Back to Details

blog-write

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Blog Writer -- New Article Generation

博客撰写工具——新文章生成

Writes complete blog articles from a topic, brief, or outline. Every article follows the 6 pillars of dual optimization (Google rankings + AI citations).
Key references:
  • references/content-templates.md
    — Template selection guide and usage
  • 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
根据主题、简介或大纲撰写完整的博客文章。每篇文章都遵循双重优化的6大核心原则（谷歌排名优化 + AI引用优化）。
核心参考资料：
  • references/content-templates.md
    — 模板选择指南及使用说明
  • references/quality-scoring.md
    — 5维度质量评分（内容30分、SEO25分、E-E-A-T15分、技术规范15分、AI引用适配15分）
  • references/eeat-signals.md
    — 经验、专业度、权威性、可信度标记说明
  • references/internal-linking.md
    — 内链策略及锚文本规则
  • references/visual-media.md
    — 图片来源及图表样式规范

Workflow

工作流程

Phase 1: Topic Understanding

第一阶段：主题理解

  1. Clarify the topic — If the user provides just a topic, ask:
    • Target audience (who is this for?)
    • Primary keyword / search intent
    • Desired word count (default: 2,000-2,500 words)
    • Platform/format (MDX, markdown, HTML — auto-detect if in a project)
  2. If a brief exists — Load it and skip to Phase 1.5
  1. 明确主题 — 若用户仅提供主题，需询问：
    • 目标受众（面向哪些人群？）
    • 核心关键词/搜索意图
    • 期望字数（默认：2000-2500字）
    • 平台/格式（MDX、markdown、HTML——若在项目环境中则自动检测）
  2. 若已有简介 — 加载简介内容，直接进入1.5阶段

Phase 1.5: Template Selection

1.5阶段：模板选择

Select the appropriate content template from the 12 templates in 
templates/
.
  1. Auto-detect content type from the topic and search intent:
    SignalTemplate
    "How to...", process, steps
    how-to-guide
    "Best X", "Top N", list format
    listicle
    Client result, before/after, metrics
    case-study
    "X vs Y", comparison, alternatives
    comparison
    Broad topic, comprehensive guide
    pillar-page
    "Is X worth it", product evaluation
    product-review
    Opinion, prediction, industry take
    thought-leadership
    Expert quotes, multi-source collection
    roundup
    Code walkthrough, tool demo, technical
    tutorial
    Breaking news, algorithm update, event
    news-analysis
    Survey results, experiment, original data
    data-research
    Q&A, knowledge base, "What is X"
    faq-knowledge
  2. Load the matching template — Read from 
    templates/<type>.md
  3. Adapt the outline — Use the template's section structure, heading patterns, and word count guidance to shape Phase 3's outline
  4. Fallback — If no template clearly fits, use the generic outline structure in Phase 3 below. Inform the user which template was selected (or that none matched).
See 
references/content-templates.md
for detailed selection criteria and intent mapping.
从
templates/
目录下的12种模板中选择合适的内容模板。
  1. 根据主题和搜索意图自动检测内容类型：
    信号模板
    “如何……”、流程、步骤
    how-to-guide
    “最佳X”、“Top N”、列表格式
    listicle
    客户成果、前后对比、数据指标
    case-study
    “X vs Y”、对比、替代方案
    comparison
    宽泛主题、综合性指南
    pillar-page
    “X是否值得”、产品评测
    product-review
    观点、预测、行业见解
    thought-leadership
    专家语录、多来源汇总
    roundup
    代码演练、工具演示、技术类内容
    tutorial
    突发新闻、算法更新、活动报道
    news-analysis
    调研结果、实验、原创数据
    data-research
    问答、知识库、“什么是X”
    faq-knowledge
  2. 加载匹配的模板 — 读取
    templates/<type>.md
    文件
  3. 调整大纲 — 利用模板的章节结构、标题模式及字数指引来构建第三阶段的大纲
  4. ** fallback方案** — 若没有完全匹配的模板，使用第三阶段的通用大纲结构。需告知用户所选模板（或未匹配到模板）。
详细的选择标准及意图映射请参考
references/content-templates.md
。

Phase 2: Research

第二阶段：调研工作

Spawn a 
blog-researcher
agent (or do inline research with WebSearch):
  1. Find 8-12 current statistics (2025-2026 data preferred)
    • Search: 
      [topic] study 2025 2026 data statistics
    • Prioritize tier 1-3 sources (see 
      references/quality-scoring.md
      )
    • Record: statistic, source name, URL, date, methodology
  2. Find a cover image (wide, high-quality, topic-relevant):
    • Search: 
      site:pixabay.com [topic] wide banner
      (preferred)
    • Alternative: 
      site:unsplash.com [topic] wide
    • Fallback: 
      site:pexels.com [topic] wide banner
    • Target dimensions: 1200x630 (OG-compatible) or 1920x1080
    • Or generate a custom SVG cover via 
      blog-chart
      (text-on-gradient with key stat)
    • See 
      references/visual-media.md
      for cover image sizing details
  3. Find 3-5 inline images from open-source platforms:
    • Pixabay (preferred): Search 
      site:pixabay.com [topic keywords]
      • Extract image URL from page
      • Direct URLs: 
        https://cdn.pixabay.com/photo/YYYY/MM/DD/HH/MM/filename.jpg
      • Verify with 
        curl -sI "<url>" | head -1
        returns HTTP 200
    • Unsplash (alternative): Search 
      site:unsplash.com [topic keywords]
      • Build URL: 
        https://images.unsplash.com/photo-<id>?w=1200&h=630&fit=crop&q=80
    • Pexels (fallback): Search 
      site:pexels.com [topic keywords]
  4. Plan 2-4 data visualizations from researched statistics
    • Select diverse chart types (see 
      references/visual-media.md
      )
    • Map data points to chart formats
调用
blog-researcher
代理（或通过WebSearch进行在线调研）：
  1. 查找8-12个最新统计数据（优先2025-2026年数据）
    • 搜索关键词：
      [主题] study 2025 2026 data statistics
    • 优先选择1-3级权威来源（参考
      references/quality-scoring.md
      ）
    • 记录内容：统计数据、来源名称、URL、日期、研究方法
  2. 查找封面图片（宽幅、高质量、与主题相关）：
    • 优先选择Pixabay：搜索
      site:pixabay.com [主题] wide banner
    • 备选平台Unsplash：
      site:unsplash.com [主题] wide
    • 兜底平台Pexels：
      site:pexels.com [主题] wide banner
    • 目标尺寸：1200x630（适配OG标准）或1920x1080
    • 或通过
      blog-chart
      生成自定义SVG封面（渐变背景+核心数据文本）
    • 封面图片尺寸详情请参考
      references/visual-media.md
  3. 从开源平台查找3-5张内文图片：
    • Pixabay（优先）：搜索
      site:pixabay.com [主题关键词]
      • 从页面提取图片URL
      • 直接URL格式：
        https://cdn.pixabay.com/photo/YYYY/MM/DD/HH/MM/filename.jpg
      • 通过
        curl -sI "<url>" | head -1
        验证返回HTTP 200状态码
    • Unsplash（备选）：搜索
      site:unsplash.com [主题关键词]
      • 构建URL：
        https://images.unsplash.com/photo-<id>?w=1200&h=630&fit=crop&q=80
    • Pexels（兜底）：搜索
      site:pexels.com [主题关键词]
  4. 基于调研的统计数据规划2-4个数据可视化图表
    • 选择多样化的图表类型（参考
      references/visual-media.md
      ）
    • 将数据点映射到对应图表格式

Phase 3: Outline Generation

第三阶段：大纲生成

Create a structured outline before writing. If a template was loaded in Phase 1.5, adapt this skeleton to match the template's section structure:
undefined
在撰写前创建结构化大纲。若在1.5阶段已加载模板，需将以下框架调整为匹配模板的章节结构：
undefined

[Title as Question — Include Primary Keyword]

[标题采用问句形式——包含核心关键词]

Introduction (100-150 words)

引言（100-150字）

  • Hook with surprising statistic
  • Problem/opportunity statement
  • What the reader will learn
TL;DR: [40-60 word standalone summary — placeholder]
  • 用令人惊讶的统计数据作为钩子
  • 问题/机遇陈述
  • 读者将学到的内容
TL;DR: [40-60字独立摘要——占位符]

H2: [Question Format] (300-400 words)

H2: [问句形式标题]（300-400字）

  • Answer-first paragraph (40-60 words with stat + source)
  • Supporting evidence
  • [Image placement]
  • Practical advice
  • [CITATION CAPSULE placeholder]
  • [INTERNAL-LINK: anchor text → target description]
  • 先答后释段落（40-60字，包含统计数据及来源）
  • 支撑证据
  • [图片位置]
  • 实用建议
  • [CITATION CAPSULE 占位符]
  • [INTERNAL-LINK: 锚文本 → 目标内容描述]

H2: [Question Format] (300-400 words)

H2: [问句形式标题]（300-400字）

  • Answer-first paragraph
  • [Chart: type + data description]
  • Analysis and implications
  • [CITATION CAPSULE placeholder]
  • [INTERNAL-LINK: anchor text → target description]
  • 先答后释段落
  • [图表：类型 + 数据描述]
  • 分析及影响
  • [CITATION CAPSULE 占位符]
  • [INTERNAL-LINK: 锚文本 → 目标内容描述]

H2: [Statement for Variety] (300-400 words)

H2: [陈述式标题（丰富多样性）]（300-400字）

  • Answer-first paragraph
  • Real-world example or case study
  • [Image placement]
  • [CITATION CAPSULE placeholder]
  • 先答后释段落
  • 真实案例或研究
  • [图片位置]
  • [CITATION CAPSULE 占位符]

H2: [Question Format] (300-400 words)

H2: [问句形式标题]（300-400字）

  • Answer-first paragraph
  • [Chart: type + data description]
  • Step-by-step guidance
  • [CITATION CAPSULE placeholder]
  • [INTERNAL-LINK: anchor text → target description]
  • 先答后释段落
  • [图表：类型 + 数据描述]
  • 分步指导
  • [CITATION CAPSULE 占位符]
  • [INTERNAL-LINK: 锚文本 → 目标内容描述]

H2: [Question Format] (200-300 words)

H2: [问句形式标题]（200-300字）

  • Answer-first paragraph
  • Forward-looking analysis
  • 先答后释段落
  • 前瞻性分析

FAQ Section (3-5 questions, 40-60 words each answer)

FAQ章节（3-5个问题，每个回答40-60字）

  • [INTERNAL-LINK: anchor text → detailed content]
  • [INTERNAL-LINK: 锚文本 → 详细内容]

Conclusion (100-150 words)

结论（100-150字）

  • Key takeaways (bulleted)
  • Call to action
  • [INTERNAL-LINK: anchor text → next logical content]

Present the outline to the user for approval before writing.
  • 核心要点（项目符号列表）
  • 行动号召
  • [INTERNAL-LINK: 锚文本 → 下一个相关内容]

在撰写前需将大纲提交给用户确认。

Phase 4: Chart Generation (Built-In)

第四阶段：图表生成（内置功能）

When the researcher identifies chart-worthy data (3+ comparable metrics, trend data, before/after comparisons):
  1. Select chart type using the diversity rule (no repeated types per post)
  2. Invoke 
    blog-chart
    sub-skill with: chart type, title, data values, source, platform format
  3. Embed the returned SVG directly in the post within a 
    <figure>
    wrapper
  4. Target 2-4 charts per 2,000-word post
  5. Distribute charts evenly — never cluster them
See 
references/visual-media.md
for chart type selection and styling rules.
当调研人员识别出适合可视化的数据（3个及以上可比较指标、趋势数据、前后对比数据）：
  1. 根据多样性规则选择图表类型（每篇文章不重复使用相同类型）
  2. 调用
    blog-chart
    子技能，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直接嵌入文章的
    <figure>
    容器中
  4. 每2000字文章目标配置2-4个图表
  5. 图表需均匀分布——切勿集中放置
图表类型选择及样式规则请参考
references/visual-media.md
。

Phase 5: Content Writing

第五阶段：内容撰写

Write the full article following these rules:
遵循以下规则撰写完整文章：

5a. Frontmatter

5a. 前置元数据（Frontmatter）

yaml
---
title: "[Question-format title with primary keyword]"
description: "[Fact-dense, 150-160 chars, includes 1 statistic]"
coverImage: "[URL from Pixabay/Unsplash/Pexels or generated SVG path]"
coverImageAlt: "[Descriptive sentence about the cover image]"
ogImage: "[Same as coverImage, or custom OG image URL]"
date: "YYYY-MM-DD"
lastUpdated: "YYYY-MM-DD"
author: "[Author name]"
tags: ["keyword1", "keyword2", "keyword3"]
---
If the platform uses a different field name (e.g., 
image
, 
hero
, 
thumbnail
), adapt to match the project's existing frontmatter convention.
yaml
---
title: "[含核心关键词的问句形式标题]"
description: "[150-160字符，包含1个统计数据的事实性描述]"
coverImage: "[Pixabay/Unsplash/Pexels的URL或生成的SVG路径]"
coverImageAlt: "[封面图片的描述性语句]"
ogImage: "[与coverImage相同，或自定义OG图片URL]"
date: "YYYY-MM-DD"
lastUpdated: "YYYY-MM-DD"
author: "[作者姓名]"
tags: ["keyword1", "keyword2", "keyword3"]
---
若平台使用不同的字段名（如
image
、
hero
、
thumbnail
），需调整为匹配项目现有前置元数据的规范。

5b. TL;DR Box

5b. TL;DR摘要框

Immediately after the introduction (before the first H2 body section), add a TL;DR box:
markdown
> **TL;DR:** [40-60 word standalone summary that makes sense without reading the
> full article. Contains the key finding or recommendation plus 1 statistic with
> source attribution. Reader should get the core value from this alone.]
Requirements:
  • 40-60 words, no more
  • Must be self-contained — understandable without reading the article
  • Include 1 specific statistic with source name
  • State the key finding, recommendation, or answer
  • Place as a blockquote directly after the introduction paragraph
在引言之后（第一个H2正文章节之前）添加TL;DR摘要框：
markdown
> **TL;DR:** [40-60字独立摘要，无需阅读全文即可理解。包含核心结论或建议及1个带来源的统计数据。读者仅通过此摘要即可获取核心价值。]
要求：
  • 40-60字，不得超字数
  • 必须独立成篇——无需阅读全文即可理解
  • 包含1个带来源名称的具体统计数据
  • 明确核心结论、建议或答案
  • 直接放置在引言段落之后的块引用中

5c. Answer-First Formatting (Critical)

5c. 先答后释格式（核心要求）

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
Pattern:
markdown
undefined
每个H2章节必须以40-60字的段落开头，包含：
  • 至少1个带来源的具体统计数据
  • 对标题隐含问题的直接回答
格式示例：
markdown
undefined

How Does X Impact Y in 2026?

2026年X对Y有何影响？

[Stat from source] (Source Name, year). [Direct answer to the heading question in 1-2 more sentences, explaining the implication and what this means for the reader.]
undefined
[来源统计数据]（来源名称，年份）。[用1-2句话直接回答标题问题，解释影响及对读者的意义。]
undefined

5d. Information Gain Markers

5d. 信息增量标记

Distribute at least 2-3 information gain markers throughout the article. These signal to search engines and AI systems that the content contains original value not available elsewhere.
Tag each with a comment or visible marker:
  • [ORIGINAL DATA]
    — Proprietary surveys, experiments, A/B test results, case study metrics the author collected first-hand
  • [PERSONAL EXPERIENCE]
    — First-hand observations, lessons learned from direct involvement, "when we tried X, Y happened" narratives
  • [UNIQUE INSIGHT]
    — Analysis others haven't made, contrarian perspectives backed by data, novel connections between existing research
Placement:
  • Weave into the body text naturally
  • Use as inline comments: 
    <!-- [ORIGINAL DATA] -->
    before the relevant paragraph
  • Or as visible callouts if the format supports it:
    markdown
    > **Our finding:** [original observation backed by specific data]
  • Minimum 2 per post, target 3 for comprehensive articles
These markers map directly to the "Originality/unique value markers" criterion in the Content Quality scoring category (see 
references/quality-scoring.md
).
在文章中分布至少2-3个信息增量标记，向搜索引擎和AI系统表明内容包含其他地方没有的原创价值。
每个标记使用注释或可见标注：
  • [ORIGINAL DATA]
    — 专有调研、实验、A/B测试结果、作者一手收集的案例数据
  • [PERSONAL EXPERIENCE]
    — 一手观察、直接参与获得的经验教训、“当我们尝试X时，发生了Y”的叙事
  • [UNIQUE INSIGHT]
    — 他人未提出的分析、有数据支撑的逆向观点、现有研究之间的新颖关联
放置规则：
  • 自然融入正文中
  • 可作为行内注释：
    <!-- [ORIGINAL DATA] -->
    放在相关段落之前
  • 若格式支持，也可作为可见提示：
    markdown
    > **我们的发现：** [有具体数据支撑的原创观察]
  • 每篇文章至少2个，综合性文章目标3个
这些标记直接对应
references/quality-scoring.md
中内容质量评分的“原创性/独特价值标记”标准。

5e. Citation Capsules

5e. 引用胶囊

For each major H2 section, generate a citation capsule — a 40-60 word self-contained passage designed so AI systems can extract and quote it directly.
Requirements per capsule:
  • 40-60 words, self-contained (makes sense in isolation)
  • Contains: one specific claim + one data point + source attribution
  • Written in a declarative, quotable style
  • Placed within the H2 section body (not as a separate block)
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" scoring category (15 points) in 
references/quality-scoring.md
.
每个主要H2章节需生成一个引用胶囊——40-60字的独立段落，方便AI系统直接提取引用。
每个引用胶囊的要求：
  • 40-60字，独立成篇（脱离上下文仍可理解）
  • 包含：1个具体主张 + 1个数据点 + 来源归因
  • 采用陈述式、适合引用的风格
  • 放置在H2章节的正文中（非独立块）
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系统提取并在回复中引用。
引用胶囊对应
references/quality-scoring.md
中的“AI引用适配性”评分项（15分）。

5f. Internal Linking Zones

5f. 内部链接区域

Mark internal linking opportunities throughout the article using placeholder notation. The user (or a follow-up pass) will resolve these to actual URLs.
Zone placement:
  • Introduction — Link to related pillar content or topic hub
  • Each H2 section — Link to supporting articles, deeper dives, related tools
  • FAQ section — Link answers to detailed content that expands on the answer
  • Conclusion — Link to the next logical piece of content the reader should consume
Format:
markdown
[INTERNAL-LINK: anchor text → target description]
Example:
markdown
For a deeper dive into keyword clustering, see our
[INTERNAL-LINK: complete guide to keyword clustering → pillar page on keyword research methodology].
Target 5-10 internal link zones per 2,000-word post. Use descriptive anchor text (never "click here" or "read more"). See 
references/internal-linking.md
for anchor text rules and linking strategy.
使用占位符标记文章中的内部链接机会，用户（或后续流程）将其替换为实际URL。
链接区域放置位置：
  • 引言 — 链接到相关的支柱内容或主题中心
  • 每个H2章节 — 链接到支撑文章、深度解析、相关工具
  • FAQ章节 — 将答案链接到展开详细内容的页面
  • 结论 — 链接到读者接下来应阅读的逻辑相关内容
格式：
markdown
[INTERNAL-LINK: 锚文本 → 目标内容描述]
示例：
markdown
如需深入了解关键词聚类，请查看我们的
[INTERNAL-LINK: 关键词聚类完整指南 → 关键词研究方法支柱页面]。
每2000字文章目标标记5-10个内部链接区域。使用描述性锚文本（切勿使用“点击此处”或“阅读更多”）。锚文本规则及链接策略请参考
references/internal-linking.md
。

5g. Paragraph Rules

5g. 段落规则

  • Every paragraph: 40-80 words (never exceed 150)
  • Every sentence: max 15-20 words
  • Start each paragraph with the most important information
  • Target Flesch Reading Ease: 60-70
  • 每个段落：40-80字（绝不超过150字）
  • 每个句子：最多15-20字
  • 每个段落以最重要的信息开头
  • 目标可读性评分（Flesch Reading Ease）：60-70

5h. Heading Rules

5h. 标题规则

  • One H1 (title only)
  • H2s for main sections (60-70% as questions)
  • H3s for subsections only — never skip levels
  • Include primary keyword naturally in 2-3 headings
  • 仅1个H1（仅标题使用）
  • H2用于主要章节（60-70%采用问句形式）
  • H3仅用于子章节——切勿跳过层级
  • 核心关键词自然融入2-3个标题中

5i. Image Embedding

5i. 图片嵌入

Standard markdown:
markdown
![Descriptive alt text — topic keywords naturally](https://cdn.pixabay.com/photo/...)
MDX with Next.js Image (if detected):
mdx
![Descriptive alt text — topic keywords naturally](https://cdn.pixabay.com/photo/...)
  • Place images after H2 headings, before body text
  • Space evenly throughout the post (not clustered)
  • Alt text should be a full descriptive sentence
标准markdown格式：
markdown
![描述性替代文本——自然融入主题关键词](https://cdn.pixabay.com/photo/...)
适配Next.js的MDX格式（若检测到）：
mdx
![描述性替代文本——自然融入主题关键词](https://cdn.pixabay.com/photo/...)
  • 图片放置在H2标题之后、正文之前
  • 在文章中均匀分布（切勿集中放置）
  • 替代文本应为完整的描述性句子

5j. Chart Embedding

5j. 图表嵌入

Standard markdown/HTML:
html
<figure>
  <svg viewBox="0 0 560 380" ...>...</svg>
  <figcaption>Source: [Source Name], [Year]</figcaption>
</figure>
MDX format:
mdx
<figure className="chart-container" style={{margin: '2.5rem 0', textAlign: 'center', padding: '1.5rem', borderRadius: '12px'}}>
  <svg viewBox="0 0 560 380" ...>...</svg>
</figure>
标准markdown/HTML格式：
html
<figure>
  <svg viewBox="0 0 560 380" ...>...</svg>
  <figcaption>来源：[来源名称]，[年份]</figcaption>
</figure>
MDX格式：
mdx
<figure className="chart-container" style={{margin: '2.5rem 0', textAlign: 'center', padding: '1.5rem', borderRadius: '12px'}}>
  <svg viewBox="0 0 560 380" ...>...</svg>
</figure>

5k. Citation Format

5k. 引用格式

Inline attribution (always):
markdown
Organic CTR declined 61% with AI Overviews ([Seer Interactive](https://www.seerinteractive.com/), 2025).
始终使用行内归因：
markdown
AI概览功能使自然点击率下降了61%（[Seer Interactive](https://www.seerinteractive.com/)，2025）。

5l. FAQ Section

5l. FAQ章节

Add 3-5 FAQ items with 40-60 word answers. Each answer must contain a statistic.
For MDX with FAQSchema component:
mdx
<FAQSchema faqs={[
  { question: "Question?", answer: "40-60 word answer with statistic and source." },
]} />
For standard markdown:
markdown
undefined
添加3-5个FAQ条目，每个回答40-60字。每个回答必须包含1个统计数据。
使用FAQSchema组件的MDX格式：
mdx
<FAQSchema faqs={[
  { question: "问题？", answer: "40-60字，包含统计数据及来源的回答。" },
]} />
标准markdown格式：
markdown
undefined

Frequently Asked Questions

常见问题

Question text here?

这里是问题文本？

Answer with statistic and source attribution (40-60 words).
undefined
包含统计数据及来源归因的回答（40-60字）。
undefined

5m. Internal Linking

5m. 内部链接

  • 5-10 internal links per 2,000-word post
  • Link to relevant existing content naturally
  • Use descriptive anchor text (not "click here")
  • 每2000字文章设置5-10个内部链接
  • 自然链接到相关的现有内容
  • 使用描述性锚文本（而非“点击此处”）

Phase 6: Quality Check

第六阶段：质量检查

Before delivering, verify:
交付前需验证以下内容：

Structure and Content

结构与内容

  1. Every H2 opens with a statistic + source
  2. No paragraph exceeds 150 words
  3. All statistics have named tier 1-3 sources
  4. 2-4 charts with type diversity
  5. 3-5 inline images with descriptive alt text
  6. Cover image present in frontmatter (coverImage + ogImage)
  7. FAQ section present with 3-5 items
  8. Heading hierarchy is clean (H1 -> H2 -> H3)
  9. Meta description is 150-160 chars with a stat
  1. 每个H2章节以统计数据+来源开头
  2. 无段落超过150字
  3. 所有统计数据均有1-3级权威来源
  4. 2-4个类型多样化的图表
  5. 3-5张带描述性替代文本的内文图片
  6. 前置元数据中包含封面图片（coverImage + ogImage）
  7. 包含3-5个条目的FAQ章节
  8. 标题层级清晰（H1 -> H2 -> H3）
  9. 元描述为150-160字符，包含1个统计数据

New Element Verification

新增元素验证

  1. TL;DR box present after introduction (40-60 words, contains statistic + source)
  2. At least 2-3 information gain markers (
    [ORIGINAL DATA]
    , 
    [PERSONAL EXPERIENCE]
    , or 
    [UNIQUE INSIGHT]
    )
  3. Citation capsules present in major H2 sections (40-60 words, self-contained, quotable)
  4. Internal linking zones marked in introduction, H2 sections, FAQ, and conclusion
  5. No AI-detectable phrases from banned list (see 
    agents/blog-writer.md
    )
  1. 引言后存在TL;DR摘要框（40-60字，包含统计数据+来源）
  2. 至少2-3个信息增量标记（
    [ORIGINAL DATA]
    、
    [PERSONAL EXPERIENCE]
    或
    [UNIQUE INSIGHT]
    ）
  3. 主要H2章节中存在引用胶囊（40-60字，独立成篇，适合引用）
  4. 引言、H2章节、FAQ及结论中标记了内部链接区域
  5. 无禁用列表中的AI可检测短语（参考
    agents/blog-writer.md
    ）

Burstiness and Naturalness Check

丰富度与自然度检查

  1. Sentence length variance — Verify a mix of short (8-word) and long (25-word) sentences. Uniform sentence length signals AI authorship.
  2. Banned AI phrase scan — Check for and remove:
    • "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
  3. Contractions — Verify natural use of contractions ("it's", "we've", "don't", "isn't"). Formal AI prose avoids contractions; natural writing uses them.
  4. Rhetorical questions — Verify at least one rhetorical question every 200-300 words to break up declarative patterns.
  1. 句子长度多样性 — 验证混合使用短句（8字）和长句（25字）。统一的句子长度是AI写作的信号。
  2. 禁用AI短语扫描 — 检查并移除：
    • “在当今数字化环境中”、“需要注意的是”、“深入探讨”
    • “游戏规则改变者”、“驾驭格局”、“彻底变革”、“无缝地”
    • “前沿”、“利用……的力量”、“借力”（动词形式）
    • “深入研究”、“至关重要”、“提升”、“培育”、“格局”（过度使用）
    • “多层面”、“强大的”、“织锦”、“开启”
    • 完整列表请参考
      agents/blog-writer.md
  3. 缩略语 — 验证自然使用缩略语（“it's”、“we've”、“don't”、“isn't”）。正式的AI文本避免使用缩略语，自然写作会使用。
  4. 反问句 — 验证每200-300字至少有1个反问句，以打破陈述式模式。

Phase 7: Delivery

第六阶段：交付

Present the completed article with a summary:
undefined
提交完成的文章并附带摘要：
undefined

Blog Post Complete: [Title]

博客文章完成：[标题]

Template Used

使用的模板

  • [Template name] (or "generic outline — no template matched")
  • [模板名称]（或“通用大纲——未匹配到模板”）

Statistics

统计数据

  • [N] sourced statistics from tier 1-3 sources
  • [N] unique sources cited
  • [数量]个来自1-3级来源的统计数据
  • [数量]个独特引用来源

Visual Elements

视觉元素

  • Cover image: [source — Pixabay/Unsplash/Pexels or generated SVG]
  • [N] inline images (Pixabay/Unsplash/Pexels)
  • [N] SVG charts (types: bar, lollipop, donut, line)
  • 封面图片：[来源——Pixabay/Unsplash/Pexels或生成的SVG]
  • [数量]张内文图片（Pixabay/Unsplash/Pexels）
  • [数量]个SVG图表（类型：柱状图、棒棒糖图、环形图、折线图）

Dual-Optimization Elements

双重优化元素

  • TL;DR box: present (N words)
  • Information gain markers: [N] ([types used])
  • Citation capsules: [N] across H2 sections
  • Internal linking zones: [N] marked
  • TL;DR摘要框：已存在（[字数]字）
  • 信息增量标记：[数量]个（使用的类型：[类型列表]）
  • 引用胶囊：[数量]个，分布在主要H2章节
  • 内部链接区域：[数量]个已标记

Structure

结构

  • [N] H2 sections with answer-first formatting
  • [N] FAQ items with schema
  • Word count: ~[N] words
  • Estimated reading time: [N] min
  • [数量]个采用先答后释格式的H2章节
  • [数量]个带Schema的FAQ条目
  • 字数：约[数量]字
  • 预估阅读时间：[数量]分钟

Naturalness

自然度

  • Sentence length variance: [pass/fail]
  • AI phrase scan: [pass/fail]
  • Contractions used: [yes/no]
  • Rhetorical questions: [N] (target: 1 per 200-300 words)
  • 句子长度多样性：[通过/不通过]
  • AI短语扫描：[通过/不通过]
  • 使用缩略语：[是/否]
  • 反问句：[数量]个（目标：每200-300字1个）

Next Steps

后续步骤

  • Review and customize for your brand voice
  • Resolve [INTERNAL-LINK] placeholders with actual URLs
  • Add internal links to your existing content
  • Run 
    /blog analyze <file>
    to verify quality score
undefined
  • 审核并调整以匹配你的品牌调性
  • 将[INTERNAL-LINK]占位符替换为实际URL
  • 添加指向现有内容的内部链接
  • 运行
    /blog analyze <file>
    验证质量评分
",