            return name
+    m = re.search(r'-([^-()【】\[\]{}《》\s]{2,30})$', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS and not re.match(r'^\d+', name):
+            return name
+    m = re.search(r'&([^&()【】\[\]\s]{2,30})$', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS:
+            return name
+    return None
+```
+
+### 坏书检测条件
+
+```python
+is_bad = (
+    len(title) > 100 or
+    '<img' in title or '<BR' in title or '<font' in title or
+    '\ufffd' in title or
+    len(title.encode('utf-8')) > 150
+)
+```
+
+---
+
+## 二、脏数据清理
+
+### 2.1 检测条件
+
+扫描书库中所有 TXT 文件，读取前 20KB 检测中文比例：
+
+- **内容损坏/二进制垃圾**：中文比例 < 10%（标记为待删除）
+- **小文件垃圾**：`uncompressed_size < 10240`（10KB 以下）
+- **垃圾格式标题**：Python 列表格式（含 `'xxx', 'R-18'` 单引号列表）、转义字符（`\n`、`\u3000`、`id=`）、HTML 实体（`raquo;`、`laquo;`）
+
+```python
+def is_garbage_format_title(title):
+    """检测标题是否为垃圾格式"""
+    import re
+    if re.search(r"'.*',\s*'R-18'", title):
+        return True
+    if re.search(r'[\\]u[0-9a-fA-F]{4}', title):
+        return True
+    if re.search(r'id=|pid=', title):
+        return True
+    if 'raquo;' in title or 'laquo;' in title:
+        return True
+    if '【内容简介】' in title or '内容简介】' in title:
+        return True
+    return False
+
+def is_dirty_content(full_path):
+    """检测文件内容是否为垃圾"""
+    if not os.path.exists(full_path):
+        return True  # 文件丢失也算脏
+    with open(full_path, 'rb') as f:
+        raw = f.read(20480)
+    text = raw.decode('utf-8', errors='replace')
+    chinese = sum(1 for c in text if '\u4e00' <= c <= '\u9fff')
+    ratio = chinese / len(text) if len(text) > 0 else 0
+    return ratio < 0.10
+```
+
+### 2.2 批量删除（通过 SQLite 直写）
+
+停掉 calibre 进程后，通过 SQLite 删除记录并清理文件系统：
+
+```sql
+DELETE FROM data WHERE book = ?
+DELETE FROM books_authors_link WHERE book = ?
+DELETE FROM books_languages_link WHERE book = ?
+DELETE FROM books_publishers_link WHERE book = ?
+DELETE FROM books_series_link WHERE book = ?
+DELETE FROM books_tags_link WHERE book = ?
+DELETE FROM comments WHERE book = ?
+DELETE FROM identifiers WHERE book = ?
+DELETE FROM books WHERE id = ?
+```
+
+同时删除对应目录：`shutil.rmtree(os.path.join('/home/yangxuan/calibre/books', bpath))`
+
+### 2.3 完整删除脚本
+
+```python
+import sqlite3, os, shutil
+
+db_path = '/home/yangxuan/calibre/books/metadata.db'
+conn = sqlite3.connect(db_path)
+c = conn.cursor()
+
+c.execute('''
+    SELECT b.id, b.title, b.path, d.name, d.uncompressed_size
+    FROM books b 
+    JOIN data d ON d.book = b.id 
+    WHERE d.format = 'TXT'
+''')
+rows = c.fetchall()
+
+to_delete = []
+
+for bid, title, bpath, fname, size in rows:
+    full_path = os.path.join('/home/yangxuan/calibre/books', bpath, fname + '.txt')
+    
+    # 条件0：垃圾格式标题（Python列表、转义字符等）
+    if is_garbage_format_title(title):
+        to_delete.append((bid, bpath))
+        continue
+    
+    # 条件1：小文件垃圾
+    if size < 10240:
+        to_delete.append((bid, bpath))
+        continue
+    
+    if not os.path.exists(full_path):
+        continue
+    
+    # 条件2：内容损坏（中文 < 10%）
+    if is_dirty_content(full_path):
+        to_delete.append((bid, bpath))
+
+print(f"待删除: {len(to_delete)}", flush=True)
+for bid, bpath in to_delete:
+    for table in ['data', 'books_authors_link', 'books_languages_link',
+                  'books_publishers_link', 'books_series_link', 'books_tags_link',
+                  'comments', 'identifiers']:
+        c.execute(f'DELETE FROM {table} WHERE book=?', (bid,))
+    c.execute('DELETE FROM books WHERE id=?', (bid,))
+    full_dir = os.path.join('/home/yangxuan/calibre/books', bpath)
+    if os.path.exists(full_dir):
+        shutil.rmtree(full_dir)
+
+conn.commit()
+conn.close()
+print(f"完成，删除: {len(to_delete)}", flush=True)
+```
+
+---
+
+## 三、书名批量清洗（作者标记去除 + 前 20 中文截取）
+
+对于书名中含 `作者：xxx`、`翻译：xxx` 标记但作者字段已有值的书，使用此脚本批量清洗：
+
+```python
+import sqlite3, re
+
+db_path = '/home/yangxuan/calibre/books/metadata.db'
+conn = sqlite3.connect(db_path)
+c = conn.cursor()
+
+c.execute('''
+    SELECT b.id, b.title, a.name as author_name, d.name as file_name
+    FROM books b
+    JOIN data d ON d.book = b.id AND d.format = 'TXT'
+    JOIN books_authors_link l ON b.id = l.book
+    JOIN authors a ON l.author = a.id
+    WHERE (b.title LIKE '%作者：%' OR b.title LIKE '%作者:%' OR b.title LIKE '%翻译：%' OR b.title LIKE '%翻译:%')
+      AND a.name NOT IN ('未知', 'Unknown')
+    ORDER BY b.id
+''')
+rows = c.fetchall()
+
+for bid, title, author_name, file_name in rows:
+    # 1. 从 data.name 提取作者并更新 author 字段（如不同）
+    name_clean = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', file_name)
+    m = re.search(r'[　\s]*?(?:作者|翻译|原?作者)[：:]\s*([^\s_）\)《\[【\]】\-,]+)', name_clean)
+    if m:
+        extracted = m.group(1).strip()
+        if extracted and extracted != author_name and len(extracted) < 30:
+            cur = conn.cursor()
+            cur.execute("SELECT id FROM authors WHERE name=?", (extracted,))
+            ar = cur.fetchone()
+            if ar:
+                aid = ar[0]
+            else:
+                cur.execute("INSERT INTO authors (name, sort) VALUES (?, ?)", (extracted, extracted.replace(',', '').strip()))
+                aid = cur.lastrowid
+            cur.execute("UPDATE books_authors_link SET author=? WHERE book=?", (aid, bid))
+            cur.close()
+    
+    # 2. 裁剪书名：去标记 + 前 20 中文
+    clean_title = re.sub(r'[　\s]*?(?:作者|翻译|原?作者)[：:].*$', '', file_name, flags=re.DOTALL)
+    clean_title = re.sub(r'\s*-\s*(Unknown|未知)\s*$', '', clean_title).strip()
+    
+    if clean_title:
+        count = 0
+        pos = 0
+        for i, ch in enumerate(clean_title):
+            if '\u4e00' <= ch <= '\u9fff':
+                count += 1
+                if count == 20:
+                    pos = i + 1
+                    break
+        if count > 20:
+            clean_title = clean_title[:pos]
+        
+        if clean_title != title:
+            c.execute("UPDATE books SET title=? WHERE id=?", (clean_title, bid))
+
+conn.commit()
+conn.close()
+```
+
+---
+
+## 四、常用查询
+
+### 4.1 查看 XX 作者的书
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT b.id, b.title
+FROM books b JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+WHERE a.name = 'Unknown'
+LIMIT 20;
+"
+```
+
+### 4.2 统计作者分布
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT a.name, COUNT(*) as cnt
+FROM books b JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+GROUP BY a.name ORDER BY cnt DESC LIMIT 20;
+"
+```
+
+### 4.3 书名异常检测
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT id, title FROM books WHERE
+  title LIKE '%作者%' OR title LIKE '%翻译%' OR
+  title LIKE '%.com%' OR title LIKE '%http%' OR
+  title LIKE '%内容简介%' OR
+  LENGTH(title) > 80;
+"
+```
+
+### 4.4 书库统计
+
+```bash
+python3 -c "
+import sqlite3
+conn = sqlite3.connect('/home/yangxuan/calibre/books/metadata.db')
+c = conn.cursor()
+c.execute('SELECT COUNT(*) FROM books')
+print(f'总书籍: {c.fetchone()[0]}')
+c.execute('SELECT COUNT(*) FROM data WHERE format=\"TXT\"')
+print(f'TXT 文件: {c.fetchone()[0]}')
+conn.close()
+"
+```
+
+---
+
+## 五、操作流程（推荐顺序）
+
+```bash
+cd /home/yangxuan/calibre
+
+# 1. 停服务 + 备份
+docker compose down
+cp books/metadata.db books/metadata.db.backup.$(date +%Y%m%d)
+killall calibre 2>/dev/null
+
+# 2. 脏数据清理（内容损坏 + 小文件 + 垃圾格式标题）
+python3 /path/to/clean_dirty_data.py
+
+# 3. 书名清洗 & 作者提取（含 data.name 级别提取）
+calibre-debug /path/to/fix_titles.py
+
+# 4. 检查是否有遗漏的异常书籍
+sqlite3 books/metadata.db \"SELECT id, title FROM books WHERE title LIKE '%作者%' OR title LIKE '%翻译%' OR title LIKE '%.com%';\" | head -10
+
+# 5. 重启
+docker compose up -d
+```
+
+---
+
+## 六、已知问题
+
+### `set_metadata` 报 `Errno 36 文件名过长`
+
+当 `author_sort` 字段超 80 字节时，Calibre 路径会触及 ext4 255 字节限制。先清理极长作者名：
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+UPDATE authors SET name='Unknown' WHERE LENGTH(name) > 30;
+"
+```
+
+### WSL `/mnt/f` 删除 NTFS 文件权限不够
+
+WSL 的 drvfs 默认不带 metadata 选项，`sudo rm`、`os.remove`、`cmd.exe /c del` 均无法删除 NTFS 文件。不要在 WSL 下尝试跨分区删除操作，直接让 Windows 侧（文件资源管理器/PowerShell）操作。
+
+### 书名长度截取规则
+
+`title` 字段清洗后最多保留 20 个中文字符。计数规则：只计 Unicode 范围的 `\u4e00-\u9fff` 中文字符，保留第 20 个中文之前的所有字符（含非中文）。如书名不足 20 个中文则全保留。
+
+### `title` vs `data.name` 区别
+
+- `books.title`：Calibre 界面显示的书名（清洗后的）
+- `data.name`：导入时的原始文件名（不含 `.txt`）
+- 作者提取优先使用 `data.name`，其文件名保留原始信息、更可靠

skill-workshop/proposals/calibre-cleaner-20260624-0fc374efd7/proposal.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposal.v1","id":"calibre-cleaner-20260624-0fc374efd7","kind":"update","status":"pending","title":"Update calibre-cleaner","description":"清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除","createdAt":"2026-06-24T03:23:27.062Z","updatedAt":"2026-06-24T03:23:27.062Z","createdBy":"skill-workshop","origin":{"agentId":"storage","sessionKey":"agent:storage:main","runId":"62debb6e-62f3-41ff-ab3a-0d2fdc63ff4d","messageId":"62debb6e-62f3-41ff-ab3a-0d2fdc63ff4d"},"proposedVersion":"v1","draftFile":"PROPOSAL.md","draftHash":"9f8e90cfa549288742db7af62bc54db12a9650208104a2efcba6c7a4fb2b4a49","target":{"skillName":"calibre-cleaner","skillKey":"calibre-cleaner","skillDir":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-cleaner","skillFile":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-cleaner/SKILL.md","source":"openclaw-workspace","currentContentHash":"929fdbb7a4de265565ca75bdf3692d33623a634f4991c21a51e5f829b0e9b2c0"},"scan":{"state":"clean","scannedAt":"2026-06-24T03:23:27.063Z","critical":0,"warn":0,"info":0,"findings":[]}}

skill-workshop/proposals/calibre-cleaner-20260624-a441798af9/PROPOSAL.md

@@ -0,0 +1,222 @@
+---
+name: "calibre-cleaner"
+description: "清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除"
+status: proposal
+version: "v1"
+date: "2026-06-24T02:29:02.278Z"
+---
+
+# Calibre 书库清洗 Skill
+
+## 概述
+
+Calibre 书库整理三件套：
+
+1. **书名清洗** —— 修复从 txt 导入产生的 HTML 标签/长文本/乱码书名
+2. **作者提取** —— 从书名中自动提取作者名（匹配 `作者：xxx`、`-xxx`、`BY xxx` 等格式）
+3. **脏数据清理** —— 检测并删除编码损坏的 txt、小于 10KB 的垃圾文件
+
+## 前置条件
+
+- 书库路径：`/home/yangxuan/calibre/books`
+- 元数据文件：`/home/yangxuan/calibre/books/metadata.db`
+- 运行前须停止其他 Calibre 进程（桌面版、Docker Calibre-Web）
+- 运行前 **必须备份** `metadata.db`
+
+---
+
+## 一、书名清洗 & 作者提取
+
+（详见 skill 原内容，此处保留完整清洗逻辑）
+
+---
+
+## 二、脏数据清理
+
+### 2.1 检测编码损坏的 TXT
+
+检测条件：中文比例 < 10% 且含有乱码字符（`Ŀ¼ĴƿȿɿʼÈÌÒÙ（` 等 UTF-8 编码错误字）
+
+```python
+import sqlite3, os
+
+bad_char_set = set('Ŀ¼ĴƿȿɿʼÈÌÒÙ（')
+bad_ids = []
+
+for bid, title, bpath, fname in rows:
+    full_path = os.path.join('/home/yangxuan/calibre/books', bpath, fname + '.txt')
+    if not os.path.exists(full_path):
+        continue
+    with open(full_path, 'rb') as f:
+        raw = f.read(20480)
+    text = raw.decode('utf-8', errors='replace')
+    chinese = sum(1 for c in text if '\u4e00' <= c <= '\u9fff')
+    total = len(text)
+    ratio = chinese / total if total > 0 else 0
+    has_bad = any(c in bad_char_set for c in text)
+    if ratio < 0.10 and has_bad:
+        bad_ids.append(bid)
+```
+
+### 2.2 检测小文件
+
+```python
+c.execute('''
+    SELECT b.id, b.path FROM books b 
+    JOIN data d ON d.book = b.id 
+    WHERE d.format = 'TXT' AND d.uncompressed_size < 10240
+''')
+```
+
+### 2.3 批量删除（通过 SQLite 直写）
+
+停掉 calibre 进程后，通过 SQLite 删除记录并清理文件系统：
+
+```sql
+DELETE FROM data WHERE book = ?
+DELETE FROM books_authors_link WHERE book = ?
+DELETE FROM books_languages_link WHERE book = ?
+DELETE FROM books_publishers_link WHERE book = ?
+DELETE FROM books_series_link WHERE book = ?
+DELETE FROM books_tags_link WHERE book = ?
+DELETE FROM comments WHERE book = ?
+DELETE FROM identifiers WHERE book = ?
+DELETE FROM books WHERE id = ?
+```
+
+同时删除对应目录：`shutil.rmtree(os.path.join('/home/yangxuan/calibre/books', bpath))`
+
+### 2.4 完整删除脚本
+
+```python
+import sqlite3, os, shutil
+
+db_path = '/home/yangxuan/calibre/books/metadata.db'
+conn = sqlite3.connect(db_path)
+c = conn.cursor()
+
+c.execute('''
+    SELECT b.id, b.title, b.path, d.name, d.uncompressed_size
+    FROM books b 
+    JOIN data d ON d.book = b.id 
+    WHERE d.format = 'TXT'
+''')
+rows = c.fetchall()
+
+bad_char_set = set('Ŀ¼ĴƿȿɿʼÈÌÒÙ（')
+to_delete = []
+
+for bid, title, bpath, fname, size in rows:
+    full_path = os.path.join('/home/yangxuan/calibre/books', bpath, fname + '.txt')
+    if not os.path.exists(full_path):
+        continue
+    with open(full_path, 'rb') as f:
+        raw = f.read(20480)
+    text = raw.decode('utf-8', errors='replace')
+    chinese = sum(1 for c in text if '\u4e00' <= c <= '\u9fff')
+    ratio = chinese / len(text) if len(text) > 0 else 0
+    has_bad = any(c in bad_char_set for c in text)
+    if (ratio < 0.10 and has_bad) or size < 10240:
+        to_delete.append((bid, bpath))
+
+print(f"待删除: {len(to_delete)}")
+for bid, bpath in to_delete:
+    c.execute('DELETE FROM data WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_authors_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_languages_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_publishers_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_series_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_tags_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM comments WHERE book=?', (bid,))
+    c.execute('DELETE FROM identifiers WHERE book=?', (bid,))
+    c.execute('DELETE FROM books WHERE id=?', (bid,))
+    full_dir = os.path.join('/home/yangxuan/calibre/books', bpath)
+    if os.path.exists(full_dir):
+        shutil.rmtree(full_dir)
+
+conn.commit()
+conn.close()
+print(f"完成，删除: {len(to_delete)}")
+```
+
+---
+
+## 三、常用操作
+
+### 3.1 查看 XX 作者的书
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT b.id, b.title
+FROM books b JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+WHERE a.name = 'Unknown'
+LIMIT 20;
+"
+```
+
+### 3.2 统计作者分布
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT a.name, COUNT(*) as cnt
+FROM books b JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+GROUP BY a.name ORDER BY cnt DESC LIMIT 20;
+"
+```
+
+### 3.3 书库统计
+
+```bash
+python3 -c "
+import sqlite3
+conn = sqlite3.connect('/home/yangxuan/calibre/books/metadata.db')
+c = conn.cursor()
+c.execute('SELECT COUNT(*) FROM books')
+print(f'总书籍: {c.fetchone()[0]}')
+c.execute('SELECT COUNT(*) FROM data WHERE format=\"TXT\"')
+print(f'TXT 文件: {c.fetchone()[0]}')
+conn.close()
+"
+```
+
+---
+
+## 四、操作流程（推荐顺序）
+
+```bash
+cd /home/yangxuan/calibre
+
+# 1. 停服务 + 备份
+docker compose down
+cp books/metadata.db books/metadata.db.backup.$(date +%Y%m%d)
+killall calibre 2>/dev/null
+
+# 2. 脏数据清理（编码损坏 + 小文件）
+python3 /path/to/clean_dirty_data.py
+
+# 3. 书名清洗 & 作者提取
+calibre-debug /path/to/fix_titles.py
+
+# 4. 重启
+docker compose up -d
+```
+
+---
+
+## 五、已知问题
+
+### `set_metadata` 报 `Errno 36 文件名过长`
+
+当 `author_sort` 字段超 80 字节时，Calibre 路径会触及 ext4 255 字节限制。先清理极长作者名：
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+UPDATE authors SET name='Unknown' WHERE LENGTH(name) > 30;
+"
+```
+
+### WSL `/mnt/f` 删除 NTFS 文件权限不够
+
+WSL 的 drvfs 默认不带 metadata 选项，`sudo rm`、`os.remove`、`cmd.exe /c del` 均无法删除 NTFS 文件。不要在 WSL 下尝试跨分区删除操作，直接让 Windows 侧（文件资源管理器/PowerShell）操作。

skill-workshop/proposals/calibre-cleaner-20260624-a441798af9/proposal.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposal.v1","id":"calibre-cleaner-20260624-a441798af9","kind":"create","status":"applied","title":"Create calibre-cleaner","description":"清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除","createdAt":"2026-06-24T02:29:02.278Z","updatedAt":"2026-06-24T02:29:27.227Z","createdBy":"skill-workshop","origin":{"agentId":"storage","sessionKey":"agent:storage:main","runId":"6e4a8a08-2c78-4b57-866f-c8377d65f96c","messageId":"6e4a8a08-2c78-4b57-866f-c8377d65f96c"},"proposedVersion":"v1","draftFile":"PROPOSAL.md","draftHash":"15703b0a633a8d2adfce44b7b6623d42f0a25778e39c1436b002a42da67c974e","target":{"skillName":"calibre-cleaner","skillKey":"calibre-cleaner","skillDir":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-cleaner","skillFile":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-cleaner/SKILL.md","source":"openclaw-workspace"},"scan":{"state":"clean","scannedAt":"2026-06-24T02:29:27.216Z","critical":0,"warn":0,"info":0,"findings":[]},"appliedAt":"2026-06-24T02:29:27.227Z"}

skill-workshop/proposals/calibre-cleaner-20260624-a441798af9/rollback.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.rollback.v1","proposalId":"calibre-cleaner-20260624-a441798af9","writtenAt":"2026-06-24T02:29:27.217Z","targetSkillFile":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-cleaner/SKILL.md","action":"create"}

skill-workshop/proposals/calibre-cleaner-20260624-cdbeb219a3/PROPOSAL.md

@@ -0,0 +1,303 @@
+---
+name: "calibre-cleaner"
+description: "清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除"
+status: proposal
+version: "v1"
+date: "2026-06-24T03:03:28.166Z"
+---
+
+# Calibre 书库清洗 Skill
+
+## 概述
+
+Calibre 书库整理三件套：
+
+1. **书名清洗** —— 修复从 txt 导入产生的 HTML 标签/长文本/乱码书名
+2. **作者提取** —— 从书名中自动提取作者名（匹配 `作者：xxx`、`-xxx`、`BY xxx` 等格式）
+3. **脏数据清理** —— 检测并删除内容损坏的 txt（中文 < 10%）以及小于 10KB 的垃圾文件
+
+## 前置条件
+
+- 书库路径：`/home/yangxuan/calibre/books`
+- 元数据文件：`/home/yangxuan/calibre/books/metadata.db`
+- 运行前须停止其他 Calibre 进程（桌面版、Docker Calibre-Web）
+- 运行前 **必须备份** `metadata.db`
+
+---
+
+## 一、书名清洗 & 作者提取
+
+### `shorten(s, max_bytes=120)`
+
+将字符串截断到指定字节数，避免因 UTF-8 中文字符跨字节而损坏。
+
+```python
+def shorten(s, max_bytes=120):
+    encoded = s.encode('utf-8')
+    if len(encoded) <= max_bytes:
+        return s
+    try:
+        return encoded[:max_bytes].decode('utf-8')
+    except:
+        return encoded[:max_bytes-3].decode('utf-8', errors='ignore')
+```
+
+### `clean_title(title)`
+
+```python
+def clean_title(title):
+    t = title
+    # 移除 HTML 标签
+    t = re.sub(r'<[^>]+>', '', t)
+    # 替换 _BR_ / _BR 标记
+    t = re.sub(r'_BR_', ' ', t, flags=re.IGNORECASE)
+    t = re.sub(r'_BR(?![a-zA-Z])', ' ', t)
+    # 移除 _fontxxx_ / _imgxxx_ 标记
+    t = re.sub(r'_font[^_]*_', '', t)
+    t = re.sub(r'_img[^_]*_', '', t)
+    # 合并多余空格
+    t = re.sub(r'\s+', ' ', t).strip()
+    # 超长截短
+    if len(t) > 100:
+        m = re.search(r'[\u4e00-\u9fff]{2,}', t)
+        if m:
+            t = t[m.start():]
+        t = t[:60].rstrip('，。；：、！？…\ufffd\'"').rstrip('.,;:!?\'').strip()
+    # 移除控制字符
+    t = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', t)
+    return shorten(t, 100).strip() or 'Unknown'
+```
+
+### 作者提取规则（从书名中提取）
+
+格式 | 示例 | 正则
+---|---|---
+`作者：xxx`（中文冒号） | `...作者：镜欲` | `作者[：:]\s*([^\s,，、\)）]+)`
+`作者:xxx`（英文冒号） | `...作者:镜欲` | 同上
+`-xxx`（英文 dash 结尾） | `善良的美艳妈妈-糠麸` | `-([^-()【】\[\]]+)$`
+`翻译：xxx` | `...翻译：kkmanlg` | `翻译[：:]\s*([^\s,，、\)）]+)`
+`BY xxx`（英文 BY） | `...BY狱厨` | `\b[Bb][Yy]\s+([^\s,，、\)）]+)`
+`&xxx`（and 符结尾） | `...&axenic` | `&([^&()【】\[\] ]+)$`
+
+提取策略：先匹配 `作者：` → `-xxx` → `翻译：` → `BY` → `&xxx`。排除项：`正文`、`内容简介`、`第\\d+[章节]`。
+
+```python
+EXCLUDE_AUTHORS = {'正文', '内容简介', ''}
+
+def extract_author_from_title(title):
+    m = re.search(r'作者[：:]\s*([^\s,，、\)）《\[]+)', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS and not re.match(r'^第\d+[章节]', name):
+            return name
+    m = re.search(r'翻译[：:]\s*([^\s,，、\)）《\[]+)', title)
+    if m:
+        return m.group(1).strip()
+    m = re.search(r'\b[Bb][Yy]\s+([^\s,，、\)）《\[]+)', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS:
+            return name
+    m = re.search(r'-([^-()【】\[\]{}《》\s]{2,30})$', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS and not re.match(r'^\d+', name):
+            return name
+    m = re.search(r'&([^&()【】\[\]\s]{2,30})$', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS:
+            return name
+    return None
+```
+
+### 坏书检测条件
+
+```python
+is_bad = (
+    len(title) > 100 or
+    '<img' in title or '<BR' in title or '<font' in title or
+    '\ufffd' in title or
+    len(title.encode('utf-8')) > 150
+)
+```
+
+---
+
+## 二、脏数据清理
+
+### 2.1 检测条件
+
+扫描书库中所有 TXT 文件，读取前 20KB 检测中文比例：
+
+- **内容损坏/二进制垃圾**：中文比例 < 10%（标记为待删除）
+- **小文件垃圾**：`uncompressed_size < 10240`（10KB 以下）
+
+```python
+with open(full_path, 'rb') as f:
+    raw = f.read(20480)
+text = raw.decode('utf-8', errors='replace')
+chinese = sum(1 for c in text if '\u4e00' <= c <= '\u9fff')
+ratio = chinese / len(text) if len(text) > 0 else 0
+
+if ratio < 0.10:   # 内容损坏，删除
+if size < 10240:   # 小文件垃圾，删除
+```
+
+### 2.2 批量删除（通过 SQLite 直写）
+
+停掉 calibre 进程后，通过 SQLite 删除记录并清理文件系统：
+
+```sql
+DELETE FROM data WHERE book = ?
+DELETE FROM books_authors_link WHERE book = ?
+DELETE FROM books_languages_link WHERE book = ?
+DELETE FROM books_publishers_link WHERE book = ?
+DELETE FROM books_series_link WHERE book = ?
+DELETE FROM books_tags_link WHERE book = ?
+DELETE FROM comments WHERE book = ?
+DELETE FROM identifiers WHERE book = ?
+DELETE FROM books WHERE id = ?
+```
+
+同时删除对应目录：`shutil.rmtree(os.path.join('/home/yangxuan/calibre/books', bpath))`
+
+### 2.3 完整删除脚本
+
+```python
+import sqlite3, os, shutil
+
+db_path = '/home/yangxuan/calibre/books/metadata.db'
+conn = sqlite3.connect(db_path)
+c = conn.cursor()
+
+c.execute('''
+    SELECT b.id, b.title, b.path, d.name, d.uncompressed_size
+    FROM books b 
+    JOIN data d ON d.book = b.id 
+    WHERE d.format = 'TXT'
+''')
+rows = c.fetchall()
+
+to_delete = []
+
+for bid, title, bpath, fname, size in rows:
+    full_path = os.path.join('/home/yangxuan/calibre/books', bpath, fname + '.txt')
+    if not os.path.exists(full_path):
+        continue
+    
+    # 条件1：小文件垃圾
+    if size < 10240:
+        to_delete.append((bid, bpath))
+        continue
+    
+    # 条件2：内容损坏（中文 < 10%）
+    with open(full_path, 'rb') as f:
+        raw = f.read(20480)
+    text = raw.decode('utf-8', errors='replace')
+    chinese = sum(1 for c in text if '\u4e00' <= c <= '\u9fff')
+    ratio = chinese / len(text) if len(text) > 0 else 0
+    if ratio < 0.10:
+        to_delete.append((bid, bpath))
+
+print(f"待删除: {len(to_delete)}", flush=True)
+for bid, bpath in to_delete:
+    c.execute('DELETE FROM data WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_authors_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_languages_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_publishers_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_series_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM books_tags_link WHERE book=?', (bid,))
+    c.execute('DELETE FROM comments WHERE book=?', (bid,))
+    c.execute('DELETE FROM identifiers WHERE book=?', (bid,))
+    c.execute('DELETE FROM books WHERE id=?', (bid,))
+    full_dir = os.path.join('/home/yangxuan/calibre/books', bpath)
+    if os.path.exists(full_dir):
+        shutil.rmtree(full_dir)
+
+conn.commit()
+conn.close()
+print(f"完成，删除: {len(to_delete)}", flush=True)
+```
+
+---
+
+## 三、常用操作
+
+### 3.1 查看 XX 作者的书
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT b.id, b.title
+FROM books b JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+WHERE a.name = 'Unknown'
+LIMIT 20;
+"
+```
+
+### 3.2 统计作者分布
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT a.name, COUNT(*) as cnt
+FROM books b JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+GROUP BY a.name ORDER BY cnt DESC LIMIT 20;
+"
+```
+
+### 3.3 书库统计
+
+```bash
+python3 -c "
+import sqlite3
+conn = sqlite3.connect('/home/yangxuan/calibre/books/metadata.db')
+c = conn.cursor()
+c.execute('SELECT COUNT(*) FROM books')
+print(f'总书籍: {c.fetchone()[0]}')
+c.execute('SELECT COUNT(*) FROM data WHERE format=\"TXT\"')
+print(f'TXT 文件: {c.fetchone()[0]}')
+conn.close()
+"
+```
+
+---
+
+## 四、操作流程（推荐顺序）
+
+```bash
+cd /home/yangxuan/calibre
+
+# 1. 停服务 + 备份
+docker compose down
+cp books/metadata.db books/metadata.db.backup.$(date +%Y%m%d)
+killall calibre 2>/dev/null
+
+# 2. 脏数据清理（内容损坏 + 小文件）
+python3 /path/to/clean_dirty_data.py
+
+# 3. 书名清洗 & 作者提取
+calibre-debug /path/to/fix_titles.py
+
+# 4. 重启
+docker compose up -d
+```
+
+---
+
+## 五、已知问题
+
+### `set_metadata` 报 `Errno 36 文件名过长`
+
+当 `author_sort` 字段超 80 字节时，Calibre 路径会触及 ext4 255 字节限制。先清理极长作者名：
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+UPDATE authors SET name='Unknown' WHERE LENGTH(name) > 30;
+"
+```
+
+### WSL `/mnt/f` 删除 NTFS 文件权限不够
+
+WSL 的 drvfs 默认不带 metadata 选项，`sudo rm`、`os.remove`、`cmd.exe /c del` 均无法删除 NTFS 文件。不要在 WSL 下尝试跨分区删除操作，直接让 Windows 侧（文件资源管理器/PowerShell）操作。

skill-workshop/proposals/calibre-cleaner-20260624-cdbeb219a3/proposal.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposal.v1","id":"calibre-cleaner-20260624-cdbeb219a3","kind":"update","status":"applied","title":"Update calibre-cleaner","description":"清洗 Calibre 书库：修复损坏书名/提取作者/检测编码损坏、小文件的批量删除","createdAt":"2026-06-24T03:03:28.166Z","updatedAt":"2026-06-24T03:03:30.915Z","createdBy":"skill-workshop","origin":{"agentId":"storage","sessionKey":"agent:storage:main","runId":"86d65e13-ea3d-4313-b25d-ee3fae219431","messageId":"86d65e13-ea3d-4313-b25d-ee3fae219431"},"proposedVersion":"v1","draftFile":"PROPOSAL.md","draftHash":"7a0719492c9262eebf6ea0a5d031bd1fdc45dd0e919e6ef04c5b1ce255ed0f2c","target":{"skillName":"calibre-cleaner","skillKey":"calibre-cleaner","skillDir":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-cleaner","skillFile":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-cleaner/SKILL.md","source":"openclaw-workspace","currentContentHash":"dd59723daea61a10edc128f446e41d71c07b03cbe6064ea5140e260a21fce51e"},"scan":{"state":"clean","scannedAt":"2026-06-24T03:03:30.906Z","critical":0,"warn":0,"info":0,"findings":[]},"appliedAt":"2026-06-24T03:03:30.915Z"}

skill-workshop/proposals/calibre-title-cleaner-20260624-3760b64e8b/PROPOSAL.md

@@ -0,0 +1,284 @@
+---
+name: "calibre-title-cleaner"
+description: "清洗 Calibre 书库中损坏的 txt 文档书名（HTML标签/长文本/乱码/路径超限修复）"
+status: proposal
+version: "v2"
+date: "2026-06-24T01:12:53.053Z"
+---
+
+# Calibre 书库书名清洗 & 作者提取 Skill
+
+## 概述
+
+清洗 Calibre 书库中因从 txt 文件自动导入而产生的损坏书名，**同时从书名中提取作者信息**并更新到作者字段。适用于 Calibre 书库路径 `/home/yangxuan/calibre/books`。
+
+## 前置条件
+
+- Calibre 数据库路径：`/home/yangxuan/calibre/books`
+- 元数据文件：`/home/yangxuan/calibre/books/metadata.db`
+- 需要 `calibre-debug` 或 `calibre` Python 环境（使用 `LibraryDatabase` API）
+- **运行前须停止其他 Calibre 进程**（桌面版、Calibre-Web Docker）
+- **运行前必须备份** `metadata.db`
+
+## 作者提取规则（从书名中提取）
+
+### 需要匹配的作者格式（基于实际书库数据）
+
+格式 | 示例 | 正则
+---|---|---
+`作者：xxx`（中文冒号） | `...作者：镜欲` | `作者[：:]\s*([^\s,，、\)）]+)`
+`作者:xxx`（英文冒号） | `...作者:镜欲` | 同上
+`-xxx`（英文 dash 结尾） | `善良的美艳妈妈-糠麸` | `-([^-()【】\[\]]+)$`
+`翻译：xxx` | `...翻译：kkmanlg` | `翻译[：:]\s*([^\s,，、\)）]+)`
+`BY xxx`（英文 BY） | `...BY狱厨` | `\b[Bb][Yy]\s+([^\s,，、\)）]+)`
+`&xxx`（and 符结尾） | `...&axenic` | `&([^&()【】\[\] ]+)$`
+
+### 提取策略
+
+1. **优先匹配精确的"作者："标记**（最可靠）
+2. 失败后尝试 `-xxx` 结尾（短作者名）
+3. 再尝试 `翻译：`、`BY`、`&xxx` 等
+4. 如果提取到的作者名仍是乱填的（如 `正文`、`第01章`、`【内容简介】`），**跳过**，标为 Unknown
+
+### 排除项（以下不是真作者）
+
+- `正文`、`内容简介`
+- `第\d+[章节]`（章节名）
+- 长度 > 30 字符的内容摘要
+
+## 书名清洗规则
+
+### `shorten(s, max_bytes=120)`
+
+将字符串截断到指定字节数，避免因 UTF-8 中文字符跨字节而损坏。
+
+```python
+def shorten(s, max_bytes=120):
+    encoded = s.encode('utf-8')
+    if len(encoded) <= max_bytes:
+        return s
+    try:
+        return encoded[:max_bytes].decode('utf-8')
+    except:
+        return encoded[:max_bytes-3].decode('utf-8', errors='ignore')
+```
+
+### `clean_title(title)`
+
+```python
+def clean_title(title):
+    t = title
+    # 移除 HTML 标签
+    t = re.sub(r'<[^>]+>', '', t)
+    # 替换 _BR_ / _BR 标记
+    t = re.sub(r'_BR_', ' ', t, flags=re.IGNORECASE)
+    t = re.sub(r'_BR(?![a-zA-Z])', ' ', t)
+    # 移除 _fontxxx_ / _imgxxx_ 标记
+    t = re.sub(r'_font[^_]*_', '', t)
+    t = re.sub(r'_img[^_]*_', '', t)
+    # 合并多余空格
+    t = re.sub(r'\s+', ' ', t).strip()
+    # 超长截短
+    if len(t) > 100:
+        m = re.search(r'[\u4e00-\u9fff]{2,}', t)
+        if m:
+            t = t[m.start():]
+        t = t[:60].rstrip('，。；：、！？…\ufffd\'"').rstrip('.,;:!?\'').strip()
+    # 移除控制字符
+    t = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', t)
+    return shorten(t, 100).strip() or 'Unknown'
+```
+
+### 坏书检测条件
+
+```python
+is_bad = (
+    len(title) > 100 or
+    '<img' in title or '<BR' in title or '<font' in title or
+    '\ufffd' in title or
+    len(title.encode('utf-8')) > 150
+)
+```
+
+## 完整脚本示例（含作者提取）
+
+```python
+import re
+from calibre.db.legacy import LibraryDatabase
+
+def shorten(s, max_bytes=120):
+    encoded = s.encode('utf-8')
+    if len(encoded) <= max_bytes:
+        return s
+    try:
+        return encoded[:max_bytes].decode('utf-8')
+    except:
+        return encoded[:max_bytes-3].decode('utf-8', errors='ignore')
+
+EXCLUDE_AUTHORS = {'正文', '内容简介', ''}
+
+def extract_author_from_title(title):
+    """从书名中提取作者名"""
+    # 1. 作者：xxx
+    m = re.search(r'作者[：:]\s*([^\s,，、\)）《\[]+)', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS and not re.match(r'^第\d+[章节]', name):
+            return name
+    # 2. 翻译：xxx
+    m = re.search(r'翻译[：:]\s*([^\s,，、\)）《\[]+)', title)
+    if m:
+        return m.group(1).strip()
+    # 3. BY xxx
+    m = re.search(r'\b[Bb][Yy]\s+([^\s,，、\)）《\[]+)', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS:
+            return name
+    # 4. -xxx 结尾（最后一个 dash 后的词）
+    m = re.search(r'-([^-()【】\[\]{}《》\s]{2,30})$', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS and not re.match(r'^\d+', name):
+            return name
+    # 5. &xxx 结尾
+    m = re.search(r'&([^&()【】\[\]\s]{2,30})$', title)
+    if m:
+        name = m.group(1).strip()
+        if name not in EXCLUDE_AUTHORS:
+            return name
+    return None
+
+def clean_title_and_extract_author(n):
+    """清洗书名并返回 (cleaned_title, extracted_author_or_None)"""
+    t = n
+    t = re.sub(r'<[^>]+>', '', t)
+    t = re.sub(r'_BR_', ' ', t, flags=re.IGNORECASE)
+    t = re.sub(r'_BR(?![a-zA-Z])', ' ', t)
+    t = re.sub(r'_font[^_]*_', '', t)
+    t = re.sub(r'_img[^_]*_', '', t)
+    t = re.sub(r'\s+', ' ', t).strip()
+
+    extracted_author = extract_author_from_title(t)
+
+    # 如果提取到了作者，从书名中移除作者部分
+    if extracted_author:
+        t = re.sub(r'作者[：:]\s*' + re.escape(extracted_author), '', t)
+        t = re.sub(r'翻译[：:]\s*' + re.escape(extracted_author), '', t)
+        t = re.sub(r'\b[Bb][Yy]\s+' + re.escape(extracted_author), '', t)
+        t = re.sub(r'-' + re.escape(extracted_author) + r'$', '', t)
+        t = re.sub(r'&' + re.escape(extracted_author) + r'$', '', t)
+
+    # 超长截短
+    if len(t) > 100:
+        m = re.search(r'[\u4e00-\u9fff]{2,}', t)
+        if m:
+            t = t[m.start():]
+        t = t[:60].rstrip('，。；：、！？…\ufffd\'"').rstrip('.,;:!?\'').strip()
+
+    t = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', t)
+    t = shorten(t, 100).strip() or 'Unknown'
+
+    return t, extracted_author
+
+
+db = LibraryDatabase('/home/yangxuan/calibre/books')
+count_clean = 0
+count_author = 0
+errors = []
+
+for bid in list(db.all_ids()):
+    mi = db.get_metadata(bid)
+    title = mi.title
+    author_name = mi.authors[0] if mi.authors else 'Unknown'
+
+    # 检测是否需要清洗书名
+    need_clean = (
+        len(title) > 100 or
+        '<img' in title or '<BR' in title or
+        '<font' in title or '\ufffd' in title or
+        len(title.encode('utf-8')) > 150
+    )
+
+    # 检测是否需要提取作者（当前作者为 Unknown）
+    need_author = (author_name == 'Unknown')
+
+    if need_clean or need_author:
+        new_title, extracted = clean_title_and_extract_author(title)
+
+        changed = False
+        if new_title and new_title != title:
+            mi.title = new_title
+            changed = True
+            count_clean += 1
+
+        if need_author and extracted:
+            mi.authors = [extracted]
+            changed = True
+            count_author += 1
+
+        if changed:
+            try:
+                db.set_metadata(bid, mi)
+            except Exception as e:
+                errors.append((bid, str(e)[:80]))
+
+print(f'书名清洗: {count_clean}')
+print(f'作者提取: {count_author}')
+print(f'错误: {len(errors)}')
+```
+
+## 常用操作
+
+### 查看 Unknown 作者的书
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT b.id, b.title
+FROM books b
+JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+WHERE a.name = 'Unknown'
+LIMIT 20;
+"
+
+# 统计
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+SELECT a.name, COUNT(*) as cnt
+FROM books b
+JOIN books_authors_link l ON b.id = l.book
+JOIN authors a ON l.author = a.id
+GROUP BY a.name
+ORDER BY cnt DESC
+LIMIT 20;
+"
+```
+
+### 运行清洗脚本
+
+```bash
+# 停服务 + 备份
+cd /home/yangxuan/calibre
+docker compose down
+cp books/metadata.db books/metadata.db.backup.$(date +%Y%m%d)
+killall calibre 2>/dev/null
+
+# 执行
+calibre-debug /tmp/fix_titles_v2.py
+
+# 重启
+docker compose up -d
+```
+
+## 已知问题
+
+### `set_metadata` 报 `Errno 36 文件名过长`
+
+当 `author_sort` 字段（基于作者名生成）超 80 字节时，Calibre 更新路径会触及 ext4 255 字节限制。此时需先清理极长作者名：
+
+```bash
+sqlite3 /home/yangxuan/calibre/books/metadata.db "
+UPDATE authors SET name='Unknown' WHERE LENGTH(name) > 30;
+"
+```
+然后重新执行脚本。

skill-workshop/proposals/calibre-title-cleaner-20260624-3760b64e8b/proposal.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposal.v1","id":"calibre-title-cleaner-20260624-3760b64e8b","kind":"create","status":"applied","title":"Create calibre-title-cleaner","description":"清洗 Calibre 书库中损坏的 txt 文档书名（HTML标签/长文本/乱码/路径超限修复）","createdAt":"2026-06-24T01:10:56.296Z","updatedAt":"2026-06-24T01:13:39.670Z","createdBy":"skill-workshop","origin":{"agentId":"storage","sessionKey":"agent:storage:main","runId":"af9dc258-69c6-4d62-85d9-80f64c387d85","messageId":"af9dc258-69c6-4d62-85d9-80f64c387d85"},"proposedVersion":"v2","draftFile":"PROPOSAL.md","draftHash":"735afe1e59db22fb6cbffbe074e559ebc91137fa3687e503b12fc91af62f42e1","target":{"skillName":"calibre-title-cleaner","skillKey":"calibre-title-cleaner","skillDir":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-title-cleaner","skillFile":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-title-cleaner/SKILL.md","source":"openclaw-workspace"},"scan":{"state":"clean","scannedAt":"2026-06-24T01:13:39.659Z","critical":0,"warn":0,"info":0,"findings":[]},"appliedAt":"2026-06-24T01:13:39.670Z"}

skill-workshop/proposals/calibre-title-cleaner-20260624-3760b64e8b/rollback.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.rollback.v1","proposalId":"calibre-title-cleaner-20260624-3760b64e8b","writtenAt":"2026-06-24T01:13:39.660Z","targetSkillFile":"/home/yangxuan/.openclaw/workspace/storage/skills/calibre-title-cleaner/SKILL.md","action":"create"}

skill-workshop/proposals/dianping-review-20260611-d402abec10/PROPOSAL.md

@@ -0,0 +1,52 @@
+---
+name: "dianping-review"
+description: "通过大众点评搜索查询餐厅、老店、美食推荐和评论"
+status: proposal
+version: "v1"
+date: "2026-06-11T23:50:15.731Z"
+---
+
+# dianping-review 技能
+
+通过大众点评（dianping.com）搜索查询美食推荐、餐厅评价和老店信息。
+
+## 能力
+
+1. 搜索指定位置附近的餐厅和美食
+2. 查询餐厅评价、评分、人均消费
+3. 查找开业超过十年的老店
+4. 按类型（烤鸭、涮肉、川菜等）筛选推荐
+
+## 使用场景
+
+- 用户住在某酒店/某区域，想知道附近有什么好吃的
+- 用户想找大众点评上高评分/开业久的餐厅
+- 用户想了解某家餐厅的口碑和人均消费
+
+## 使用方法
+
+由于大众点评有反爬机制，以下为可行方案：
+
+### 方案一：大众点评公开页面直接访问
+```bash
+# 搜索关键词构造
+SEARCH_URL="https://www.dianping.com/search/keyword/2/0_$(python3 -c 'import urllib.parse; print(urllib.parse.quote(sys.argv[1]))' "$KEYWORD")"
+```
+
+### 方案二：通过搜索引擎间接获取
+```bash
+# 用搜索引擎搜索大众点评的公开信息
+curl -sL "https://www.google.com/search?q=site:dianping.com+${KEYWORD}&hl=zh-CN" \
+  -H 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+```
+
+### 方案三：推荐通过大众点评App/小程序
+用户自行在微信小程序打开「大众点评」，定位当前位置查看附近美食更为方便。
+
+## 示例输出格式
+
+推荐餐厅时按以下格式：
+
+- **店名** — 评分/人均/经营年限
+- 地址：具体地址
+- 推荐理由：为什么推荐

skill-workshop/proposals/dianping-review-20260611-d402abec10/proposal.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposal.v1","id":"dianping-review-20260611-d402abec10","kind":"create","status":"pending","title":"Create dianping-review","description":"通过大众点评搜索查询餐厅、老店、美食推荐和评论","createdAt":"2026-06-11T23:50:15.731Z","updatedAt":"2026-06-11T23:50:15.731Z","createdBy":"skill-workshop","origin":{"agentId":"travel","sessionKey":"agent:travel:openclaw-weixin:direct:o9cq80w6znnpgitw-ggackwd69ba@im.wechat","runId":"877b3a72-a43d-4105-bc96-68d122db4362","messageId":"openclaw-weixin:1781221807078-aeb5f501"},"proposedVersion":"v1","draftFile":"PROPOSAL.md","draftHash":"e1b2e0249d29f948d5f7c08421dc563c8ffa8da5eef28d7ee1d7df5cc0315cbf","target":{"skillName":"dianping-review","skillKey":"dianping-review","skillDir":"/home/yangxuan/.openclaw/workspace/travel/skills/dianping-review","skillFile":"/home/yangxuan/.openclaw/workspace/travel/skills/dianping-review/SKILL.md","source":"openclaw-workspace"},"scan":{"state":"clean","scannedAt":"2026-06-11T23:50:15.731Z","critical":0,"warn":0,"info":0,"findings":[]}}

skill-workshop/proposals/jellyfin-nfo-builder-20260701-6434352e0d/PROPOSAL.md

@@ -0,0 +1,96 @@
+---
+name: "jellyfin-nfo-builder"
+description: "为剧集整理统一文件名、生成缺失的 Jellyfin .nfo 剧集元数据"
+status: proposal
+version: "v1"
+date: "2026-07-01T23:52:24.406Z"
+---
+
+# Jellyfin NFO 剧集元数据补齐技能
+
+为剧集目录整理统一文件名，并为缺失的集数生成标准的 Jellyfin `.nfo` 元数据文件。
+
+## 适用场景
+
+- 手动清理/重命名剧集文件后，部分集数的 `.nfo` 元数据缺失
+- 从不同来源合并剧集（高质量版 + 补全集），需要统一格式
+- 批量标准化剧集视频文件和元数据
+
+## 前置条件
+
+- 视频文件已整理到一个目录
+- 有一条完整的剧集（有 `.nfo` 示例可参照格式）
+- 了解剧集的总集数
+- shell 工作目录为剧集所在目录
+
+## 步骤
+
+### 1. 检查现有状态
+
+列出目录下所有视频文件和 `.nfo` 文件：
+
+```bash
+ls -lh *.mp4 *.nfo 2>/dev/null
+```
+
+确定：
+- 总集数
+- 已有哪些集的 `.nfo`
+- 哪些集缺失 `.nfo`
+- 文件名是否统一
+
+### 2. 读取一个已有 `.nfo` 作为模板
+
+```bash
+cat "剧集名 第xx集.nfo"
+```
+
+标准 Jellyfin 剧集 nfo 格式：
+
+```xml
+<?xml version="1.0" encoding="UTF-8"?>
+<episodedetails>
+  <title>第N集</title>
+  <season>1</season>
+  <episode>N</episode>
+  <plot>剧集名 第N集</plot>
+  <runtime>233</runtime>
+  <aired>2026-01-01</aired>
+</episodedetails>
+```
+
+### 3. 生成缺失的 `.nfo`
+
+```bash
+cd /path/to/剧集目录
+for i in 4 5 8 9 10 11; do
+  cat > "剧集名 第${i}集.nfo" << EOF
+<?xml version="1.0" encoding="UTF-8"?>
+<episodedetails>
+  <title>第${i}集</title>
+  <season>1</season>
+  <episode>${i}</episode>
+  <plot>剧集名 第${i}集</plot>
+  <runtime>233</runtime>
+  <aired>2026-01-01</aired>
+</episodedetails>
+EOF
+done
+```
+
+> `runtime`（时长秒数）和 `aired`（首播日期）可以参照已有文件填写，或设为默认值。
+
+### 4. 检查结果
+
+```bash
+ls -lh *.mp4 *.nfo 2>/dev/null
+```
+
+确认每一集都有对应的视频文件和 `.nfo` 文件。
+
+## 注意事项
+
+- Jellyfin 依赖文件名排序，统一格式为 `剧集名 第XX集.mp4`（两位数字，按字母排序正确）
+- `.nfo` 中的 `<episode>` 标签必须与集数一致
+- 如果整个剧集目录还没有 `tvshow.nfo` 和 `season.nfo`，也需要一并创建
+- 视频文件命名应与 `.nfo` 文件名完全一致（仅扩展名不同）

skill-workshop/proposals/jellyfin-nfo-builder-20260701-6434352e0d/proposal.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposal.v1","id":"jellyfin-nfo-builder-20260701-6434352e0d","kind":"create","status":"pending","title":"Create jellyfin-nfo-builder","description":"为剧集整理统一文件名、生成缺失的 Jellyfin .nfo 剧集元数据","createdAt":"2026-07-01T23:52:24.406Z","updatedAt":"2026-07-01T23:52:24.406Z","createdBy":"skill-workshop","origin":{"agentId":"storage","sessionKey":"agent:storage:main","runId":"1b45e119-4276-4a7c-8a20-e52d1679a304","messageId":"1b45e119-4276-4a7c-8a20-e52d1679a304"},"proposedVersion":"v1","draftFile":"PROPOSAL.md","draftHash":"fa9a54a33aecdbb0a96e175f7acf1e923606cbf90114460da48548e127710a48","target":{"skillName":"jellyfin-nfo-builder","skillKey":"jellyfin-nfo-builder","skillDir":"/home/yangxuan/.openclaw/workspace/storage/skills/jellyfin-nfo-builder","skillFile":"/home/yangxuan/.openclaw/workspace/storage/skills/jellyfin-nfo-builder/SKILL.md","source":"openclaw-workspace"},"scan":{"state":"clean","scannedAt":"2026-07-01T23:52:24.407Z","critical":0,"warn":0,"info":0,"findings":[]}}

skill-workshop/proposals/weekly-report-g5-20260626-7595273f1d/PROPOSAL.md

@@ -0,0 +1,106 @@
+---
+name: "weekly-report-g5"
+description: "维云智造G5周报生成：整理每日工作→多段邮件(纯文本+HTML含签名图)→存入钉邮草稿箱"
+status: proposal
+version: "v1"
+date: "2026-06-26T00:46:22.478Z"
+---
+
+# weekly-report-g5 — 维云智造 G5 周报生成技能
+
+## 适用场景
+用户提供了周一至周五的每日工作内容，需要生成 G5 周报并存入钉邮草稿箱。
+
+## 工作流程
+
+### 1. 收集每日工作内容
+- 周一（本周首日）至周五
+- 如果用户分多次给出，先等待所有日期内容收齐再生成
+
+### 2. 邮件格式规范
+
+**主题**：`G5开发周报 (YYYY-MM-DD ~ YYYY-MM-DD)`
+
+**收件人**：liuqiang@witsoft.cn
+
+**抄送**：wurd@witsoft.cn, chenm@witsoft.cn, zengli@witsoft.cn
+
+**发送人**：杨轩 \<yangxuan@witsoft.cn\>
+
+**正文（纯文本版）**：
+```
+项目名称： 维云智造G5
+主要任务： <本周主要任务>
+
+本周工作内容
+周一（YYYY-MM-DD）
+ - ...
+周二（YYYY-MM-DD）
+ - ...
+周三（YYYY-MM-DD）
+ - ...
+周四（YYYY-MM-DD）
+ - ...
+周五（YYYY-MM-DD）
+ - ...
+
+存在问题
+<内容或"无">
+```
+
+**签名格式（纯文本）**：
+```
+Best regards,
+杨轩
+https://minio.climbcube.cn/img/202606260843249.jpg
+地址：中国·南京云密城L栋5/10楼
+手机：18726128489
+邮箱：yangxuan@witsoft.cn
+```
+
+### 3. 发送方式
+
+使用 Python 构造**多段邮件**（同时含纯文本和 HTML），然后通过 himalaya 存入草稿箱。
+
+HTML 版签名区应该包含 `<img>` 标签嵌入签名图片：
+```html
+<img src="https://minio.climbcube.cn/img/202606260843249.jpg" alt="签名" style="max-width:200px; height:auto;">
+```
+
+**生成命令模板**：
+
+```bash
+python3 << 'PYEOF'
+import email
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
+from email.header import Header
+
+plain_body = """..."""
+html_text = """..."""
+
+msg = MIMEMultipart('related')
+msg['From'] = Header('杨轩', 'utf-8').encode() + ' <yangxuan@witsoft.cn>'
+msg['To'] = Header('刘强', 'utf-8').encode() + ' <liuqiang@witsoft.cn>'
+msg['Cc'] = Header('吴睿东', 'utf-8').encode() + ' <wurd@witsoft.cn>, ' + Header('陈明', 'utf-8').encode() + ' <chenm@witsoft.cn>, ' + Header('曾莉', 'utf-8').encode() + ' <zengli@witsoft.cn>'
+msg['Subject'] = Header('G5开发周报 (...)', 'utf-8').encode()
+
+alt = MIMEMultipart('alternative')
+alt.attach(MIMEText(plain_body, 'plain', 'utf-8'))
+alt.attach(MIMEText(html_text, 'html', 'utf-8'))
+msg.attach(alt)
+
+with open('/tmp/weekly-report-YYYY-MM-DD.eml', 'w') as f:
+    f.write(msg.as_string())
+PYEOF
+himalaya message save --folder "草稿" < /tmp/weekly-report-YYYY-MM-DD.eml
+```
+
+### 4. 最后通知
+通知用户去钉钉邮箱草稿箱确认并发送。
+
+## 注意事项
+- 纯文本版签名包含图片 URL 链接
+- HTML 版使用 `<img>` 标签嵌入签名图片
+- 如用户不提供签名信息，使用 MEMORY.md 中的默认签名：姓名、地址、手机、邮箱
+- 所有交互使用中文

skill-workshop/proposals/weekly-report-g5-20260626-7595273f1d/proposal.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.proposal.v1","id":"weekly-report-g5-20260626-7595273f1d","kind":"create","status":"applied","title":"Create weekly-report-g5","description":"维云智造G5周报生成：整理每日工作→多段邮件(纯文本+HTML含签名图)→存入钉邮草稿箱","createdAt":"2026-06-26T00:46:22.478Z","updatedAt":"2026-06-26T00:46:35.812Z","createdBy":"skill-workshop","origin":{"agentId":"resume","sessionKey":"agent:resume:main","runId":"7fa9bf80-5f98-41ba-8744-83e449da1295","messageId":"7fa9bf80-5f98-41ba-8744-83e449da1295"},"proposedVersion":"v1","draftFile":"PROPOSAL.md","draftHash":"f608b6a347fcb01303eff420e73bbb95a2b9d313b55d046fc65c131ec2db14ba","target":{"skillName":"weekly-report-g5","skillKey":"weekly-report-g5","skillDir":"/home/yangxuan/.openclaw/workspace/resume/skills/weekly-report-g5","skillFile":"/home/yangxuan/.openclaw/workspace/resume/skills/weekly-report-g5/SKILL.md","source":"openclaw-workspace"},"scan":{"state":"clean","scannedAt":"2026-06-26T00:46:35.797Z","critical":0,"warn":0,"info":0,"findings":[]},"appliedAt":"2026-06-26T00:46:35.812Z"}

skill-workshop/proposals/weekly-report-g5-20260626-7595273f1d/rollback.json

@@ -0,0 +1 @@
+{"schema":"openclaw.skill-workshop.rollback.v1","proposalId":"weekly-report-g5-20260626-7595273f1d","writtenAt":"2026-06-26T00:46:35.798Z","targetSkillFile":"/home/yangxuan/.openclaw/workspace/resume/skills/weekly-report-g5/SKILL.md","action":"create"}