chore: release v1.27.0

Preprocess markdown with remark-cjk-friendly to properly handle
CJK emphasis markers before HTML conversion.

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.26.0"
+    "version": "1.27.0"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,14 @@
 
 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

CHANGELOG.zh.md

@@ -2,6 +2,14 @@
 
 [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

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

@@ -13,8 +13,7 @@ Scripts in `scripts/` subdirectory. Replace `${SKILL_DIR}` with this SKILL.md's
 
 | Script | Purpose |
 |--------|---------|
-| `scripts/main.ts` | Main entry point with CLI options |
-| `scripts/cjk-emphasis.ts` | Fix CJK emphasis/bold punctuation issues |
+| `scripts/main.ts` | Main entry point with CLI options (uses remark-cjk-friendly for CJK emphasis) |
 | `scripts/quotes.ts` | Replace ASCII quotes with fullwidth quotes |
 | `scripts/autocorrect.ts` | Add CJK/English spacing via autocorrect |
 

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

@@ -1,314 +0,0 @@
-const CJK_PUNCT_COMMON = "。．，、？！：；";
-const CJK_OPENING_PUNCT = "（〔〖〘〚「『〈《【\u201C\u2018";
-const CJK_CLOSING_PUNCT = "）〕〗〙〛」』〉》】\u201D\u2019" + CJK_PUNCT_COMMON;
-const CJK_SCRIPTS =
-  "\\p{Script=Han}\\p{Script=Hiragana}\\p{Script=Katakana}\\p{Script=Hangul}";
-
-export const CJK_CLOSING_PUNCT_RE = new RegExp(`[${CJK_CLOSING_PUNCT}]`);
-export const CJK_OPENING_PUNCT_RE = new RegExp(`^[${CJK_OPENING_PUNCT}]`);
-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;
-  while (i < text.length) {
-    if (text[i] !== "`") {
-      i += 1;
-      continue;
-    }
-
-    let run = 1;
-    while (i + run < text.length && text[i + run] === "`") {
-      run += 1;
-    }
-
-    const start = i;
-    let j = i + run;
-    let found = false;
-    while (j < text.length) {
-      if (text[j] !== "`") {
-        j += 1;
-        continue;
-      }
-      let closeRun = 1;
-      while (j + closeRun < text.length && text[j + closeRun] === "`") {
-        closeRun += 1;
-      }
-      if (closeRun === run) {
-        ranges.push([start, j + closeRun - 1]);
-        i = j + closeRun;
-        found = true;
-        break;
-      }
-      j += closeRun;
-    }
-
-    if (!found) {
-      i = start + run;
-    }
-  }
-  return ranges;
-}
-
-function isEscaped(text: string, pos: number): boolean {
-  let count = 0;
-  for (let i = pos - 1; i >= 0 && text[i] === "\\"; i -= 1) {
-    count += 1;
-  }
-  return count % 2 === 1;
-}
-
-function isWhitespaceChar(ch: string | undefined): boolean {
-  return !ch || /\s/u.test(ch);
-}
-
-function isPunctuationOrSymbol(ch: string | undefined): boolean {
-  return !!ch && PUNCT_OR_SYMBOL_RE.test(ch);
-}
-
-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<{
-    pos: number;
-    canOpen: boolean;
-    canClose: boolean;
-  }> = [];
-  let cursor = 0;
-  while (cursor < normalized.length - 1) {
-    if (rangeIndex < codeRanges.length && cursor >= codeRanges[rangeIndex][0]) {
-      if (cursor <= codeRanges[rangeIndex][1]) {
-        cursor = codeRanges[rangeIndex][1] + 1;
-        continue;
-      }
-      rangeIndex += 1;
-      continue;
-    }
-
-    if (
-      normalized[cursor] === "*" &&
-      normalized[cursor + 1] === "*" &&
-      normalized[cursor - 1] !== "*" &&
-      normalized[cursor + 2] !== "*" &&
-      !isEscaped(normalized, cursor)
-    ) {
-      const before = normalized[cursor - 1];
-      const after = normalized[cursor + 2];
-      const beforeIsSpace = isWhitespaceChar(before);
-      const afterIsSpace = isWhitespaceChar(after);
-      const beforeIsPunct = isPunctuationOrSymbol(before);
-      const afterIsPunct = isPunctuationOrSymbol(after);
-      const leftFlanking =
-        !afterIsSpace && (!afterIsPunct || beforeIsSpace || beforeIsPunct);
-      const rightFlanking =
-        !beforeIsSpace && (!beforeIsPunct || afterIsSpace || afterIsPunct);
-      const cjkPunctBefore = !!before && CJK_CLOSING_PUNCT_RE.test(before);
-      const wordAfter = !!after && WORD_CHAR_RE.test(after);
-
-      delimiters.push({
-        pos: cursor,
-        canOpen: leftFlanking,
-        canClose: rightFlanking || (cjkPunctBefore && wordAfter),
-      });
-      cursor += 2;
-      continue;
-    }
-
-    cursor += 1;
-  }
-
-  const stack: Array<{ pos: number }> = [];
-  const pairs: Array<{ open: number; close: number }> = [];
-  for (const delimiter of delimiters) {
-    if (delimiter.canClose) {
-      let openerIndex = -1;
-      for (let j = stack.length - 1; j >= 0; j -= 1) {
-        openerIndex = j;
-        break;
-      }
-      if (openerIndex !== -1) {
-        const opener = stack.splice(openerIndex, 1)[0];
-        pairs.push({ open: opener.pos, close: delimiter.pos });
-      }
-    }
-    if (delimiter.canOpen) {
-      stack.push({ pos: delimiter.pos });
-    }
-  }
-
-  if (pairs.length === 0) return normalized;
-
-  const insertPositions = new Set<number>();
-  for (const pair of pairs) {
-    const insideLast = normalized[pair.close - 1];
-    const afterClose = normalized[pair.close + 2];
-    if (!afterClose) continue;
-    if (
-      CJK_CLOSING_PUNCT_RE.test(insideLast) &&
-      WORD_CHAR_RE.test(afterClose)
-    ) {
-      insertPositions.add(pair.close + 2);
-    }
-  }
-
-  if (insertPositions.size === 0) return normalized;
-
-  let result = "";
-  for (let idx = 0; idx < normalized.length; idx += 1) {
-    if (insertPositions.has(idx)) {
-      result += " ";
-    }
-    result += normalized[idx];
-  }
-  if (insertPositions.has(normalized.length)) {
-    result += " ";
-  }
-  return result;
-}
-
-export function fixCjkEmphasisSpacing(content: string): string {
-  const parts = content.split(/(^```[\s\S]*?^```|^~~~[\s\S]*?^~~~)/m);
-  return parts
-    .map((part, i) => {
-      if (i % 2 === 1) return part;
-      const blocks = part.split(/(\n\s*\n+)/);
-      return blocks
-        .map((block, index) => {
-          if (index % 2 === 1) return block;
-          return fixCjkEmphasisSpacingInBlock(block);
-        })
-        .join("");
-    })
-    .join("");
-}

skills/baoyu-format-markdown/scripts/main.ts

@@ -1,17 +1,12 @@
 import { readFileSync, writeFileSync } from "fs";
 import { unified } from "unified";
 import remarkParse from "remark-parse";
+import remarkCjkFriendly from "remark-cjk-friendly";
 import remarkGfm from "remark-gfm";
 import remarkFrontmatter from "remark-frontmatter";
 import remarkStringify from "remark-stringify";
 import { visit } from "unist-util-visit";
 import YAML from "yaml";
-import {
-  fixCjkEmphasisSpacing,
-  CJK_CLOSING_PUNCT_RE,
-  CJK_OPENING_PUNCT_RE,
-  CJK_CHAR_RE,
-} from "./cjk-emphasis";
 import { replaceQuotes } from "./quotes";
 import { applyAutocorrect } from "./autocorrect";
 
@@ -36,6 +31,12 @@ const DEFAULT_OPTIONS: Required<FormatOptions> = {
   emphasis: true,
 };
 
+function decodeHtmlEntities(text: string): string {
+  return text.replace(/&#x([0-9A-Fa-f]+);/g, (_, hex) =>
+    String.fromCodePoint(parseInt(hex, 16))
+  );
+}
+
 function formatFrontmatter(value: string): string | null {
   try {
     const doc = YAML.parseDocument(value);
@@ -49,12 +50,9 @@ function formatMarkdownContent(
   content: string,
   options: Required<FormatOptions>
 ): string {
-  if (options.emphasis) {
-    content = fixCjkEmphasisSpacing(content);
-  }
-
   const processor = unified()
     .use(remarkParse)
+    .use(options.emphasis ? remarkCjkFriendly : [])
     .use(remarkGfm)
     .use(remarkFrontmatter, ["yaml"])
     .use(remarkStringify, {
@@ -63,7 +61,7 @@ function formatMarkdownContent(
 
   const tree = processor.parse(content);
 
-  visit(tree, (node, _index, parent) => {
+  visit(tree, (node) => {
     if (node.type === "text" && options.quotes) {
       const textNode = node as { value: string };
       textNode.value = replaceQuotes(textNode.value);
@@ -77,54 +75,11 @@ function formatMarkdownContent(
       }
       return;
     }
-    if (
-      options.emphasis &&
-      (node.type === "strong" ||
-        node.type === "emphasis" ||
-        node.type === "delete") &&
-      parent
-    ) {
-      const siblings = (parent as { children: typeof node[] }).children;
-      const idx = siblings.indexOf(node);
-      const children = (node as { children: typeof node[] }).children;
-      if (!children || children.length === 0) return;
-
-      const lastChild = children[children.length - 1];
-      if (lastChild.type === "text") {
-        const lastText = (lastChild as { value: string }).value;
-        if (
-          CJK_CLOSING_PUNCT_RE.test(lastText.slice(-1)) &&
-          idx + 1 < siblings.length
-        ) {
-          const nextSib = siblings[idx + 1];
-          if (nextSib.type === "text") {
-            const nextText = (nextSib as { value: string }).value;
-            if (CJK_CHAR_RE.test(nextText.charAt(0))) {
-              (nextSib as { value: string }).value = " " + nextText;
-            }
-          }
-        }
-      }
-
-      const firstChild = children[0];
-      if (firstChild.type === "text") {
-        const firstText = (firstChild as { value: string }).value;
-        if (CJK_OPENING_PUNCT_RE.test(firstText) && idx > 0) {
-          const prevSib = siblings[idx - 1];
-          if (prevSib.type === "text") {
-            const prevText = (prevSib as { value: string }).value;
-            if (CJK_CHAR_RE.test(prevText.charAt(prevText.length - 1))) {
-              (prevSib as { value: string }).value = prevText + " ";
-            }
-          }
-        }
-      }
-    }
   });
 
   let result = processor.stringify(tree);
   if (options.emphasis) {
-    result = fixCjkEmphasisSpacing(result);
+    result = decodeHtmlEntities(result);
   }
   return result;
 }

skills/baoyu-format-markdown/scripts/package.json

@@ -1,5 +1,6 @@
 {
   "dependencies": {
+    "remark-cjk-friendly": "^1.1.0",
     "remark-frontmatter": "^5.0.0",
     "remark-gfm": "^4.0.1",
     "remark-parse": "^11.0.0",

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.
 
@@ -182,13 +184,20 @@ Recommend 3-5 layout×style combinations based on:
 
 ### Step 4: Confirm Options
 
-Present all options in single confirmation:
-1. **Combination** (always): 3+ options with rationale
-2. **Aspect** (always): landscape/portrait/square
-3. **Language** (only if source ≠ user language): which language for text
+Use **single AskUserQuestion call** with multiple questions to confirm all options together:
+
+| Question | When | Options |
+|----------|------|---------|
+| **Combination** | Always | 3+ layout×style combos with rationale |
+| **Aspect** | Always | landscape (16:9), portrait (9:16), square (1:1) |
+| **Language** | Only if source ≠ user language | Language for text content |
+
+**Important**: Do NOT split into separate AskUserQuestion calls. Combine all applicable questions into one call.
 
 ### 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 +208,10 @@ 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/md/package.json

@@ -0,0 +1,14 @@
+{
+  "dependencies": {
+    "fflate": "^0.8.2",
+    "front-matter": "^4.0.2",
+    "highlight.js": "^11.11.1",
+    "juice": "^11.0.1",
+    "marked": "^15.0.6",
+    "reading-time": "^1.5.0",
+    "remark-cjk-friendly": "^1.1.0",
+    "remark-parse": "^11.0.0",
+    "remark-stringify": "^11.0.0",
+    "unified": "^11.0.5"
+  }
+}

skills/baoyu-markdown-to-html/scripts/md/render.ts

@@ -7,6 +7,10 @@ import frontMatter from "front-matter";
 import hljs from "highlight.js/lib/core";
 import { marked, type RendererObject, type Tokens } from "marked";
 import readingTime, { type ReadTimeResults } from "reading-time";
+import { unified } from "unified";
+import remarkParse from "remark-parse";
+import remarkCjkFriendly from "remark-cjk-friendly";
+import remarkStringify from "remark-stringify";
 
 import {
   markedAlert,
@@ -552,12 +556,47 @@ interface CliOptions {
   keepTitle: boolean;
 }
 
+function preprocessCjkEmphasis(markdown: string): string {
+  const processor = unified()
+    .use(remarkParse)
+    .use(remarkCjkFriendly);
+  const tree = processor.parse(markdown);
+  const visit = (node: any, parent?: any, index?: number) => {
+    if (node.children) {
+      for (let i = 0; i < node.children.length; i++) {
+        visit(node.children[i], node, i);
+      }
+    }
+    if (node.type === "strong" && parent && typeof index === "number") {
+      const text = extractText(node);
+      parent.children[index] = { type: "html", value: `<strong>${text}</strong>` };
+    }
+    if (node.type === "emphasis" && parent && typeof index === "number") {
+      const text = extractText(node);
+      parent.children[index] = { type: "html", value: `<em>${text}</em>` };
+    }
+  };
+  const extractText = (node: any): string => {
+    if (node.type === "text") return node.value;
+    if (node.children) return node.children.map(extractText).join("");
+    return "";
+  };
+  visit(tree);
+  const stringify = unified().use(remarkStringify);
+  let result = stringify.stringify(tree);
+  result = result.replace(/&#x([0-9A-Fa-f]+);/g, (_, hex) =>
+    String.fromCodePoint(parseInt(hex, 16))
+  );
+  return result;
+}
+
 function renderMarkdown(raw: string, renderer: RendererAPI): {
   html: string;
   readingTime: ReadTimeResults;
 } {
+  const preprocessed = preprocessCjkEmphasis(raw);
   const { markdownContent, readingTime: readingTimeResult } =
-    renderer.parseFrontMatterAndContent(raw);
+    renderer.parseFrontMatterAndContent(preprocessed);
 
   const html = marked.parse(markdownContent) as string;
 

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 11 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.
+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
@@ -42,7 +42,7 @@ 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, notebook, study-notes |
+| **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.
@@ -60,7 +60,6 @@ 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 |
-| `notebook` | Hand-drawn infographic style, watercolor rendering + Morandi palette |
 | `study-notes` | Realistic handwritten photo style, blue pen + red annotations + yellow highlighter |
 
 Detailed style definitions: `references/presets/<style>.md`
@@ -93,7 +92,6 @@ 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, hand-drawn, infographic, study, mindmap, Morandi | `notebook` | mindmap/balanced/dense |
 | Notes, handwritten, study guide, knowledge, realistic, photo | `study-notes` | dense/list/mindmap |
 
 ## Outline Strategies
@@ -233,6 +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...)
@@ -359,7 +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):
@@ -434,7 +435,6 @@ Files:
 | pop | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ |
 | notion | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ |
 | chalkboard | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ |
-| notebook | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ |
 | study-notes | ✗ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ |
 
 ## References

skills/baoyu-xhs-images/references/presets/notebook.md

@@ -1,76 +0,0 @@
----
-name: notebook
-category: educational
----
-
-# Notebook Style
-
-Hand-drawn infographic / study notes aesthetic with watercolor rendering and Morandi color palette.
-
-## Element Combination
-
-```yaml
-canvas:
-  ratio: portrait-3-4
-  grid: single | dual | triptych
-
-image_effects:
-  cutout: soft
-  stroke: none | watercolor-edge
-  filter: muted-tones | morandi
-
-typography:
-  decorated: watercolor-highlight | handwritten-bold
-  tags: pill | rounded-rect
-  direction: horizontal
-
-decorations:
-  emphasis: circle-mark | underline | checkmark
-  background: paper-texture | watercolor-wash
-  doodles: hand-drawn-lines | mindmap-nodes | speech-bubbles | hearts | peace-dove
-  frames: rounded-rect | none
-```
-
-## Color Palette (Morandi Tones)
-
-| Role | Colors | Hex |
-|------|--------|-----|
-| Primary | Sage green, Teal | #A8B5A0, #4A7C7C |
-| Background | Off-white, Warm paper | #FAF8F5, #F5F0E8 |
-| Accents | Dust blue, Warm grey, Terracotta | #8FA3B0, #9A9590, #C4A484 |
-
-## Visual Elements
-
-- Bold handwritten titles with watercolor wash blocks (sage green/teal backgrounds)
-- Black line illustrations, slightly imperfect, simulating ink effect
-- Soft paper texture background, mimicking watercolor paper
-- Mindmap nodes, list boxes, explanatory doodles
-- Symbolic icons: hearts, speech bubbles, peace dove, handshake
-- Flat lighting, vector illustration feel with analog texture
-
-## Typography
-
-- Bold handwritten fonts
-- Watercolor wash effect backgrounds
-- Clear and readable, CJK optimized
-
-## Best Layout Pairings
-
-| Layout | Compatibility | Use Case |
-|--------|---------------|----------|
-| sparse | ✓✓ | Covers, quotes |
-| balanced | ✓✓ | Standard content cards |
-| dense | ✓✓ | Knowledge cards, checklists |
-| list | ✓✓ | Step guides, rankings |
-| comparison | ✓✓ | Before/after, contrasts |
-| flow | ✓✓ | Processes, timelines |
-| mindmap | ✓✓ | Mind maps |
-| quadrant | ✓✓ | Quadrant analysis, circular sections |
-
-## Best For
-
-- Study notes, knowledge summaries
-- Mind maps, infographics
-- Tutorials, knowledge sharing
-- Bullet journal style content
-- Concept explanations, framework overviews