chore: release v1.26.1

- notebook: hand-drawn infographic style with watercolor rendering and Morandi palette
- study-notes: realistic handwritten photo style with blue pen, red annotations, yellow highlighter
- mindmap: center radial layout (4-8 branches)
- quadrant: four-quadrant / circular section layout

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.25.2"
+    "version": "1.26.1"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,33 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.26.1 - 2026-01-29
+
+### Features
+- `baoyu-article-illustrator`, `baoyu-comic`, `baoyu-cover-image`, `baoyu-infographic`, `baoyu-slide-deck`, `baoyu-xhs-images`: add backup rules for existing files—automatically renames source, prompt, and image files with timestamp suffix before overwriting.
+
+### Fixes
+- `baoyu-xhs-images`: remove `notebook` style (10 styles remaining).
+
+## 1.26.0 - 2026-01-29
+
+### Features
+- `baoyu-xhs-images`: add `notebook` style (hand-drawn infographic with watercolor rendering and Morandi palette) and `study-notes` style (realistic handwritten photo aesthetic).
+- `baoyu-xhs-images`: add `mindmap` (center radial) and `quadrant` (four-section grid) layouts.
+
+## 1.25.4 - 2026-01-29
+
+### Fixes
+- `baoyu-markdown-to-html`: generate proper `<img>` tags with `data-local-path` attribute instead of text placeholders.
+- `baoyu-post-to-wechat`: fix API publishing to read image paths from `data-local-path` attribute; fix title/cover extraction from corresponding `.md` frontmatter when publishing HTML files.
+- `baoyu-post-to-wechat`: fix CLI argument parsing to handle unknown parameters gracefully; add `--summary` parameter support.
+- `baoyu-post-to-wechat`: fix browser publishing to convert `<img>` tags back to text placeholders before paste.
+
+## 1.25.3 - 2026-01-28
+
+### Features
+- `baoyu-format-markdown`: add content type detection with user confirmation for markdown files; add CJK punctuation handling to move paired punctuation outside emphasis markers.
+
 ## 1.25.2 - 2026-01-28
 
 ### Documentation

CHANGELOG.zh.md

@@ -2,6 +2,33 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.26.1 - 2026-01-29
+
+### 新功能
+- `baoyu-article-illustrator`、`baoyu-comic`、`baoyu-cover-image`、`baoyu-infographic`、`baoyu-slide-deck`、`baoyu-xhs-images`：新增文件备份规则，覆盖前自动将现有源文件、提示词和图片重命名为带时间戳后缀的备份文件。
+
+### 修复
+- `baoyu-xhs-images`：移除 `notebook` 风格（保留 10 种风格）。
+
+## 1.26.0 - 2026-01-29
+
+### 新功能
+- `baoyu-xhs-images`：新增 `notebook` 风格（水彩渲染手绘信息图 + 莫兰迪配色）和 `study-notes` 风格（真实手写照片美学）。
+- `baoyu-xhs-images`：新增 `mindmap`（中心发散式）和 `quadrant`（四象限）布局。
+
+## 1.25.4 - 2026-01-29
+
+### 修复
+- `baoyu-markdown-to-html`：生成带 `data-local-path` 属性的 `<img>` 标签，而非纯文本占位符。
+- `baoyu-post-to-wechat`：修复 API 发布时从 `data-local-path` 属性读取图片路径；修复发布 HTML 文件时从对应 `.md` 的 frontmatter 提取标题和封面图。
+- `baoyu-post-to-wechat`：修复命令行参数解析，正确跳过未知参数；新增 `--summary` 参数支持。
+- `baoyu-post-to-wechat`：修复浏览器发布模式，粘贴前将 `<img>` 标签转换回文本占位符。
+
+## 1.25.3 - 2026-01-28
+
+### 新功能
+- `baoyu-format-markdown`：新增内容类型检测，对已有 markdown 格式的文件提供用户确认选项；新增 CJK 配对标点处理，将括号、引号等标点移出加粗标记外。
+
 ## 1.25.2 - 2026-01-28
 
 ### 文档

skills/baoyu-article-illustrator/SKILL.md

@@ -78,6 +78,8 @@ Progress:
 | File path | Ask user (1.2) | → 1.2 |
 | Pasted content | `illustrations/{topic-slug}/` | → 1.4 |
 
+**Backup rule for pasted content**: If `source.md` exists in target directory, rename to `source-backup-YYYYMMDD-HHMMSS.md` before saving.
+
 **1.2 Determine Output Directory** (file path input only)
 
 Check `default_output_dir` in preferences:
@@ -236,6 +238,7 @@ image_count: 4
 **5.1 Create Prompts**
 
 Follow [references/prompt-construction.md](references/prompt-construction.md). Save to `prompts/illustration-{slug}.md`.
+- **Backup rule**: If prompt file exists, rename to `prompts/illustration-{slug}-backup-YYYYMMDD-HHMMSS.md`
 
 **5.2 Select Generation Skill**
 
@@ -247,7 +250,9 @@ Add: `Include a subtle watermark "[content]" at [position].`
 
 **5.4 Generate**
 
-1. Generate sequentially
+1. For each illustration:
+   - **Backup rule**: If image file exists, rename to `NN-{type}-{slug}-backup-YYYYMMDD-HHMMSS.png`
+   - Generate image
 2. After each: "Generated X/N"
 3. On failure: retry once, then log and continue
 

skills/baoyu-comic/SKILL.md

@@ -194,6 +194,7 @@ Input → Preferences → Analyze → [Check Existing?] → [Confirm: Style + Re
 **Character reference is MANDATORY for visual consistency.**
 
 **7.1 Generate character sheet first**:
+- **Backup rule**: If `characters/characters.png` exists, rename to `characters/characters-backup-YYYYMMDD-HHMMSS.png`
 ```bash
 # Use Reference Sheet Prompt from characters/characters.md
 npx -y bun ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \
@@ -214,6 +215,10 @@ Compress to reduce token usage when used as reference image:
 | Supports `--ref` | Pass `characters/characters.png` with EVERY page |
 | No `--ref` support | Prepend character descriptions to EVERY prompt file |
 
+**Backup rules for page generation**:
+- If prompt file exists: rename to `prompts/NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.md`
+- If image file exists: rename to `NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.png`
+
 ```bash
 # Example: ALWAYS include --ref for consistency
 npx -y bun ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \

skills/baoyu-comic/references/workflow.md

@@ -84,6 +84,7 @@ Read source content, save it if needed, and perform deep analysis.
 1. **Save source content** (if not already a file):
    - If user provides a file path: use as-is
    - If user pastes content: save to `source.md` in target directory
+   - **Backup rule**: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
 2. Read source content
 3. **Deep analysis** following `analysis-framework.md`:
    - Target audience identification
@@ -329,6 +330,7 @@ Create image generation prompts for all pages.
 1. Create prompt following art style + tone guidelines
 2. Include character visual descriptions for consistency
 3. Save to `prompts/NN-{cover|page}-[slug].md`
+   - **Backup rule**: If prompt file exists, rename to `prompts/NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.md`
 
 **Prompt File Format**:
 ```markdown
@@ -405,8 +407,9 @@ With confirmed prompts from Step 5/6:
 ### 7.1 Generate Character Reference Sheet (first)
 
 1. Use Reference Sheet Prompt from `characters/characters.md`
-2. Generate → `characters/characters.png`
-3. This ensures visual consistency for all subsequent pages
+2. **Backup rule**: If `characters/characters.png` exists, rename to `characters/characters-backup-YYYYMMDD-HHMMSS.png`
+3. Generate → `characters/characters.png`
+4. This ensures visual consistency for all subsequent pages
 
 ### 7.2 Generate Comic Pages
 
@@ -453,9 +456,10 @@ When skill does NOT support reference images, create combined prompt files:
 
 **For each page (cover + pages)**:
 1. Read prompt from `prompts/NN-{cover|page}-[slug].md`
-2. Generate image using Strategy A or B (based on skill capability)
-3. Save to `NN-{cover|page}-[slug].png`
-4. Report progress after each generation: "Generated X/N: [page title]"
+2. **Backup rule**: If image file exists, rename to `NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.png`
+3. Generate image using Strategy A or B (based on skill capability)
+4. Save to `NN-{cover|page}-[slug].png`
+5. Report progress after each generation: "Generated X/N: [page title]"
 
 **Session Management**:
 If image generation skill supports `--sessionId`:

skills/baoyu-cover-image/SKILL.md

@@ -209,6 +209,7 @@ Schema: [references/config/preferences-schema.md](references/config/preferences-
 ### Step 1: Analyze Content
 
 1. **Save source content** (if pasted, save to `source.md` in target directory; if file path, use as-is)
+   - **Backup rule**: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
 2. **Content analysis**: Extract topic, core message, tone, keywords; identify visual metaphors; detect content type
 3. **Language detection**: Detect source language, note user's input language, compare with EXTEND.md preference
 4. **Determine output directory** per File Structure rules. If no `default_output_dir` preference + file path input, include in Step 2 Q4
@@ -226,6 +227,8 @@ Validate all 5 dimensions + aspect ratio. Full confirmation flow: [references/wo
 
 ### Step 3: Create Prompt
 
+**Backup rule**: If `prompts/cover.md` exists, rename to `prompts/cover-backup-YYYYMMDD-HHMMSS.md`
+
 Save to `prompts/cover.md`. Full template: [references/workflow/prompt-template.md](references/workflow/prompt-template.md)
 
 ### Step 4: Generate Image

skills/baoyu-format-markdown/SKILL.md

@@ -58,6 +58,55 @@ Claude performs content analysis and formatting (Steps 1-6), then runs the scrip
 
 Read the user-specified markdown or plain text file.
 
+### Step 1.5: Detect Content Type & Confirm
+
+**Content Type Detection:**
+
+| Indicator | Classification |
+|-----------|----------------|
+| Has `---` YAML frontmatter | Markdown |
+| Has `#`, `##`, `###` headings | Markdown |
+| Has `**bold**`, `*italic*` | Markdown |
+| Has `- ` or `1. ` lists | Markdown |
+| Has ``` code blocks | Markdown |
+| Has `> ` blockquotes | Markdown |
+| None of above | Plain text |
+
+**Decision Flow:**
+
+┌─────────────────┬────────────────────────────────────────────────┐
+│  Content Type   │                     Action                     │
+├─────────────────┼────────────────────────────────────────────────┤
+│ Plain text      │ Proceed to Step 2 (format to markdown)         │
+├─────────────────┼────────────────────────────────────────────────┤
+│ Markdown        │ Use AskUserQuestion to confirm optimization    │
+└─────────────────┴────────────────────────────────────────────────┘
+
+**If Markdown detected, ask user:**
+
+```
+Detected existing markdown formatting. What would you like to do?
+
+1. Optimize formatting (Recommended)
+   - Add/improve frontmatter, headings, bold, lists
+   - Run typography script (spacing, emphasis fixes)
+   - Output: {filename}-formatted.md
+
+2. Keep original formatting
+   - Preserve existing markdown structure
+   - Run typography script (spacing, emphasis fixes)
+   - Output: {filename}-formatted.md
+
+3. Typography fixes only
+   - Run typography script on original file in-place
+   - No copy created, modifies original file directly
+```
+
+**Based on user choice:**
+- **Optimize**: Continue to Step 2-8 (full workflow)
+- **Keep original**: Skip Steps 2-5, copy file → Step 6-8 (run script on copy)
+- **Typography only**: Skip Steps 2-6, run Step 7 on original file directly
+
 ### Step 2: Analyze Content Structure
 
 Identify:
@@ -138,6 +187,10 @@ Examples:
 - `final.md` → `final-formatted.md`
 - `draft-v1.md` → `draft-v1-formatted.md`
 
+**If user chose "Keep original formatting" (from Step 1.5):**
+- Copy original file to `{filename}-formatted.md` without modifications
+- Proceed to Step 7 for typography fixes only
+
 **Backup existing file:**
 
 If `{filename}-formatted.md` already exists, backup before overwriting:

skills/baoyu-format-markdown/scripts/cjk-emphasis.ts

@@ -11,6 +11,21 @@ export const CJK_CHAR_RE = new RegExp(`[${CJK_SCRIPTS}]`, "u");
 const PUNCT_OR_SYMBOL_RE = /[\p{P}\p{S}]/u;
 const WORD_CHAR_RE = /[\p{L}\p{N}]/u;
 
+const CJK_PUNCT_PAIRS: Record<string, string> = {
+  "“": "”",
+  "‘": "’",
+  "（": "）",
+  "〔": "〕",
+  "〖": "〗",
+  "〘": "〙",
+  "〚": "〛",
+  "「": "」",
+  "『": "』",
+  "〈": "〉",
+  "《": "》",
+  "【": "】",
+};
+
 function findInlineCodeRanges(text: string): Array<[number, number]> {
   const ranges: Array<[number, number]> = [];
   let i = 0;
@@ -69,8 +84,120 @@ function isPunctuationOrSymbol(ch: string | undefined): boolean {
   return !!ch && PUNCT_OR_SYMBOL_RE.test(ch);
 }
 
-function fixCjkEmphasisSpacingInBlock(block: string): string {
+function isMatchingCjkPunct(open: string, close: string): boolean {
+  return CJK_PUNCT_PAIRS[open] === close;
+}
+
+function mapNonCodeSegments(
+  block: string,
+  mapper: (segment: string) => string
+): string {
   const codeRanges = findInlineCodeRanges(block);
+  if (codeRanges.length === 0) {
+    return mapper(block);
+  }
+
+  let result = "";
+  let lastIndex = 0;
+  for (const [start, end] of codeRanges) {
+    if (start > lastIndex) {
+      result += mapper(block.slice(lastIndex, start));
+    }
+    result += block.slice(start, end + 1);
+    lastIndex = end + 1;
+  }
+  if (lastIndex < block.length) {
+    result += mapper(block.slice(lastIndex));
+  }
+  return result;
+}
+
+function moveCjkPunctuationOutsideEmphasis(block: string): string {
+  return mapNonCodeSegments(block, (segment) => {
+    const delimiterPositions: number[] = [];
+    let cursor = 0;
+    while (cursor < segment.length - 1) {
+      if (
+        segment[cursor] === "*" &&
+        segment[cursor + 1] === "*" &&
+        segment[cursor - 1] !== "*" &&
+        segment[cursor + 2] !== "*" &&
+        !isEscaped(segment, cursor)
+      ) {
+        delimiterPositions.push(cursor);
+        cursor += 2;
+        continue;
+      }
+      cursor += 1;
+    }
+
+    if (delimiterPositions.length < 2) return segment;
+
+    const stack: number[] = [];
+    const pairs: Array<{ open: number; close: number }> = [];
+    for (const pos of delimiterPositions) {
+      if (stack.length === 0) {
+        stack.push(pos);
+      } else {
+        const open = stack.pop() as number;
+        pairs.push({ open, close: pos });
+      }
+    }
+
+    const skip = new Set<number>();
+    const insertBefore = new Map<number, string>();
+
+    for (const pair of pairs) {
+      const openPunctPos = pair.open + 2;
+      const closePunctPos = pair.close - 1;
+      if (openPunctPos >= closePunctPos) continue;
+
+      const openPunct = segment[openPunctPos];
+      const closePunct = segment[closePunctPos];
+      if (!openPunct || !closePunct) continue;
+      if (!CJK_OPENING_PUNCT_RE.test(openPunct)) continue;
+      if (!CJK_CLOSING_PUNCT_RE.test(closePunct)) continue;
+      if (!isMatchingCjkPunct(openPunct, closePunct)) continue;
+      if (openPunctPos + 1 >= closePunctPos) continue;
+
+      const inner = segment.slice(openPunctPos + 1, closePunctPos);
+      if (inner.length === 0) continue;
+
+      skip.add(openPunctPos);
+      skip.add(closePunctPos);
+
+      insertBefore.set(pair.open, (insertBefore.get(pair.open) ?? "") + openPunct);
+      const afterClose = pair.close + 2;
+      insertBefore.set(
+        afterClose,
+        (insertBefore.get(afterClose) ?? "") + closePunct
+      );
+    }
+
+    if (skip.size === 0) return segment;
+
+    let result = "";
+    for (let idx = 0; idx < segment.length; idx += 1) {
+      const insert = insertBefore.get(idx);
+      if (insert) {
+        result += insert;
+      }
+      if (skip.has(idx)) {
+        continue;
+      }
+      result += segment[idx];
+    }
+    const tailInsert = insertBefore.get(segment.length);
+    if (tailInsert) {
+      result += tailInsert;
+    }
+    return result;
+  });
+}
+
+function fixCjkEmphasisSpacingInBlock(block: string): string {
+  const normalized = moveCjkPunctuationOutsideEmphasis(block);
+  const codeRanges = findInlineCodeRanges(normalized);
   let rangeIndex = 0;
 
   const delimiters: Array<{
@@ -79,7 +206,7 @@ function fixCjkEmphasisSpacingInBlock(block: string): string {
     canClose: boolean;
   }> = [];
   let cursor = 0;
-  while (cursor < block.length - 1) {
+  while (cursor < normalized.length - 1) {
     if (rangeIndex < codeRanges.length && cursor >= codeRanges[rangeIndex][0]) {
       if (cursor <= codeRanges[rangeIndex][1]) {
         cursor = codeRanges[rangeIndex][1] + 1;
@@ -90,14 +217,14 @@ function fixCjkEmphasisSpacingInBlock(block: string): string {
     }
 
     if (
-      block[cursor] === "*" &&
-      block[cursor + 1] === "*" &&
-      block[cursor - 1] !== "*" &&
-      block[cursor + 2] !== "*" &&
-      !isEscaped(block, cursor)
+      normalized[cursor] === "*" &&
+      normalized[cursor + 1] === "*" &&
+      normalized[cursor - 1] !== "*" &&
+      normalized[cursor + 2] !== "*" &&
+      !isEscaped(normalized, cursor)
     ) {
-      const before = block[cursor - 1];
-      const after = block[cursor + 2];
+      const before = normalized[cursor - 1];
+      const after = normalized[cursor + 2];
       const beforeIsSpace = isWhitespaceChar(before);
       const afterIsSpace = isWhitespaceChar(after);
       const beforeIsPunct = isPunctuationOrSymbol(before);
@@ -140,12 +267,12 @@ function fixCjkEmphasisSpacingInBlock(block: string): string {
     }
   }
 
-  if (pairs.length === 0) return block;
+  if (pairs.length === 0) return normalized;
 
   const insertPositions = new Set<number>();
   for (const pair of pairs) {
-    const insideLast = block[pair.close - 1];
-    const afterClose = block[pair.close + 2];
+    const insideLast = normalized[pair.close - 1];
+    const afterClose = normalized[pair.close + 2];
     if (!afterClose) continue;
     if (
       CJK_CLOSING_PUNCT_RE.test(insideLast) &&
@@ -155,16 +282,16 @@ function fixCjkEmphasisSpacingInBlock(block: string): string {
     }
   }
 
-  if (insertPositions.size === 0) return block;
+  if (insertPositions.size === 0) return normalized;
 
   let result = "";
-  for (let idx = 0; idx < block.length; idx += 1) {
+  for (let idx = 0; idx < normalized.length; idx += 1) {
     if (insertPositions.has(idx)) {
       result += " ";
     }
-    result += block[idx];
+    result += normalized[idx];
   }
-  if (insertPositions.has(block.length)) {
+  if (insertPositions.has(normalized.length)) {
     result += " ";
   }
   return result;

skills/baoyu-infographic/SKILL.md

@@ -153,10 +153,12 @@ Schema: `references/config/preferences-schema.md`
 **1.2 Analyze Content → `analysis.md`**
 
 1. Save source content (file path or paste → `source.md`)
+   - **Backup rule**: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
 2. Analyze: topic, data type, complexity, tone, audience
 3. Detect source language and user language
 4. Extract design instructions from user input
 5. Save analysis
+   - **Backup rule**: If `analysis.md` exists, rename to `analysis-backup-YYYYMMDD-HHMMSS.md`
 
 See `references/analysis-framework.md` for detailed format.
 
@@ -189,6 +191,8 @@ Present all options in single confirmation:
 
 ### Step 5: Generate Prompt → `prompts/infographic.md`
 
+**Backup rule**: If `prompts/infographic.md` exists, rename to `prompts/infographic-backup-YYYYMMDD-HHMMSS.md`
+
 Combine:
 1. Layout definition from `references/layouts/<layout>.md`
 2. Style definition from `references/styles/<style>.md`
@@ -199,8 +203,10 @@ Combine:
 ### Step 6: Generate Image
 
 1. Select available image generation skill (ask user if multiple)
-2. Call with prompt file and output path
-3. On failure, auto-retry once
+2. **Check for existing file**: Before generating, check if `infographic.png` exists
+   - If exists: Rename to `infographic-backup-YYYYMMDD-HHMMSS.png`
+3. Call with prompt file and output path
+4. On failure, auto-retry once
 
 ### Step 7: Output Summary
 

skills/baoyu-markdown-to-html/scripts/main.ts

@@ -214,7 +214,6 @@ export async function convertMarkdown(markdownPath: string, options?: { title?:
   }
 
   fs.copyFileSync(tempHtmlPath, finalHtmlPath);
-  console.error(`[markdown-to-html] HTML saved to: ${finalHtmlPath}`);
 
   const contentImages: ImageInfo[] = [];
   for (const img of images) {
@@ -226,6 +225,15 @@ export async function convertMarkdown(markdownPath: string, options?: { title?:
     });
   }
 
+  let htmlContent = fs.readFileSync(finalHtmlPath, 'utf-8');
+  for (const img of contentImages) {
+    const imgTag = `<img src="${img.placeholder}" data-local-path="${img.localPath}" style="display: block; width: 100%; margin: 1.5em auto;">`;
+    htmlContent = htmlContent.replace(img.placeholder, imgTag);
+  }
+  fs.writeFileSync(finalHtmlPath, htmlContent, 'utf-8');
+
+  console.error(`[markdown-to-html] HTML saved to: ${finalHtmlPath}`);
+
   return {
     title,
     author,

skills/baoyu-post-to-wechat/scripts/wechat-api.ts

@@ -177,7 +177,7 @@ async function uploadImagesInHtml(
   accessToken: string,
   baseDir: string
 ): Promise<{ html: string; firstMediaId: string }> {
-  const imgRegex = /<img[^>]+src=["']([^"']+)["'][^>]*>/gi;
+  const imgRegex = /<img[^>]*\ssrc=["']([^"']+)["'][^>]*>/gi;
   const matches = [...html.matchAll(imgRegex)];
 
   if (matches.length === 0) {
@@ -188,7 +188,7 @@ async function uploadImagesInHtml(
   let updatedHtml = html;
 
   for (const match of matches) {
-    const [, src] = match;
+    const [fullTag, src] = match;
     if (!src) continue;
 
     if (src.startsWith("https://mmbiz.qpic.cn")) {
@@ -198,15 +198,21 @@ async function uploadImagesInHtml(
       continue;
     }
 
-    console.error(`[wechat-api] Uploading image: ${src}`);
+    const localPathMatch = fullTag.match(/data-local-path=["']([^"']+)["']/);
+    const imagePath = localPathMatch ? localPathMatch[1]! : src;
+
+    console.error(`[wechat-api] Uploading image: ${imagePath}`);
     try {
-      const resp = await uploadImage(src, accessToken, baseDir);
-      updatedHtml = updatedHtml.replace(src, resp.url);
+      const resp = await uploadImage(imagePath, accessToken, baseDir);
+      const newTag = fullTag
+        .replace(/\ssrc=["'][^"']+["']/, ` src="${resp.url}"`)
+        .replace(/\sdata-local-path=["'][^"']+["']/, "");
+      updatedHtml = updatedHtml.replace(fullTag, newTag);
       if (!firstMediaId) {
         firstMediaId = resp.media_id;
       }
     } catch (err) {
-      console.error(`[wechat-api] Failed to upload ${src}:`, err);
+      console.error(`[wechat-api] Failed to upload ${imagePath}:`, err);
     }
   }
 
@@ -310,6 +316,7 @@ Arguments:
 
 Options:
   --title <title>     Override title
+  --summary <text>    Article summary (for future use)
   --theme <name>      Theme name for markdown (default, grace, simple). Default: default
   --cover <path>      Cover image path (local or URL)
   --dry-run           Parse and render only, don't publish
@@ -337,6 +344,7 @@ interface CliArgs {
   filePath: string;
   isHtml: boolean;
   title?: string;
+  summary?: string;
   theme: string;
   cover?: string;
   dryRun: boolean;
@@ -358,12 +366,16 @@ function parseArgs(argv: string[]): CliArgs {
     const arg = argv[i]!;
     if (arg === "--title" && argv[i + 1]) {
       args.title = argv[++i];
+    } else if (arg === "--summary" && argv[i + 1]) {
+      args.summary = argv[++i];
     } else if (arg === "--theme" && argv[i + 1]) {
       args.theme = argv[++i]!;
     } else if (arg === "--cover" && argv[i + 1]) {
       args.cover = argv[++i];
     } else if (arg === "--dry-run") {
       args.dryRun = true;
+    } else if (arg.startsWith("--") && argv[i + 1] && !argv[i + 1]!.startsWith("-")) {
+      i++;
     } else if (!arg.startsWith("-")) {
       args.filePath = arg;
     }
@@ -405,6 +417,15 @@ async function main(): Promise<void> {
   if (args.isHtml) {
     htmlPath = filePath;
     htmlContent = extractHtmlContent(htmlPath);
+    const mdPath = filePath.replace(/\.html$/i, ".md");
+    if (fs.existsSync(mdPath)) {
+      const mdContent = fs.readFileSync(mdPath, "utf-8");
+      const parsed = parseFrontmatter(mdContent);
+      frontmatter = parsed.frontmatter;
+      if (!title && frontmatter.title) {
+        title = frontmatter.title;
+      }
+    }
     if (!title) {
       title = extractHtmlTitle(fs.readFileSync(htmlPath, "utf-8"));
     }

skills/baoyu-post-to-wechat/scripts/wechat-article.ts

@@ -115,7 +115,7 @@ async function sendPaste(cdp?: CdpConnection, sessionId?: string): Promise<void>
   }
 }
 
-async function copyHtmlFromBrowser(cdp: CdpConnection, htmlFilePath: string): Promise<void> {
+async function copyHtmlFromBrowser(cdp: CdpConnection, htmlFilePath: string, contentImages: ImageInfo[] = []): Promise<void> {
   const absolutePath = path.isAbsolute(htmlFilePath) ? htmlFilePath : path.resolve(process.cwd(), htmlFilePath);
   const fileUrl = `file://${absolutePath}`;
 
@@ -128,6 +128,28 @@ async function copyHtmlFromBrowser(cdp: CdpConnection, htmlFilePath: string): Pr
   await cdp.send('Runtime.enable', {}, { sessionId });
   await sleep(2000);
 
+  if (contentImages.length > 0) {
+    console.log('[wechat] Replacing img tags with placeholders for browser paste...');
+    const replacements = contentImages.map(img => ({ placeholder: img.placeholder, localPath: img.localPath }));
+    await cdp.send<{ result: { value: unknown } }>('Runtime.evaluate', {
+      expression: `
+        (function() {
+          const replacements = ${JSON.stringify(replacements)};
+          for (const r of replacements) {
+            const imgs = document.querySelectorAll('img[src="' + r.placeholder + '"], img[data-local-path="' + r.localPath + '"]');
+            for (const img of imgs) {
+              const text = document.createTextNode(r.placeholder);
+              img.parentNode.replaceChild(text, img);
+            }
+          }
+          return true;
+        })()
+      `,
+      returnByValue: true,
+    }, { sessionId });
+    await sleep(500);
+  }
+
   console.log('[wechat] Selecting #output content...');
   await cdp.send<{ result: { value: unknown } }>('Runtime.evaluate', {
     expression: `
@@ -176,7 +198,7 @@ async function parseMarkdownWithPlaceholders(markdownPath: string, theme?: strin
   return JSON.parse(output);
 }
 
-function parseHtmlMeta(htmlPath: string): { title: string; author: string; summary: string } {
+function parseHtmlMeta(htmlPath: string): { title: string; author: string; summary: string; contentImages: ImageInfo[] } {
   const content = fs.readFileSync(htmlPath, 'utf-8');
 
   let title = '';
@@ -203,7 +225,45 @@ function parseHtmlMeta(htmlPath: string): { title: string; author: string; summa
     }
   }
 
-  return { title, author, summary };
+  const mdPath = htmlPath.replace(/\.html$/i, '.md');
+  if (fs.existsSync(mdPath)) {
+    const mdContent = fs.readFileSync(mdPath, 'utf-8');
+    const fmMatch = mdContent.match(/^---\r?\n([\s\S]*?)\r?\n---/);
+    if (fmMatch) {
+      const lines = fmMatch[1]!.split('\n');
+      for (const line of lines) {
+        const colonIdx = line.indexOf(':');
+        if (colonIdx > 0) {
+          const key = line.slice(0, colonIdx).trim();
+          let value = line.slice(colonIdx + 1).trim();
+          if ((value.startsWith('"') && value.endsWith('"')) || (value.startsWith("'") && value.endsWith("'"))) {
+            value = value.slice(1, -1);
+          }
+          if (key === 'title' && !title) title = value;
+          if (key === 'author' && !author) author = value;
+          if ((key === 'description' || key === 'summary') && !summary) summary = value;
+        }
+      }
+    }
+  }
+
+  const contentImages: ImageInfo[] = [];
+  const imgRegex = /<img[^>]*\ssrc=["']([^"']+)["'][^>]*>/gi;
+  const matches = [...content.matchAll(imgRegex)];
+  for (const match of matches) {
+    const [fullTag, src] = match;
+    if (!src || src.startsWith('http')) continue;
+    const localPathMatch = fullTag.match(/data-local-path=["']([^"']+)["']/);
+    if (localPathMatch) {
+      contentImages.push({
+        placeholder: src,
+        localPath: localPathMatch[1]!,
+        originalPath: src,
+      });
+    }
+  }
+
+  return { title, author, summary, contentImages };
 }
 
 async function selectAndReplacePlaceholder(session: ChromeSession, placeholder: string): Promise<boolean> {
@@ -273,9 +333,13 @@ export async function postArticle(options: ArticleOptions): Promise<void> {
     effectiveAuthor = effectiveAuthor || meta.author;
     effectiveSummary = effectiveSummary || meta.summary;
     effectiveHtmlFile = htmlFile;
+    if (meta.contentImages.length > 0) {
+      contentImages = meta.contentImages;
+    }
     console.log(`[wechat] Title: ${effectiveTitle || '(empty)'}`);
     console.log(`[wechat] Author: ${effectiveAuthor || '(empty)'}`);
     console.log(`[wechat] Summary: ${effectiveSummary || '(empty)'}`);
+    console.log(`[wechat] Found ${contentImages.length} images to insert`);
   }
 
   if (effectiveTitle && effectiveTitle.length > 64) throw new Error(`Title too long: ${effectiveTitle.length} chars (max 64)`);
@@ -416,7 +480,7 @@ export async function postArticle(options: ArticleOptions): Promise<void> {
 
     if (effectiveHtmlFile && fs.existsSync(effectiveHtmlFile)) {
       console.log(`[wechat] Copying HTML content from: ${effectiveHtmlFile}`);
-      await copyHtmlFromBrowser(cdp, effectiveHtmlFile);
+      await copyHtmlFromBrowser(cdp, effectiveHtmlFile, contentImages);
       await sleep(500);
       console.log('[wechat] Pasting into editor...');
       await pasteFromClipboardInEditor(session);

skills/baoyu-slide-deck/SKILL.md

@@ -226,6 +226,7 @@ Schema: `references/config/preferences-schema.md`
 **1.2 Analyze Content**
 
 1. Save source content (if pasted, save as `source.md`)
+   - **Backup rule**: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
 2. Follow `references/analysis-framework.md` for content analysis
 3. Analyze content signals for style recommendations
 4. Detect source language
@@ -483,6 +484,7 @@ options:
    - Add slide-specific content
    - If `Layout:` specified, include layout guidance from `references/layouts.md`
 3. Save to `prompts/` directory
+   - **Backup rule**: If prompt file exists, rename to `prompts/NN-slide-{slug}-backup-YYYYMMDD-HHMMSS.md`
 
 **After generation**:
 - If `--prompts-only`, stop here and output prompt summary
@@ -539,7 +541,9 @@ options:
 **Standard flow**:
 1. Select available image generation skill
 2. Generate session ID: `slides-{topic-slug}-{timestamp}`
-3. Generate each slide sequentially with same session ID
+3. For each slide:
+   - **Backup rule**: If image file exists, rename to `NN-slide-{slug}-backup-YYYYMMDD-HHMMSS.png`
+   - Generate image sequentially with same session ID
 4. Report progress: "Generated X/N" (in user's language)
 5. Auto-retry once on failure before reporting error
 

skills/baoyu-xhs-images/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: baoyu-xhs-images
-description: Generates Xiaohongshu (Little Red Book) infographic series with 9 visual styles and 6 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
+description: Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
 ---
 
 # Xiaohongshu Infographic Series Generator
@@ -42,8 +42,8 @@ Break down complex content into eye-catching infographic series for Xiaohongshu
 
 | Dimension | Controls | Options |
 |-----------|----------|---------|
-| **Style** | Visual aesthetics: colors, lines, decorations | cute, fresh, warm, bold, minimal, retro, pop, notion, chalkboard |
-| **Layout** | Information structure: density, arrangement | sparse, balanced, dense, list, comparison, flow |
+| **Style** | Visual aesthetics: colors, lines, decorations | cute, fresh, warm, bold, minimal, retro, pop, notion, chalkboard, study-notes |
+| **Layout** | Information structure: density, arrangement | sparse, balanced, dense, list, comparison, flow, mindmap, quadrant |
 
 Style × Layout can be freely combined. Example: `--style notion --layout dense` creates an intellectual-looking knowledge card with high information density.
 
@@ -60,6 +60,7 @@ Style × Layout can be freely combined. Example: `--style notion --layout dense`
 | `pop` | Vibrant, energetic, eye-catching |
 | `notion` | Minimalist hand-drawn line art, intellectual |
 | `chalkboard` | Colorful chalk on black board, educational |
+| `study-notes` | Realistic handwritten photo style, blue pen + red annotations + yellow highlighter |
 
 Detailed style definitions: `references/presets/<style>.md`
 
@@ -73,6 +74,8 @@ Detailed style definitions: `references/presets/<style>.md`
 | `list` | Enumeration and ranking format (4-7 items) |
 | `comparison` | Side-by-side contrast layout |
 | `flow` | Process and timeline layout (3-6 steps) |
+| `mindmap` | Center radial mind map layout (4-8 branches) |
+| `quadrant` | Four-quadrant / circular section layout |
 
 Detailed layout definitions: `references/elements/canvas.md`
 
@@ -89,6 +92,7 @@ Detailed layout definitions: `references/elements/canvas.md`
 | Fun, exciting, wow, amazing | `pop` | sparse/list |
 | Knowledge, concept, productivity, SaaS | `notion` | dense/list |
 | Education, tutorial, learning, teaching, classroom | `chalkboard` | balanced/dense |
+| Notes, handwritten, study guide, knowledge, realistic, photo | `study-notes` | dense/list/mindmap |
 
 ## Outline Strategies
 
@@ -227,6 +231,7 @@ Read source content, save it if needed, and perform deep analysis.
 1. **Save source content** (if not already a file):
    - If user provides a file path: use as-is
    - If user pastes content: save to `source.md` in target directory
+   - **Backup rule**: If `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`
 2. Read source content
 3. **Deep analysis** following `references/workflows/analysis-framework.md`:
    - Content type classification (种草/干货/测评/教程/避坑...)
@@ -353,7 +358,9 @@ With confirmed outline + style + layout:
 
 **For each image (cover + content + ending)**:
 1. Save prompt to `prompts/NN-{type}-[slug].md` (in user's preferred language)
+   - **Backup rule**: If prompt file exists, rename to `prompts/NN-{type}-[slug]-backup-YYYYMMDD-HHMMSS.md`
 2. Generate image using confirmed style and layout
+   - **Backup rule**: If image file exists, rename to `NN-{type}-[slug]-backup-YYYYMMDD-HHMMSS.png`
 3. Report progress after each generation
 
 **Watermark Application** (if enabled in preferences):
@@ -417,17 +424,18 @@ Files:
 
 **Style × Layout Matrix** (✓✓ = highly recommended, ✓ = works well):
 
-| | sparse | balanced | dense | list | comparison | flow |
-|---|:---:|:---:|:---:|:---:|:---:|:---:|
-| cute | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ |
-| fresh | ✓✓ | ✓✓ | ✓ | ✓ | ✓ | ✓✓ |
-| warm | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ |
-| bold | ✓✓ | ✓ | ✓ | ✓✓ | ✓✓ | ✓ |
-| minimal | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ |
-| retro | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ |
-| pop | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ |
-| notion | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ |
-| chalkboard | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓✓ |
+| | sparse | balanced | dense | list | comparison | flow | mindmap | quadrant |
+|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| cute | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ |
+| fresh | ✓✓ | ✓✓ | ✓ | ✓ | ✓ | ✓✓ | ✓ | ✓ |
+| warm | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ |
+| bold | ✓✓ | ✓ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ |
+| minimal | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
+| retro | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ |
+| pop | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ |
+| notion | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ |
+| chalkboard | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ |
+| study-notes | ✗ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ |
 
 ## References
 

skills/baoyu-xhs-images/references/elements/canvas.md

@@ -51,6 +51,8 @@ Avoid placing critical content in these areas:
 | list | Vertical enumeration | 4-7 | Rankings, checklists, step guides |
 | comparison | Left vs Right | 2 sections | Before/after, pros/cons |
 | flow | Connected nodes | 3-6 steps | Processes, timelines, workflows |
+| mindmap | Center radial | 4-8 branches | Concept maps, brainstorming, topic overview |
+| quadrant | 4-section grid | 4 sections | SWOT analysis, priority matrix, classification |
 
 ## Layout by Position
 
@@ -106,3 +108,15 @@ For multi-element compositions:
 - Directional flow (top→bottom or left→right)
 - Connected nodes with arrows
 - Clear progression indicators
+
+### Mindmap Layout
+- Central topic node
+- Radial branches outward
+- Hierarchical sub-branches
+- Organic curved connections
+
+### Quadrant Layout
+- 4-section grid (2×2)
+- Clear axis labels
+- Each quadrant with distinct content
+- Optional circular variant for cycles

skills/baoyu-xhs-images/references/presets/study-notes.md

@@ -0,0 +1,115 @@
+---
+name: study-notes
+category: realistic
+---
+
+# Study Notes Style
+
+Realistic handwritten photo aesthetic - student notes style, dense and messy but readable.
+
+## Element Combination
+
+```yaml
+canvas:
+  ratio: portrait-3-4
+  grid: single
+
+image_effects:
+  cutout: none
+  stroke: none
+  filter: natural-photo
+
+typography:
+  decorated: none
+  tags: none
+  direction: horizontal
+
+decorations:
+  emphasis: circle-mark | underline | checkmark | cross | star-simple
+  background: lined-paper-white
+  doodles: arrows-simple | margin-notes | corrections | explanatory-diagrams
+  frames: none
+```
+
+## Color Palette (Three-Color Annotation System)
+
+| Role | Colors | Hex |
+|------|--------|-----|
+| Primary | Blue ballpoint, Black ink | #1E3A5F, #1A1A1A |
+| Highlights | Yellow highlighter | #FFFF00 (50% opacity) |
+| Accents | Red pen (circles, underlines) | #CC0000 |
+| Background | White lined paper | #FFFFFF |
+
+## Visual Elements
+
+- Realistic photo perspective: top-down view of study desk
+- Hand holding blue ballpoint pen, actively underlining
+- Extremely dense handwritten content, filling entire page
+- Red pen annotations: circles, underlines, stars, boxes
+- Yellow highlighter marking key terms
+- Correction marks, cramped notes squeezed into margins
+- Simple hand-drawn symbols: → * ✓ ✗ !
+- Varying pen pressure creating lighter and darker strokes
+
+## Typography
+
+- Authentic student handwriting
+- Messy but readable, clear structure maintained
+- Varying font sizes (large titles, small body, tiny margin notes)
+- CJK optimized
+
+## Content Structure
+
+Three-section layout:
+
+### Top Section
+- Core topic (circled multiple times in red)
+- First section title + 3-4 key points
+- Arrow connections, red underlines
+
+### Middle Section
+- Second section title (red pen box)
+- Numbered steps ①②③
+- Specific methods and supplementary notes
+
+### Bottom Section
+- Third section title (red star)
+- Time points / key metrics
+- Key quotes / core tips (tiny corner notes)
+
+## Best Layout Pairings
+
+| Layout | Compatibility | Use Case |
+|--------|---------------|----------|
+| sparse | ✗ | Not suitable - style requires dense content |
+| balanced | ✓ | When content is lighter |
+| dense | ✓✓ | Best fit - knowledge notes, summaries |
+| list | ✓✓ | Step checklists, rankings |
+| comparison | ✓ | Comparative analysis |
+| flow | ✓ | Process flows |
+| mindmap | ✓✓ | Mind map notes |
+| quadrant | ✓ | Quadrant analysis |
+
+## Best For
+
+- Study guides, exam notes
+- Knowledge organization, framework summaries
+- Tutorial summaries, quick notes
+- "Top student notes" style content
+- Knowledge sharing requiring authentic feel
+
+## Style Rules
+
+### DO ✓
+- Keep content extremely dense
+- Use simple symbols (→ * ✓ ✗ !)
+- Annotate key points with red pen
+- Include correction marks
+- Squeeze tiny notes into margins
+
+### DON'T ✗
+- Use complex emojis
+- Leave too much whitespace
+- Make neat, tidy layouts
+- Add colorful decorations
+- Include cartoon elements