chore: release v1.56.1

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.55.0"
+    "version": "1.56.1"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,20 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.56.1 - 2026-03-08
+
+### Fixes
+- `baoyu-post-to-weibo`: simplify article image insertion with Backspace-based placeholder deletion for ProseMirror compatibility
+
+## 1.56.0 - 2026-03-08
+
+### Features
+- `baoyu-article-illustrator`: preset-first selection flow with categorized style presets by content type
+- `baoyu-xhs-images`: streamline workflow from 6 to 4 steps with Smart Confirm (Quick/Customize/Detailed paths)
+
+### Fixes
+- `baoyu-post-to-wechat`: improve image upload reliability with file chooser interception and fallback
+
 ## 1.55.0 - 2026-03-08
 
 ### Features

CHANGELOG.zh.md

@@ -2,6 +2,20 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.56.1 - 2026-03-08
+
+### 修复
+- `baoyu-post-to-weibo`：简化头条文章图片插入逻辑，使用 Backspace 按键替代复杂的 deleteContents 方案，兼容 ProseMirror 编辑器
+
+## 1.56.0 - 2026-03-08
+
+### 新功能
+- `baoyu-article-illustrator`：预设优先选择流程，按内容类型分类的风格预设
+- `baoyu-xhs-images`：精简工作流从 6 步到 4 步，新增智能确认（快速/自定义/详细三种路径）
+
+### 修复
+- `baoyu-post-to-wechat`：通过文件选择器拦截改进图片上传可靠性
+
 ## 1.55.0 - 2026-03-08
 
 ### 新功能

skills/baoyu-article-illustrator/SKILL.md

@@ -82,13 +82,13 @@ Full procedures: [references/workflow.md](references/workflow.md#step-2-setup--a
 
 ### Step 3: Confirm Settings ⚠️
 
-**ONE AskUserQuestion, max 4 Qs. Q1-Q3 REQUIRED.**
+**ONE AskUserQuestion, max 4 Qs. Q1-Q2 REQUIRED. Q3 required unless preset chosen.**
 
 | Q | Options |
 |---|---------|
-| **Q1: Type** | [Recommended], infographic, scene, flowchart, comparison, framework, timeline, mixed |
+| **Q1: Preset or Type** | [Recommended preset], [alt preset], or manual: infographic, scene, flowchart, comparison, framework, timeline, mixed |
 | **Q2: Density** | minimal (1-2), balanced (3-5), per-section (Recommended), rich (6+) |
-| **Q3: Style** | [Recommended], minimal-flat, sci-fi, hand-drawn, editorial, scene, poster, Other |
+| **Q3: Style** | [Recommended], minimal-flat, sci-fi, hand-drawn, editorial, scene, poster, Other — **skip if preset chosen** |
 | Q4: Language | When article language ≠ EXTEND.md setting |
 
 Full procedures: [references/workflow.md](references/workflow.md#step-3-confirm-settings-)

skills/baoyu-article-illustrator/references/style-presets.md

@@ -2,26 +2,67 @@
 
 `--preset X` expands to a type + style combination. Users can override either dimension.
 
-| --preset | Type | Style |
-|----------|------|-------|
-| `tech-explainer` | `infographic` | `blueprint` |
-| `knowledge-base` | `infographic` | `vector-illustration` |
-| `saas-guide` | `infographic` | `notion` |
-| `data-report` | `infographic` | `editorial` |
-| `science-paper` | `infographic` | `scientific` |
-| `tutorial` | `flowchart` | `vector-illustration` |
-| `process-flow` | `flowchart` | `notion` |
-| `system-design` | `framework` | `blueprint` |
-| `architecture` | `framework` | `vector-illustration` |
-| `versus` | `comparison` | `vector-illustration` |
-| `business-compare` | `comparison` | `elegant` |
-| `storytelling` | `scene` | `warm` |
-| `lifestyle` | `scene` | `watercolor` |
-| `history` | `timeline` | `elegant` |
-| `evolution` | `timeline` | `warm` |
-| `opinion-piece` | `scene` | `screen-print` |
-| `editorial-poster` | `comparison` | `screen-print` |
-| `cinematic` | `scene` | `screen-print` |
+## By Category
+
+### Technical & Engineering
+
+| --preset | Type | Style | Best For |
+|----------|------|-------|----------|
+| `tech-explainer` | `infographic` | `blueprint` | API docs, system metrics, technical deep-dives |
+| `system-design` | `framework` | `blueprint` | Architecture diagrams, system design |
+| `architecture` | `framework` | `vector-illustration` | Component relationships, module structure |
+| `science-paper` | `infographic` | `scientific` | Research findings, lab results, academic |
+
+### Knowledge & Education
+
+| --preset | Type | Style | Best For |
+|----------|------|-------|----------|
+| `knowledge-base` | `infographic` | `vector-illustration` | Concept explainers, tutorials, how-to |
+| `saas-guide` | `infographic` | `notion` | Product guides, SaaS docs, tool walkthroughs |
+| `tutorial` | `flowchart` | `vector-illustration` | Step-by-step tutorials, setup guides |
+| `process-flow` | `flowchart` | `notion` | Workflow documentation, onboarding flows |
+
+### Data & Analysis
+
+| --preset | Type | Style | Best For |
+|----------|------|-------|----------|
+| `data-report` | `infographic` | `editorial` | Data journalism, metrics reports, dashboards |
+| `versus` | `comparison` | `vector-illustration` | Tech comparisons, framework shootouts |
+| `business-compare` | `comparison` | `elegant` | Product evaluations, strategy options |
+
+### Narrative & Creative
+
+| --preset | Type | Style | Best For |
+|----------|------|-------|----------|
+| `storytelling` | `scene` | `warm` | Personal essays, reflections, growth stories |
+| `lifestyle` | `scene` | `watercolor` | Travel, wellness, lifestyle, creative |
+| `history` | `timeline` | `elegant` | Historical overviews, milestones |
+| `evolution` | `timeline` | `warm` | Progress narratives, growth journeys |
+
+### Editorial & Opinion
+
+| --preset | Type | Style | Best For |
+|----------|------|-------|----------|
+| `opinion-piece` | `scene` | `screen-print` | Op-eds, commentary, critical essays |
+| `editorial-poster` | `comparison` | `screen-print` | Debate, contrasting viewpoints |
+| `cinematic` | `scene` | `screen-print` | Dramatic narratives, cultural essays |
+
+## Content Type → Preset Recommendations
+
+Use this table during Step 3 to recommend presets based on Step 2 content analysis:
+
+| Content Type (Step 2) | Primary Preset | Alternatives |
+|------------------------|----------------|--------------|
+| Technical | `tech-explainer` | `system-design`, `architecture` |
+| Tutorial | `tutorial` | `process-flow`, `knowledge-base` |
+| Methodology / Framework | `system-design` | `architecture`, `process-flow` |
+| Data / Metrics | `data-report` | `versus`, `tech-explainer` |
+| Comparison / Review | `versus` | `business-compare`, `editorial-poster` |
+| Narrative / Personal | `storytelling` | `lifestyle`, `evolution` |
+| Opinion / Editorial | `opinion-piece` | `cinematic`, `editorial-poster` |
+| Historical / Timeline | `history` | `evolution` |
+| Academic / Research | `science-paper` | `tech-explainer`, `data-report` |
+| SaaS / Product | `saas-guide` | `knowledge-base`, `process-flow` |
 
 ## Override Examples
 

skills/baoyu-article-illustrator/references/workflow.md

@@ -165,9 +165,16 @@ For each reference image:
 
 **Do NOT skip.** Use ONE AskUserQuestion call with max 4 questions. **Q1, Q2, Q3 are ALL REQUIRED.**
 
-### Q1: Illustration Type ⚠️ REQUIRED
-- [Recommended based on analysis] (Recommended)
-- infographic / scene / flowchart / comparison / framework / timeline / mixed
+### Q1: Preset or Type ⚠️ REQUIRED
+
+Based on Step 2 content analysis, recommend a preset first (sets both type & style). Look up [style-presets.md](style-presets.md) "Content Type → Preset Recommendations" table.
+
+- [Recommended preset] — [brief: type + style + why] (Recommended)
+- [Alternative preset] — [brief]
+- Or choose type manually: infographic / scene / flowchart / comparison / framework / timeline / mixed
+
+**If user picks a preset → skip Q3** (type & style both resolved).
+**If user picks a type → Q3 is REQUIRED.**
 
 ### Q2: Density ⚠️ REQUIRED - DO NOT SKIP
 - minimal (1-2) - Core concepts only
@@ -175,7 +182,7 @@ For each reference image:
 - per-section - At least 1 per section/chapter (Recommended)
 - rich (6+) - Comprehensive coverage
 
-### Q3: Style ⚠️ REQUIRED (ALWAYS ask, even with preferred_style in EXTEND.md)
+### Q3: Style ⚠️ REQUIRED (skip if preset chosen in Q1)
 
 If EXTEND.md has `preferred_style`:
 - [Custom style name + brief description] (Recommended)
@@ -191,14 +198,14 @@ If no `preferred_style` (present Core Styles first):
 
 **Core Styles** (simplified selection):
 
-| Core Style | Best For |
-|------------|----------|
-| `minimal-flat` | General, knowledge sharing, SaaS |
-| `sci-fi` | AI, frontier tech, system design |
-| `hand-drawn` | Relaxed, reflective, casual |
-| `editorial` | Processes, data, journalism |
-| `scene` | Narratives, emotional, lifestyle |
-| `poster` | Opinion, editorial, cultural, cinematic |
+| Core Style | Maps To | Best For |
+|------------|---------|----------|
+| `minimal-flat` | notion | General, knowledge sharing, SaaS |
+| `sci-fi` | blueprint | AI, frontier tech, system design |
+| `hand-drawn` | sketch/warm | Relaxed, reflective, casual |
+| `editorial` | editorial | Processes, data, journalism |
+| `scene` | warm/watercolor | Narratives, emotional, lifestyle |
+| `poster` | screen-print | Opinion, editorial, cultural, cinematic |
 
 Style selection based on Type × Style compatibility matrix (styles.md).
 Full specs: `styles/<style>.md`

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

@@ -551,37 +551,126 @@ export async function postToWeChat(options: WeChatBrowserOptions): Promise<void>
     const absolutePaths = images.map(p => path.isAbsolute(p) ? p : path.resolve(process.cwd(), p));
     console.log(`[wechat-browser] Images: ${absolutePaths.join(', ')}`);
 
-    const { root } = await cdp.send<{ root: { nodeId: number } }>('DOM.getDocument', {}, { sessionId });
+    // --- PRIMARY approach: intercept file chooser dialog ---
+    let uploadSuccess = false;
+    try {
+      console.log('[wechat-browser] [primary] Enabling file chooser interception...');
+      await cdp.send('Page.setInterceptFileChooserDialog', { enabled: true }, { sessionId });
 
-    // Try primary selector, then fallback to any multi-file image input
-    let { nodeId } = await cdp.send<{ nodeId: number }>('DOM.querySelector', {
-      nodeId: root.nodeId,
-      selector: '.js_upload_btn_container input[type=file]',
-    }, { sessionId });
+      // Set up listener for file chooser opened event BEFORE clicking
+      const fileChooserPromise = new Promise<{ backendNodeId: number; mode: string }>((resolve, reject) => {
+        const timeout = setTimeout(() => reject(new Error('File chooser dialog not opened within 10s')), 10_000);
+        cdp!.on('Page.fileChooserOpened', (params: unknown) => {
+          clearTimeout(timeout);
+          const p = params as { backendNodeId: number; mode: string };
+          console.log(`[wechat-browser] [primary] File chooser opened: backendNodeId=${p.backendNodeId}, mode=${p.mode}`);
+          resolve(p);
+        });
+      });
 
-    if (!nodeId) {
-      console.log('[wechat-browser] Primary file input not found, trying fallback selector...');
-      const fallback = await cdp.send<{ nodeId: number }>('DOM.querySelector', {
-        nodeId: root.nodeId,
-        selector: 'input[type=file][multiple][accept*="image"]',
+      // Trigger file chooser by calling .click() on the file input with userGesture
+      const fileInputSelectors = [
+        '.js_upload_btn_container input[type=file]',
+        'input[type=file][multiple][accept*="image"]',
+        'input[type=file][accept*="image"]',
+        'input[type=file][multiple]',
+        'input[type=file]',
+      ];
+
+      console.log('[wechat-browser] [primary] Clicking file input via JS .click() with userGesture...');
+      const clickResult = await cdp.send<{ result: { value: string } }>('Runtime.evaluate', {
+        expression: `
+          (function() {
+            const selectors = ${JSON.stringify(fileInputSelectors)};
+            for (const sel of selectors) {
+              const el = document.querySelector(sel);
+              if (el) {
+                el.click();
+                return JSON.stringify({ clicked: sel });
+              }
+            }
+            const debug = [];
+            document.querySelectorAll('input[type=file]').forEach((inp, i) => {
+              debug.push({ i, accept: inp.accept, multiple: inp.multiple, parentClass: inp.parentElement?.className?.slice(0, 60) });
+            });
+            return JSON.stringify({ error: 'no file input found', fileInputs: debug });
+          })()
+        `,
+        returnByValue: true,
+        userGesture: true,
       }, { sessionId });
-      nodeId = fallback.nodeId;
+      console.log(`[wechat-browser] [primary] Click result: ${clickResult.result.value}`);
+
+      const clickStatus = JSON.parse(clickResult.result.value);
+      if (clickStatus.error) {
+        throw new Error(`File input not found: ${clickStatus.error}`);
+      }
+
+      // Wait for the file chooser event
+      console.log('[wechat-browser] [primary] Waiting for file chooser dialog...');
+      const chooser = await fileChooserPromise;
+
+      console.log(`[wechat-browser] [primary] Setting files via backendNodeId=${chooser.backendNodeId}...`);
+      await cdp.send('DOM.setFileInputFiles', {
+        files: absolutePaths,
+        backendNodeId: chooser.backendNodeId,
+      }, { sessionId });
+      console.log('[wechat-browser] [primary] Files set successfully via file chooser interception');
+      uploadSuccess = true;
+    } catch (primaryErr) {
+      console.log(`[wechat-browser] [primary] File chooser approach failed: ${primaryErr instanceof Error ? primaryErr.message : String(primaryErr)}`);
+      // Disable interception before falling back
+      try { await cdp.send('Page.setInterceptFileChooserDialog', { enabled: false }, { sessionId }); } catch {}
     }
 
-    if (!nodeId) throw new Error('File input not found');
+    // --- FALLBACK approach: direct DOM.setFileInputFiles on nodeId ---
+    if (!uploadSuccess) {
+      console.log('[wechat-browser] [fallback] Trying direct DOM.setFileInputFiles...');
+      const { root } = await cdp.send<{ root: { nodeId: number } }>('DOM.getDocument', {}, { sessionId });
 
-    await cdp.send('DOM.setFileInputFiles', {
-      nodeId,
-      files: absolutePaths,
-    }, { sessionId });
+      const fileInputSelectors = [
+        '.js_upload_btn_container input[type=file]',
+        'input[type=file][multiple][accept*="image"]',
+        'input[type=file][accept*="image"]',
+        'input[type=file][multiple]',
+        'input[type=file]',
+      ];
 
-    // Dispatch change event to trigger the upload
-    await cdp.send('Runtime.evaluate', {
-      expression: `
-        const fileInput = document.querySelector('.js_upload_btn_container input[type=file]') || document.querySelector('input[type=file][multiple][accept*="image"]');
-        if (fileInput) fileInput.dispatchEvent(new Event('change', { bubbles: true }));
-      `,
-    }, { sessionId });
+      let nodeId = 0;
+      for (const sel of fileInputSelectors) {
+        const result = await cdp.send<{ nodeId: number }>('DOM.querySelector', { nodeId: root.nodeId, selector: sel }, { sessionId });
+        if (result.nodeId) {
+          console.log(`[wechat-browser] [fallback] Found file input with selector: ${sel}`);
+          nodeId = result.nodeId;
+          break;
+        }
+      }
+
+      if (!nodeId) throw new Error('File input not found with any selector');
+
+      await cdp.send('DOM.setFileInputFiles', { nodeId, files: absolutePaths }, { sessionId });
+      console.log('[wechat-browser] [fallback] Files set via nodeId');
+
+      // Dispatch change event
+      await cdp.send('Runtime.evaluate', {
+        expression: `
+          (function() {
+            const selectors = ${JSON.stringify(fileInputSelectors)};
+            for (const sel of selectors) {
+              const el = document.querySelector(sel);
+              if (el) {
+                el.dispatchEvent(new Event('change', { bubbles: true }));
+                el.dispatchEvent(new Event('input', { bubbles: true }));
+                return 'dispatched on ' + sel;
+              }
+            }
+            return 'no input found for event dispatch';
+          })()
+        `,
+        returnByValue: true,
+      }, { sessionId });
+      console.log('[wechat-browser] [fallback] Change event dispatched');
+    }
 
     // Wait for images to upload
     console.log('[wechat-browser] Waiting for images to upload...');
@@ -589,11 +678,16 @@ export async function postToWeChat(options: WeChatBrowserOptions): Promise<void>
     for (let i = 0; i < 30; i++) {
       await sleep(2000);
       const uploadCheck = await cdp.send<{ result: { value: string } }>('Runtime.evaluate', {
-        expression: `JSON.stringify({ uploaded: document.querySelectorAll('.weui-desktop-upload__thumb, .pic_item, [class*=upload_thumb]').length })`,
+        expression: `
+          JSON.stringify({
+            uploaded: document.querySelectorAll('.weui-desktop-upload__thumb, .pic_item, [class*=upload_thumb], [class*="pic_item"], [class*="upload__thumb"]').length,
+            loading: document.querySelectorAll('[class*="upload_loading"], [class*="uploading"], .weui-desktop-upload__loading').length
+          })
+        `,
         returnByValue: true,
       }, { sessionId });
       const status = JSON.parse(uploadCheck.result.value);
-      console.log(`[wechat-browser] Upload progress: ${status.uploaded}/${targetCount}`);
+      console.log(`[wechat-browser] Upload progress: ${status.uploaded}/${targetCount} (loading: ${status.loading})`);
       if (status.uploaded >= targetCount) break;
     }
 

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

@@ -459,7 +459,7 @@ export async function publishArticle(options: ArticleOptions): Promise<void> {
                     if (charAfter === undefined || !/\\d/.test(charAfter)) {
                       const parentElement = node.parentElement;
                       if (parentElement) {
-                        parentElement.scrollIntoView({ behavior: 'smooth', block: 'center' });
+                        parentElement.scrollIntoView({ behavior: 'instant', block: 'center' });
                       }
 
                       const range = document.createRange();
@@ -500,112 +500,56 @@ export async function publishArticle(options: ArticleOptions): Promise<void> {
           return false;
         };
 
+        // Step A: Copy image to clipboard first (slow due to Swift compilation)
+        console.log(`[weibo-article] Copying image to clipboard: ${path.basename(img.localPath)}`);
+        if (!copyImageToClipboard(img.localPath)) {
+          console.warn(`[weibo-article] Failed to copy image to clipboard`);
+          continue;
+        }
+        await sleep(500);
+
+        // Step B: Select placeholder text (paste will replace the selection)
         const selected = await selectPlaceholder(3);
         if (!selected) {
           console.warn(`[weibo-article] Skipping image - could not select placeholder: ${img.placeholder}`);
           continue;
         }
 
-        console.log(`[weibo-article] Copying image: ${path.basename(img.localPath)}`);
-
-        if (!copyImageToClipboard(img.localPath)) {
-          console.warn(`[weibo-article] Failed to copy image to clipboard`);
-          continue;
-        }
-
-        await sleep(1000);
-
-        // Delete placeholder by replacing selection with empty text
-        console.log(`[weibo-article] Deleting placeholder...`);
-        await cdp.send('Runtime.evaluate', {
-          expression: `(() => {
-            const sel = window.getSelection();
-            if (!sel || sel.isCollapsed) return false;
-            const range = sel.getRangeAt(0);
-            range.deleteContents();
-            sel.collapseToStart();
-            return true;
-          })()`,
-          returnByValue: true,
-        }, { sessionId });
-
-        await sleep(300);
-
-        // Fallback: send Backspace key if placeholder still exists
-        const stillExists = await cdp!.send<{ result: { value: boolean } }>('Runtime.evaluate', {
-          expression: `(() => {
-            const editor = document.querySelector('div[contenteditable="true"]');
-            if (!editor) return false;
-            const placeholder = ${JSON.stringify(img.placeholder)};
-            const regex = new RegExp(placeholder + '(?!\\\\d)');
-            return regex.test(editor.innerText);
-          })()`,
-          returnByValue: true,
-        }, { sessionId });
-
-        if (stillExists.result.value) {
-          console.log('[weibo-article] Placeholder survived deleteContents, trying Input.insertText replacement...');
-          // Re-select and replace with empty via Input.insertText
-          await cdp!.send('Runtime.evaluate', {
-            expression: `(() => {
-              const editor = document.querySelector('div[contenteditable="true"]');
-              if (!editor) return false;
-              const placeholder = ${JSON.stringify(img.placeholder)};
-              const walker = document.createTreeWalker(editor, NodeFilter.SHOW_TEXT, null, false);
-              let node;
-              while ((node = walker.nextNode())) {
-                const text = node.textContent || '';
-                let searchStart = 0;
-                let idx;
-                while ((idx = text.indexOf(placeholder, searchStart)) !== -1) {
-                  const afterIdx = idx + placeholder.length;
-                  const charAfter = text[afterIdx];
-                  if (charAfter === undefined || !/\\d/.test(charAfter)) {
-                    const range = document.createRange();
-                    range.setStart(node, idx);
-                    range.setEnd(node, idx + placeholder.length);
-                    const sel = window.getSelection();
-                    sel.removeAllRanges();
-                    sel.addRange(range);
-                    return true;
-                  }
-                  searchStart = afterIdx;
-                }
-              }
-              return false;
-            })()`,
-          }, { sessionId });
-          await sleep(200);
-          await cdp!.send('Input.insertText', { text: '' }, { sessionId });
-          await sleep(300);
-        }
-
-        await sleep(200);
+        // Step C: Delete selected placeholder via Backspace (ProseMirror-compatible)
+        console.log(`[weibo-article] Deleting placeholder via Backspace...`);
+        await cdp.send('Input.dispatchKeyEvent', { type: 'keyDown', key: 'Backspace', code: 'Backspace', windowsVirtualKeyCode: 8 }, { sessionId });
+        await cdp.send('Input.dispatchKeyEvent', { type: 'keyUp', key: 'Backspace', code: 'Backspace', windowsVirtualKeyCode: 8 }, { sessionId });
+        await sleep(500);
 
         // Verify placeholder was deleted
-        const afterDelete = await cdp.send<{ result: { value: boolean } }>('Runtime.evaluate', {
+        const placeholderGone = await cdp.send<{ result: { value: boolean } }>('Runtime.evaluate', {
           expression: `(() => {
             const editor = document.querySelector('div[contenteditable="true"]');
             if (!editor) return true;
-            const text = editor.innerText;
             const placeholder = ${JSON.stringify(img.placeholder)};
             const regex = new RegExp(placeholder + '(?!\\\\d)');
-            return !regex.test(text);
+            return !regex.test(editor.innerText);
           })()`,
           returnByValue: true,
         }, { sessionId });
 
-        if (afterDelete.result.value) {
+        if (placeholderGone.result.value) {
           console.log(`[weibo-article] Placeholder deleted`);
         } else {
-          console.warn(`[weibo-article] Placeholder may still exist after delete`);
+          console.warn(`[weibo-article] Placeholder may still exist, trying execCommand delete...`);
+          // Re-select and delete via execCommand
+          await selectPlaceholder(1);
+          await cdp.send('Runtime.evaluate', {
+            expression: `document.execCommand('delete')`,
+          }, { sessionId });
+          await sleep(300);
         }
 
-        // Focus editor for paste
+        // Step D: Focus editor and paste image
         await cdp.send('Runtime.evaluate', {
           expression: `document.querySelector('div[contenteditable="true"]')?.focus()`,
         }, { sessionId });
-        await sleep(300);
+        await sleep(200);
 
         // Count images before paste
         const imgCountBefore = await cdp.send<{ result: { value: number } }>('Runtime.evaluate', {
@@ -613,7 +557,7 @@ export async function publishArticle(options: ArticleOptions): Promise<void> {
           returnByValue: true,
         }, { sessionId });
 
-        // Paste image
+        // Paste image at cursor position (where placeholder was)
         console.log(`[weibo-article] Pasting image...`);
         if (pasteFromClipboard('Google Chrome', 5, 1000)) {
           console.log(`[weibo-article] Paste keystroke sent for: ${path.basename(img.localPath)}`);

skills/baoyu-xhs-images/SKILL.md

@@ -76,7 +76,7 @@ Detailed style definitions: `references/presets/<style>.md`
 
 ## Preset Gallery
 
-Quick-start presets by content scenario. Use `--preset <name>` or recommend during Step 4.
+Quick-start presets by content scenario. Use `--preset <name>` or recommend during Step 2.
 
 **Knowledge & Learning**:
 
@@ -237,11 +237,12 @@ XHS Infographic Progress:
   - [ ] Found → load preferences → continue
   - [ ] Not found → run first-time setup → MUST complete before Step 1
 - [ ] Step 1: Analyze content → analysis.md
-- [ ] Step 2: Confirmation 1 - Content understanding ⚠️ REQUIRED
-- [ ] Step 3: Generate 3 outline + style variants
-- [ ] Step 4: Confirmation 2 - Outline & style & elements selection ⚠️ REQUIRED
-- [ ] Step 5: Generate images (sequential)
-- [ ] Step 6: Completion report
+- [ ] Step 2: Smart Confirm ⚠️ REQUIRED
+  - [ ] Path A: Quick confirm → generate recommended outline
+  - [ ] Path B: Customize → adjust then generate outline
+  - [ ] Path C: Detailed → 3 outlines → second confirm → generate outline
+- [ ] Step 3: Generate images (sequential)
+- [ ] Step 4: Completion report
 ```
 
 ### Flow
@@ -255,7 +256,11 @@ Input → [Step 0: Preferences] ─┬─ Found → Continue
                                                                                       │
         ┌───────────────────────────────────────────────────────────────────────────┘
         ↓
-Analyze → [Confirm 1] → 3 Outlines → [Confirm 2: Outline + Style + Elements] → Generate → Complete
+Analyze → [Smart Confirm] ─┬─ Quick: confirm recommended → outline.md → Generate → Complete
+                           │
+                           ├─ Customize: adjust options → outline.md → Generate → Complete
+                           │
+                           └─ Detailed: 3 outlines → [Confirm 2] → outline.md → Generate → Complete
 ```
 
 ### Step 0: Load Preferences (EXTEND.md) ⛔ BLOCKING
@@ -323,18 +328,63 @@ Read source content, save it if needed, and perform deep analysis.
    - Swipe flow design
 4. Detect source language
 5. Determine recommended image count (2-10)
-6. **Generate clarifying questions** (see Step 2)
+6. **Auto-recommend** best strategy + style + layout based on content signals
 7. **Save to `analysis.md`**
 
-### Step 2: Confirmation 1 - Content Understanding ⚠️
+### Step 2: Smart Confirm ⚠️
 
-**Purpose**: Validate understanding + collect missing info. **Do NOT skip.**
+**Purpose**: Present auto-recommended plan, let user confirm or adjust. **Do NOT skip.**
 
-**Display summary**:
-- Content type + topic identified
-- Key points extracted
-- Tone detected
-- Source images count
+**Auto-Recommendation Logic**:
+1. Use Auto Selection table to match content signals → best strategy + style + layout
+2. Infer optimal image count from content density
+3. Load style's default elements from preset
+
+**Display** (analysis summary + recommended plan):
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+📋 内容分析
+  主题：[topic] | 类型：[content_type]
+  要点：[key points summary]
+  受众：[target audience]
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+🎨 推荐方案（自动匹配）
+  策略：[A/B/C] [strategy name]（[reason]）
+  风格：[style] · 布局：[layout] · 预设：[preset]
+  图片：[N]张（封面+[N-2]内容+结尾）
+  元素：[background] / [decorations] / [emphasis]
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+**Use AskUserQuestion** with single question:
+
+| Option | Description |
+|--------|-------------|
+| 1. ✅ 确认，直接生成（推荐） | Trust auto-recommendation, proceed immediately |
+| 2. 🎛️ 自定义调整 | Modify strategy/style/layout/count in one step |
+| 3. 📋 详细模式 | Generate 3 outlines, then choose (two confirmations) |
+
+#### Path A: Quick Confirm (Option 1)
+
+Generate single outline using recommended strategy + style → save to `outline.md` → Step 3.
+
+#### Path B: Customize (Option 2)
+
+**Use AskUserQuestion** with adjustable options (leave blank = keep recommended):
+
+1. **策略风格**: Current: [strategy + style]. Options: A Story-Driven(warm) | B Information-Dense(notion) | C Visual-First(screen-print). Or specify style directly: cute/fresh/warm/bold/minimal/retro/pop/notion/chalkboard/study-notes/screen-print. Or use preset: knowledge-card / checklist / tutorial / poster / cinematic / etc.
+2. **布局**: Current: [layout]. Options: sparse | balanced | dense | list | comparison | flow | mindmap | quadrant
+3. **图片数量**: Current: [N]. Range: 2-10
+4. **补充说明**（可选）: Selling point emphasis, audience adjustment, color preference, etc.
+
+**After response**: Generate single outline with user's choices → save to `outline.md` → Step 3.
+
+#### Path C: Detailed Mode (Option 3)
+
+Full two-confirmation flow for maximum control:
+
+**Step 2a: Content Understanding**
 
 **Use AskUserQuestion** for:
 1. Core selling point (multiSelect: true)
@@ -342,13 +392,9 @@ Read source content, save it if needed, and perform deep analysis.
 3. Style preference: Authentic sharing / Professional review / Aesthetic mood / Auto
 4. Additional context (optional)
 
-**After response**: Update `analysis.md` → Step 3
+**After response**: Update `analysis.md`.
 
-### Step 3: Generate 3 Outline + Style Variants
-
-Based on analysis + user context, create three distinct strategy variants. Each variant includes both **outline structure** and **visual style recommendation**.
-
-**For each strategy**:
+**Step 2b: Generate 3 Outline Variants**
 
 | Strategy | Filename | Outline | Recommended Style |
 |----------|----------|---------|-------------------|
@@ -363,7 +409,7 @@ strategy: a  # a, b, or c
 name: Story-Driven
 style: warm  # recommended style for this strategy
 style_reason: "Warm tones enhance emotional storytelling and personal connection"
-elements:  # from style preset, can be customized in Step 4
+elements:  # from style preset, can be customized
   background: solid-pastel
   decorations: [clouds, stars-sparkles]
   emphasis: star-burst
@@ -391,50 +437,22 @@ image_count: 5
 - Each strategy MUST have different outline structure AND different recommended style
 - Adapt page count: A typically 4-6, B typically 3-5, C typically 3-4
 - Include `style_reason` explaining why this style fits the strategy
-- Consider user's style preference from Step 2
 
 Reference: `references/workflows/outline-template.md`
 
-### Step 4: Confirmation 2 - Outline & Style & Elements Selection ⚠️
-
-**Purpose**: User chooses outline strategy, confirms visual style, and customizes elements. **Do NOT skip.**
-
-**Display each strategy**:
-- Strategy name + page count + recommended style
-- Page-by-page summary (P1 → P2 → P3...)
+**Step 2c: Outline & Style Selection**
 
 **Use AskUserQuestion** with three questions:
 
-**Question 1: Outline Strategy**
-- Strategy A (Recommended if "authentic sharing")
-- Strategy B (Recommended if "professional review")
-- Strategy C (Recommended if "aesthetic mood")
-- Combine: specify pages from each
+**Q1: Outline Strategy**: A / B / C / Combine (specify pages from each)
 
-**Question 2: Visual Style**
-- Use strategy's recommended style (show which style)
-- Or use a preset: knowledge-card / checklist / tutorial / poster / cinematic / etc. (see [Style Presets](references/style-presets.md))
-- Or select from: cute / fresh / warm / bold / minimal / retro / pop / notion / chalkboard / screen-print
-- Or type custom style description
+**Q2: Visual Style**: Use recommended | Select preset | Select style | Custom description
 
-**Question 3: Visual Elements** (show after style selection)
-Display the selected style's default elements from preset, then ask:
-- Use style defaults (Recommended) - show preview: background, decorations, emphasis
-- Adjust background - options: solid-pastel / solid-saturated / gradient-linear / gradient-radial / paper-texture / grid
-- Adjust decorations - options: hearts / stars-sparkles / flowers / clouds / leaves / confetti
-- Type custom element preferences
+**Q3: Visual Elements**: Use defaults (Recommended) | Adjust background | Adjust decorations | Custom
 
-**After response**:
-- Single strategy → copy to `outline.md` with confirmed style
-- Combination → merge specified pages with confirmed style
-- Custom request → regenerate based on feedback
-- Style defaults → use preset's Element Combination as-is
-- Background adjustment → update elements.background with user choice
-- Decorations adjustment → update elements.decorations with user choice
-- Custom elements → parse user's preferences into elements fields
-- Update `outline.md` frontmatter with final style and elements
+**After response**: Save selected/merged outline to `outline.md` with confirmed style and elements → Step 3.
 
-### Step 5: Generate Images
+### Step 3: Generate Images
 
 With confirmed outline + style + layout:
 
@@ -474,12 +492,13 @@ If image generation skill supports `--sessionId`:
 2. Use same session ID for all images
 3. Combined with reference image chain, ensures maximum visual consistency
 
-### Step 6: Completion Report
+### Step 4: Completion Report
 
 ```
 Xiaohongshu Infographic Series Complete!
 
 Topic: [topic]
+Mode: [Quick / Custom / Detailed]
 Strategy: [A/B/C/Combined]
 Style: [style name]
 Layout: [layout name or "varies"]
@@ -487,10 +506,8 @@ Location: [directory path]
 Images: N total
 
 ✓ analysis.md
-✓ outline-strategy-a.md
-✓ outline-strategy-b.md
-✓ outline-strategy-c.md
-✓ outline.md (selected: [strategy])
+✓ outline.md
+✓ outline-strategy-a/b/c.md (detailed mode only)
 
 Files:
 - 01-cover-[slug].png ✓ Cover (sparse)
@@ -559,7 +576,7 @@ Detailed templates in `references/` directory:
 
 - Auto-retry once on failure | Cartoon alternatives for sensitive figures
 - Use confirmed language preference | Maintain style consistency
-- **Two confirmation points required** (Steps 2 & 4) - do not skip
+- **Smart Confirm required** (Step 2) - do not skip; detailed mode uses two sub-confirmations
 
 ## Extension Support
 

skills/baoyu-xhs-images/references/workflows/analysis-framework.md

@@ -195,4 +195,4 @@ Before proceeding to outline generation:
 - [ ] Have I identified save/share triggers?
 - [ ] Are there clear visual opportunities?
 - [ ] Is the swipe flow planned?
-- [ ] Have I selected 3 style+layout combinations?
+- [ ] Have I identified the best style+layout recommendation?