Back to Details

blog-rewrite

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Blog Rewriter -- Optimize Existing Posts

博客重写工具——优化现有文章

Rewrites and optimizes existing blog posts for dual ranking: Google search and AI citation platforms. Preserves the author's voice while applying the 6 pillars of optimization.
Key references:
  • references/quality-scoring.md
    - 5-category scoring (Content 30, SEO 25, E-E-A-T 15, Technical 15, AI Citation 15)
  • references/eeat-signals.md
    - Experience, expertise, authority, trust markers
  • references/internal-linking.md
    - Linking strategy and anchor text rules
  • references/visual-media.md
    - Image sourcing and chart styling
针对Google搜索和AI引用平台的双重排名需求，重写并优化现有博客文章。在应用六大优化支柱的同时，保留作者的写作风格。
核心参考资料：
  • references/quality-scoring.md
    - 五大维度评分（内容质量30分、SEO优化25分、E-E-A-T 15分、技术要素15分、AI引用适配15分）
  • references/eeat-signals.md
    - 经验、专业度、权威性、可信度标记
  • references/internal-linking.md
    - 内链策略与锚文本规则
  • references/visual-media.md
    - 图片来源与图表样式规范

Cross-reference

交叉参考

For 21 evidence-led optimization prompts (AI-detector test, CTR audit, schema, PAA rewording, technical audit, ChatGPT visibility) directly applicable to rewrite work, see 
/blog flow optimize
.
如需直接应用于重写工作的21项基于实证的优化提示（AI检测器测试、点击率审核、Schema优化、PAA改写、技术审核、ChatGPT可见性优化），请查看
/blog flow optimize
。

Workflow

工作流程

Phase 1: Audit (Read-Only)

阶段1：审核（只读）

  1. Read the blog post - Detect format (MDX, markdown, HTML)
  2. Run the quality checklist against 
    references/quality-scoring.md
    :
    • Count fabricated vs sourced statistics
    • Check answer-first formatting (H2 -> stat in first sentence?)
    • Count images and charts (type diversity?)
    • Measure paragraph lengths (any > 150 words?)
    • Check heading hierarchy (H1 -> H2 -> H3, no skips?)
    • Look for FAQ schema
    • Check freshness signals (lastUpdated, dateModified)
    • Assess self-promotion level
    • Evaluate citation tier quality
  3. AI content detection scan:
    • Burstiness score - Measure sentence length variance across the post. Low variance (most sentences within 3-5 words of each other) is a strong AI signal. Calculate: standard deviation of sentence word counts. Target SD > 6.
    • Known AI phrase scan - Check for these high-frequency AI phrases:
      • "in today's digital landscape", "it's important to note", "dive into"
      • "game-changer", "navigate the landscape", "revolutionize", "seamlessly"
      • "cutting-edge", "harness the power of", "leverage" (as verb)
      • "delve", "crucial", "elevate", "foster", "landscape" (overused)
      • "multifaceted", "robust", "tapestry", "embark"
      • Full list in 
        agents/blog-writer.md
    • Vocabulary diversity - Calculate Type-Token Ratio (TTR): unique words / total words. Low TTR (< 0.40) suggests AI-generated repetitive phrasing. Target TTR > 0.50 for natural prose.
    • AI content percentage estimate - Based on burstiness, phrase density, and TTR, estimate what percentage of the content reads as AI-generated (0-100%). Report as: "AI content estimate: ~X%"
  4. Video embed check:
    • Count existing YouTube embeds in the post
    • If 0 embeds, flag: "No video embeds. YouTube has the strongest AI visibility correlation (0.737)"
    • If present, check: lazy loading? aria-labels? noscript fallback? VideoObject schema?
  5. Cannibalization check:
    • Identify the post's primary keyword from title, H1, and first paragraph
    • Search the blog directory for other posts targeting the same keyword:
      • Grep headings and meta descriptions across all blog posts
      • Flag any posts with significant keyword overlap
    • If cannibalization found, report:
      • Which posts compete for the same keyword
      • Recommend: merge (combine into one stronger post) or differentiate (shift one post to a related but distinct keyword)
  6. Calculate current score across 5 categories:
    • Score across 5 categories (Content Quality 30, SEO Optimization 25, E-E-A-T Signals 15, Technical Elements 15, AI Citation Readiness 15)
    • Total: 0-100
  7. Present audit summary with specific findings, AI detection results, video status, cannibalization status, and score
  8. Enter plan mode - Present section-by-section optimization plan
Wait for user approval before proceeding.
  1. 阅读博客文章 - 检测格式（MDX、markdown、HTML）
  2. 对照
    references/quality-scoring.md
    执行质量检查清单    ：
    • 统计虚构数据与有来源数据的数量
    • 检查先答后述格式（H2标题下首句是否包含数据？）
    • 统计图片与图表数量（类型是否多样？）
    • 测量段落长度（是否存在超过150词的段落？）
    • 检查标题层级（是否遵循H1→H2→H3的顺序，无层级跳跃？）
    • 查看是否包含FAQ schema
    • 检查新鲜度信号（lastUpdated、dateModified字段）
    • 评估自我推广程度
    • 评估引用来源的层级质量
  3. AI内容检测扫描：
    • 句子长度多样性评分 - 测量整篇文章的句子长度差异。低差异（大多数句子长度相差3-5词）是明显的AI生成信号。计算方式：句子词数的标准差。目标标准差＞6。
    • 高频AI短语扫描 - 检查以下高频AI生成短语：
      • "in today's digital landscape"、"it's important to note"、"dive into"
      • "game-changer"、"navigate the landscape"、"revolutionize"、"seamlessly"
      • "cutting-edge"、"harness the power of"、"leverage"（作为动词）
      • "delve"、"crucial"、"elevate"、"foster"、"landscape"（过度使用）
      • "multifaceted"、"robust"、"tapestry"、"embark"
      • 完整列表见
        agents/blog-writer.md
    • 词汇多样性 - 计算类型-标记比（TTR）：独特词数/总词数。低TTR（＜0.40）表明AI生成内容存在重复措辞。目标TTR＞0.50以保证自然流畅的文笔。
    • AI生成内容占比估算 - 根据句子长度多样性、AI短语密度和TTR，估算文章中AI生成内容的占比（0-100%）。报告格式："AI内容占比估算：~X%"
  4. 视频嵌入检查：
    • 统计文章中已有的YouTube嵌入视频数量
    • 若为0，标记："未嵌入视频。YouTube与AI可见性的相关性最强（相关系数0.737）"
    • 若已嵌入，检查：是否启用懒加载？是否添加aria-labels？是否有noscript降级方案？是否包含VideoObject schema？
  5. 关键词 cannibalization（自竞争）检查：
    • 从标题、H1和第一段中识别文章的核心关键词
    • 在博客目录中搜索其他针对同一关键词的文章：
      • 遍历所有博客文章的标题和元描述
      • 标记任何存在显著关键词重叠的文章
    • 若发现自竞争问题，报告：
      • 哪些文章针对同一关键词竞争
      • 建议：合并（整合为一篇更优质的文章）或差异化（将其中一篇文章转向相关但不同的关键词）
  6. 计算五大维度的当前得分：
    • 五大维度得分（内容质量30分、SEO优化25分、E-E-A-T信号15分、技术要素15分、AI引用适配15分）
    • 总分：0-100分
  7. 呈现审核总结，包含具体发现、AI检测结果、视频状态、自竞争状态及得分
  8. 进入规划模式 - 呈现逐段优化方案
等待用户批准后再继续执行。

Phase 2: Research

阶段2：调研

  1. Identify the blog's core topic from existing content
  2. Find replacement statistics for any fabricated/unsourced data:
    • Search: 
      [topic] study 2025 2026 data statistics
    • Target tier 1-3 sources only
  3. Find images if post has fewer than 3:
    • Pixabay: 
      site:pixabay.com [topic keywords]
    • Unsplash: 
      site:unsplash.com [topic keywords]
    • Verify each URL returns HTTP 200
    • If nanobanana-mcp is configured, offer AI generation for missing/insufficient images via 
      blog-image
  4. Plan charts if post has fewer than 2:
    • Identify data suitable for visualization
    • Select diverse chart types
  1. 从现有内容中识别博客的核心主题
  2. 为所有虚构/无来源数据寻找替代数据：
    • 搜索关键词：
      [主题] study 2025 2026 data statistics
    • 仅选择1-3层级的权威来源
  3. 若文章图片少于3张，寻找合适图片：
    • Pixabay：
      site:pixabay.com [主题关键词]
    • Unsplash：
      site:unsplash.com [主题关键词]
    • 验证每个URL返回HTTP 200状态码
    • 若配置了nanobanana-mcp，可通过
      blog-image
      指令生成缺失/不足的图片
  4. 若文章图表少于2个，规划图表内容：
    • 识别适合可视化的数据
    • 选择多样的图表类型

Phase 3: Chart Generation (Built-In)

阶段3：图表生成（内置功能）

When the post needs more visual elements, invoke the 
blog-chart
sub-skill:
  1. Select chart type using the diversity rule (no repeated types per post)
  2. Pass: chart type, title, data values, source, platform format
  3. Embed the returned SVG directly within a 
    <figure>
    wrapper
  4. Target 2-4 charts per 2,000-word post
See 
references/visual-media.md
for chart type selection and styling rules.
当文章需要更多视觉元素时，调用
blog-chart
子功能：
  1. 遵循多样性规则选择图表类型（单篇文章不重复使用相同类型）
  2. 传入参数：图表类型、标题、数据值、来源、平台格式
  3. 将返回的SVG直接嵌入
    <figure>
    标签中
  4. 目标：每2000字文章添加2-4个图表
图表类型选择和样式规则请参考
references/visual-media.md
。

Phase 4: Content Rewrite

阶段4：内容重写

Apply changes in this order:
按以下顺序应用修改：

4a. Preserve What Works

4a. 保留优质内容

  • Keep the author's voice and unique perspective
  • Preserve original insights and first-hand experience
  • Keep existing quality images and charts
  • Maintain internal links
  • 保留作者的写作风格和独特视角
  • 保留原创见解和一手经验
  • 保留已有的优质图片和图表
  • 保留现有内链

4b. Fix Frontmatter

4b. 修复前置元数据

  • Add 
    lastUpdated: "YYYY-MM-DD"
    (today's date)
  • Keep original 
    date
    unchanged
  • Fix meta description: fact-dense, 150-160 chars, includes 1 statistic
  • Add 
    coverImage
    + 
    coverImageAlt
    + 
    ogImage
    if missing
    • Search Pixabay/Unsplash/Pexels for wide hero image (1200x630)
    • Or generate custom SVG cover via 
      blog-chart
      (text-on-gradient with key stat)
    • Or generate custom AI image via 
      blog-image
      sub-skill (if nanobanana-mcp configured)
  • Verify tags/categories are appropriate
  • 添加
    lastUpdated: "YYYY-MM-DD"
    （当前日期）
  • 保留原始
    date
    字段不变
  • 优化元描述：内容详实，长度150-160字符，包含至少1个数据
  • 若缺失，添加
    coverImage
    + 
    coverImageAlt
    + 
    ogImage
    • 在Pixabay/Unsplash/Pexels中搜索宽幅封面图（1200x630）
    • 或通过
      blog-chart
      生成自定义SVG封面图（带关键数据的渐变文字）
    • 或通过
      blog-image
      子功能生成自定义AI图片（若配置了nanobanana-mcp）
  • 验证标签/分类是否合适

4c. Apply Answer-First Formatting

4c. 应用先答后述格式

Every H2 section MUST open with a 40-60 word paragraph containing:
  • At least one specific statistic with source attribution
  • A direct answer to the heading's implicit question
每个H2章节必须以一段40-60词的段落开头，包含：
  • 至少1个带来源标注的具体数据
  • 直接回答标题隐含的问题

4d. Replace Fabricated Statistics

4d. 替换虚构数据

  • Search for patterns: "X% of...", "X out of Y...", unsourced claims
  • Replace with real data from tier 1-3 sources
  • Always include inline attribution: 
    ([Source Name](url), year)
  • 搜索以下模式："X% of..."、"X out of Y..."、无来源的声明
  • 用1-3层级权威来源的真实数据替换
  • 始终添加内联标注：
    ([来源名称](链接), 年份)

4e. Improve Headings

4e. 优化标题

  • Convert statement headings to questions where natural (60-70% target)
  • Keep 2-3 statement headings for variety
  • Ensure keyword appears in 2-3 headings naturally
  • 尽可能将陈述式标题改为疑问式标题（目标60-70%）
  • 保留2-3个陈述式标题以增加多样性
  • 确保关键词自然出现在2-3个标题中

4f. Fix Paragraph Length

4f. 调整段落长度

  • Split any paragraph > 150 words
  • Target 40-80 words per paragraph
  • Ensure each paragraph starts with its most important sentence
  • 拆分所有超过150词的段落
  • 目标段落长度为40-80词
  • 确保每个段落以最重要的句子开头

4g. Add Visual Elements

4g. 添加视觉元素

  • Embed new images after H2 headings, spaced evenly
  • Embed charts within relevant sections
  • If nanobanana-mcp configured: generate custom images for sections lacking good stock matches (invoke 
    blog-image
    sub-skill via Task)
  • Adapt embed format to detected platform (MDX vs markdown vs HTML)
  • 在H2标题后均匀嵌入新图片
  • 在相关章节中嵌入图表
  • 若配置了nanobanana-mcp：为找不到合适库存图片的章节生成自定义图片（通过Task调用
    blog-image
    子功能）
  • 根据检测到的平台（MDX/markdown/HTML）调整嵌入格式

4h. Add Video Embeds

4h. 添加视频嵌入

If the post lacks YouTube video embeds:
  • Search 2-3 relevant videos using quality criteria from 
    references/video-embeds.md
  • Embed using platform-appropriate format (srcdoc lazy loading)
  • Place: 1 after introduction, 1-2 in mid-article sections
  • Include noscript fallback for AI crawlers
若文章未嵌入YouTube视频：
  • 根据
    references/video-embeds.md
    的质量标准搜索2-3个相关视频
  • 使用适合平台的格式嵌入（srcdoc懒加载）
  • 放置位置：1个在引言之后，1-2个在文章中部章节
  • 为AI爬虫添加noscript降级方案

4i. Add/Improve FAQ

4i. 添加/优化FAQ

  • If no FAQ exists, add one (3-5 questions)
  • If FAQ exists, ensure answers are 40-60 words with statistics
  • Add FAQ schema markup appropriate to platform
  • 若没有FAQ，添加3-5个问题的FAQ模块
  • 若已有FAQ，确保每个回答为40-60词且包含数据
  • 添加适合平台的FAQ schema标记

4j. Reduce Self-Promotion

4j. 减少自我推广

  • Max 1 brand mention (author bio context only)
  • Remove "At [Company], we..." patterns
  • Convert promotional sections to educational content
  • 最多仅在作者简介中提及1次品牌
  • 删除“At [Company], we...”这类句式
  • 将推广内容转化为教育性内容

4k. Citation Capsule Injection

4k. 注入引用胶囊

For each H2 section, generate (or improve existing) a citation capsule:
  • 40-60 word self-contained passage per H2
  • Contains: one specific claim + one data point + source attribution
  • Written in a declarative style so an AI system could extract and quote it directly
  • Placed naturally within the section body, not as a separate callout
Example:
markdown
According to a 2026 Gartner study, 58% of enterprise buyers now consult AI
assistants before contacting a vendor ([Gartner](https://www.gartner.com), 2026).
This shift means B2B content must answer specific questions concisely enough
for AI systems to extract and cite in their responses.
Capsules map to the "AI Citation Readiness" category (15 points) in 
references/quality-scoring.md
.
为每个H2章节生成（或优化现有）引用胶囊：
  • 每个H2对应一段40-60词的独立段落
  • 包含：1个具体声明 + 1个数据点 + 来源标注
  • 采用陈述式写法，便于AI系统直接提取引用
  • 自然嵌入章节内容中，不作为单独的提示框
示例：
markdown
根据2026年Gartner的研究，58%的企业买家在联系供应商前会先咨询AI助手([Gartner](https://www.gartner.com), 2026)。
这一转变意味着B2B内容必须足够简洁地回答具体问题，以便AI系统提取并引用。
引用胶囊对应
references/quality-scoring.md
中的“AI引用适配”维度（15分）。

4l. Anti-AI-Detection Patterns

4l. 反AI检测优化

Apply these transformations to reduce AI-detectable writing patterns:
  • Eliminate em dashes - Replace every em dash (-) with a comma, hyphen (-), colon, or period. Split sentences if needed. Em dashes are an AI writing tell.
  • Replace flagged phrases - Swap every detected AI phrase (from the scan in Phase 1 step 3) with a natural alternative. Examples:
    • "it's important to note" -> "worth noting" or "keep in mind"
    • "in today's digital landscape" -> "right now" or "in [specific year]"
    • "leverage" -> "use", "apply", "take advantage of"
    • "delve" -> "look at", "explore", "dig into"
    • "robust" -> "strong", "solid", "reliable"
    • "crucial" -> "key", "essential", "critical" (or restructure the sentence)
  • Vary sentence length deliberately - After rewriting, scan each paragraph. Inject short punchy sentences (5-10 words) between longer ones (18-25 words). Target: no more than 3 consecutive sentences within 5 words of each other's length.
  • Inject rhetorical questions - Add at least one rhetorical question every 200-300 words to break up declarative monotony.
  • Use contractions naturally - Replace formal constructions with contractions where they sound natural: "it is" -> "it's", "we have" -> "we've", "do not" -> "don't", "is not" -> "isn't".
  • Include hedging language - Sprinkle first-person hedges that signal real experience: "in our experience", "we've found that", "from what we've seen", "this tends to", "it depends on".
应用以下修改以减少AI可检测的写作模式：
  • 删除破折号 - 将所有破折号（—）替换为逗号、连字符（-）、冒号或句号。必要时拆分句子。破折号是AI写作的典型特征。
  • 替换标记短语 - 将阶段1步骤3中检测到的所有AI短语替换为自然表达。示例：
    • "it's important to note" → "值得注意的是"或"请记住"
    • "in today's digital landscape" → "目前"或"在[具体年份]"
    • "leverage" → "使用"、"应用"、"利用"
    • "delve" → "审视"、"探索"、"深入研究"
    • "robust" → "强大的"、"可靠的"、"稳固的"
    • "crucial" → "关键的"、"必要的"、"重要的"（或重构句子）
  • 刻意调整句子长度 - 重写后扫描每个段落。在长句（18-25词）之间插入简短有力的句子（5-10词）。目标：连续3个句子的长度差异不超过5词。
  • 加入反问句 - 每200-300词至少添加1个反问句，打破陈述式的单调感。
  • 自然使用缩写 - 在合适的场景将正式表达替换为缩写："it is" → "it's"、"we have" → "we've"、"do not" → "don't"、"is not" → "isn't"
  • 加入模糊性表述 - 适当添加第一人称模糊表述以体现真实经验："根据我们的经验"、"我们发现"、"从我们的观察来看"、"这通常会"、"这取决于"

4m. Summary Box (Key Takeaways)

4m. 摘要框（核心要点）

If the post lacks a summary box, add one immediately after the introduction:
markdown
> **Key Takeaways**
> - [Core finding with statistic and source]
> - [Second key insight or recommendation]
> - [Third actionable takeaway]
> (3-5 bullets, 40-60 words combined. Self-contained - reader gets
> the core value without reading the full article.)
Default label is "Key Takeaways", but this is configurable per persona or brand voice (e.g., "The Bottom Line", "Quick Summary", "What You Need to Know").
If an existing TL;DR box is present, convert it to the bullet-point Key Takeaways format. Verify it meets the 40-60 word requirement and contains at least one statistic with source attribution.
若文章没有摘要框，在引言后立即添加：
markdown
> **核心要点**
> - [带数据和来源的核心发现]
> - [第二个关键见解或建议]
> - [第三个可执行要点]
> （3-5个项目符号，总长度40-60词。内容独立完整——读者无需阅读全文即可获取核心价值。）
默认标签为“核心要点”，可根据用户角色或品牌风格配置（如“总结”、“快速摘要”、“你需要知道的内容”）。
若已有TL;DR框，将其转换为项目符号形式的核心要点。确保符合40-60词的要求，并包含至少1个带来源的数据。

4n. Information Gain Marker Injection

4n. 注入信息增益标记

Review the post for original value and tag it:
  • [ORIGINAL DATA]
    - Any proprietary data, survey results, experiments, or case study metrics the author collected first-hand
  • [PERSONAL EXPERIENCE]
    - First-hand observations, lessons learned
  • [UNIQUE INSIGHT]
    - Novel analysis, contrarian perspectives backed by data
If the post lacks original value markers:
  • Ask the author for first-hand data or experience to include
  • At minimum, add analytical insights that connect existing research in new ways
  • Target: at least 2-3 markers per post
Use HTML comments (
<!-- [ORIGINAL DATA] -->
) or visible callouts depending on the post's style.
检查文章的原创价值并添加标记：
  • [ORIGINAL DATA]
    - 作者一手收集的任何专有数据、调查结果、实验数据或案例研究指标
  • [PERSONAL EXPERIENCE]
    - 一手观察结果、经验教训
  • [UNIQUE INSIGHT]
    - 新颖的分析、有数据支持的逆向观点
若文章缺少原创价值标记：
  • 向作者索要一手数据或经验以补充
  • 至少添加将现有研究以新方式关联的分析见解
  • 目标：每篇文章至少添加2-3个标记
根据文章风格，可使用HTML注释(
<!-- [ORIGINAL DATA] -->
)或可见提示框。

Phase 5: Verification

阶段5：验证

After rewriting, verify all quality gates pass:
重写完成后，验证所有质量标准是否达标：

Core Quality Gates

核心质量标准

  1. Every H2 opens with a statistic + source
  2. No paragraph exceeds 150 words
  3. Zero fabricated statistics
  4. Heading hierarchy is clean
  5. FAQ section present with schema
  6. Images have descriptive alt text
  7. Cover image present in frontmatter (coverImage + ogImage)
  8. If MDX: build the project to verify no compilation errors
  1. 每个H2章节开头均包含数据+来源
  2. 无超过150词的段落
  3. 无虚构数据
  4. 标题层级清晰
  5. 包含带Schema的FAQ模块
  6. 图片带有描述性alt文本
  7. 前置元数据中包含封面图（coverImage + ogImage）
  8. 若为MDX格式：构建项目以验证无编译错误

New Element Verification

新增元素验证

  1. TL;DR box present after introduction (40-60 words, contains statistic)
  2. At least 2-3 information gain markers present
  3. Citation capsules in major H2 sections (40-60 words, self-contained)
  4. Internal linking zones marked or actual links present (5-10 per 2,000 words)
  5. No AI-detectable phrases remain from banned list
  1. 引言后包含TL;DR框（40-60词，包含数据）
  2. 至少包含2-3个信息增益标记
  3. 主要H2章节包含引用胶囊（40-60词，独立完整）
  4. 标记内链区域或添加实际内链（每2000字5-10个）
  5. 无禁用列表中的AI可检测短语

Burstiness and Naturalness Check

句子多样性与自然度检查

  1. Sentence length variance: SD > 6 (mix of short and long sentences)
  2. Contractions used naturally throughout
  3. Rhetorical questions present (1 per 200-300 words)
  4. AI content estimate reduced from audit baseline
  5. Score improved across all 5 categories vs Phase 1 audit
  6. YouTube video embeds present with lazy loading, aria-labels, and noscript fallback
  1. 句子长度差异：标准差＞6（长短句混合）
  2. 全文自然使用缩写
  3. 包含反问句（每200-300词1个）
  4. AI生成内容占比较审核基线降低
  5. 五大维度得分较阶段1审核有所提升
  6. 嵌入的YouTube视频包含懒加载、aria-labels和noscript降级方案

Phase 6: Summary

阶段6：总结

undefined
undefined

Blog Optimization Complete: [Title]

博客优化完成：[标题]

Score Change

得分变化

  • Before: [X]/100 ([Rating])
    • Content Quality: [X]/30
    • SEO Optimization: [X]/25
    • E-E-A-T Signals: [X]/15
    • Technical Elements: [X]/15
    • AI Citation Readiness: [X]/15
  • After: [Y]/100 ([Rating])
    • Content Quality: [Y]/30
    • SEO Optimization: [Y]/25
    • E-E-A-T Signals: [Y]/15
    • Technical Elements: [Y]/15
    • AI Citation Readiness: [Y]/15
  • 优化前：[X]/100（[评级]）
    • 内容质量：[X]/30
    • SEO优化：[X]/25
    • E-E-A-T信号：[X]/15
    • 技术要素：[X]/15
    • AI引用适配：[X]/15
  • 优化后：[Y]/100（[评级]）
    • 内容质量：[Y]/30
    • SEO优化：[Y]/25
    • E-E-A-T信号：[Y]/15
    • 技术要素：[Y]/15
    • AI引用适配：[Y]/15

AI Detection

AI检测结果

  • Before: ~[X]% AI-detected content
  • After: ~[Y]% AI-detected content
  • Phrases replaced: [N]
  • Burstiness improved: [before SD] -> [after SD]
  • 优化前：~[X]% AI生成内容
  • 优化后：~[Y]% AI生成内容
  • 替换的短语数量：[N]
  • 句子多样性提升：[优化前标准差] → [优化后标准差]

Cannibalization

关键词自竞争

  • [Status: none found / flagged N posts / resolved]
  • [状态：未发现/标记N篇文章/已解决]

Changes Made

已完成修改

  • statistics replaced with sourced data
  • SVG charts added (types: ...)
  • images added from Pixabay/Unsplash
  • Answer-first formatting applied to [N] H2 sections
  • FAQ schema injected with [N] questions
  • TL;DR box: [added/updated]
  • Information gain markers: [N] ([types])
  • Citation capsules: [N] across H2 sections
  • AI phrases replaced: [N]
  • lastUpdated set to [date]
  • Self-promotion reduced to [N] mentions
  • [X]个虚构数据替换为有来源的数据
  • 添加[X]个SVG图表（类型：...）
  • 从Pixabay/Unsplash添加[X]张图片
  • 为[N]个H2章节应用先答后述格式
  • 注入包含[N]个问题的FAQ schema
  • TL;DR框：[已添加/已更新]
  • 信息增益标记：[N]个（类型：...）
  • H2章节引用胶囊：[N]个
  • 替换AI短语：[N]个
  • lastUpdated设置为[日期]
  • 自我推广提及次数减少至[N]次

Visual Elements

视觉元素统计

  • Charts: [count] ([types])
  • Images: [count]
  • YouTube videos: [count] ([titles])
  • 图表：[数量]个（类型：...）
  • 图片：[数量]张
  • YouTube视频：[数量]个（标题：...）

Ready for

后续操作

  • /blog analyze <file>
    to verify final score
  • Publishing / deploying
undefined
  • 使用
    /blog analyze <file>
    验证最终得分
  • 发布/部署
undefined

Update Mode

更新模式

When invoked as 
/blog update <file>
, focus on freshness:
  1. Update statistics to latest available data (2025-2026)
  2. Add new developments since last update
  3. Refresh images if older than 1 year
  4. Update 
    lastUpdated
    in frontmatter
  5. Preserve the existing structure - minimize rewrites
  6. Target: at least 30% content change to register as "fresh" for AI crawlers
当以
/blog update <file>
调用时，聚焦于内容新鲜度：
  1. 将数据更新为最新可用的2025-2026年数据
  2. 添加上次更新后的新进展
  3. 替换超过1年的旧图片
  4. 更新前置元数据中的
    lastUpdated
    字段
  5. 保留现有结构——最小化重写
  6. 目标：至少30%的内容变更，以被AI爬虫识别为“新鲜”内容 ",