Back to Details

content-quality-auditor

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Content Quality Auditor

内容质量审核器

Based on CORE-EEAT Content Benchmark. Full benchmark reference: references/core-eeat-benchmark.md
This skill evaluates content quality across 80 standardized criteria organized in 8 dimensions. It produces a comprehensive audit report with per-item scoring, dimension and system scores, weighted totals by content type, and a prioritized action plan.
基于CORE-EEAT内容基准。完整基准参考：references/core-eeat-benchmark.md
本技能会依据8个维度下的80项标准化标准评估内容质量，生成包含逐项评分、维度与系统得分、按内容类型加权的总分，以及优先级行动计划的全面审核报告。

When to Use This Skill

何时使用本技能

  • Auditing content quality before publishing
  • Evaluating existing content for improvement opportunities
  • Benchmarking content against CORE-EEAT standards
  • Comparing content quality against competitors
  • Assessing both GEO readiness (AI citation potential) and SEO strength (source credibility)
  • Running periodic content quality checks as part of a content maintenance program
  • After writing or optimizing content with seo-content-writer or geo-content-optimizer
  • 发布前审核内容质量
  • 评估现有内容的优化空间
  • 对照CORE-EEAT标准进行内容基准测试
  • 与竞品内容进行质量对比
  • 评估GEO适配性（AI引用潜力）和SEO实力（来源可信度）
  • 将定期内容质量检查作为内容维护计划的一部分
  • 使用seo-content-writer或geo-content-optimizer完成内容撰写或优化后

What This Skill Does

本技能的功能

  1. Full 80-Item Audit: Scores every CORE-EEAT check item as Pass/Partial/Fail
  2. Dimension Scoring: Calculates scores for all 8 dimensions (0-100 each)
  3. System Scoring: Computes GEO Score (CORE) and SEO Score (EEAT)
  4. Weighted Totals: Applies content-type-specific weights for final score
  5. Veto Detection: Flags critical trust violations (T04, C01, R10)
  6. Priority Ranking: Identifies Top 5 improvements sorted by impact
  7. Action Plan: Generates specific, actionable improvement steps
  1. 完整80项审核：对每一项CORE-EEAT检查项进行通过/部分通过/不通过评分
  2. 维度评分：计算8个维度的得分（各0-100分）
  3. 系统评分：计算GEO得分（CORE）和SEO得分（EEAT）
  4. 加权总分：根据内容类型应用特定权重计算最终得分
  5. 否决项检测：标记严重信任违规项（T04、C01、R10）
  6. 优先级排序：按影响程度排序找出前5项优化点
  7. 行动计划：生成具体、可执行的优化步骤

How to Use

使用方法

Audit Content

审核内容

Audit this content against CORE-EEAT: [content text or URL]
Run a content quality audit on [URL] as a [content type]
Audit this content against CORE-EEAT: [content text or URL]
Run a content quality audit on [URL] as a [content type]

Audit with Content Type

指定内容类型审核

CORE-EEAT audit for this product review: [content]
Score this how-to guide against the 80-item benchmark: [content]
CORE-EEAT audit for this product review: [content]
Score this how-to guide against the 80-item benchmark: [content]

Comparative Audit

对比审核

Audit my content vs competitor: [your content] vs [competitor content]
Audit my content vs competitor: [your content] vs [competitor content]

Data Sources

数据源

See CONNECTORS.md for tool category placeholders.
With ~~web crawler + ~~SEO tool connected: Automatically fetch page content, extract HTML structure, check schema markup, verify internal/external links, and pull competitor content for comparison.
With manual data only: Ask the user to provide:
  1. Content text, URL, or file path
  2. Content type (if not auto-detectable): Product Review, How-to Guide, Comparison, Landing Page, Blog Post, FAQ Page, Alternative, Best-of, or Testimonial
  3. Optional: competitor content for benchmarking
Proceed with the full 80-item audit using provided data. Note in the output which items could not be fully evaluated due to missing access (e.g., backlink data, schema markup, site-level signals).
工具类别占位符请参考CONNECTORS.md。
连接~~网页爬虫 + ~~SEO工具后： 自动获取页面内容、提取HTML结构、检查Schema标记、验证内链/外链，并拉取竞品内容进行对比。
仅手动提供数据时： 请用户提供：
  1. 内容文本、URL或文件路径
  2. 内容类型（若无法自动检测）：产品评测、操作指南、对比文章、落地页、博客文章、FAQ页面、替代方案、最佳推荐或客户证言
  3. 可选：用于基准测试的竞品内容
使用提供的数据执行完整的80项审核。在输出中注明因缺少访问权限而无法全面评估的项（如反向链接数据、Schema标记、站点级信号等）。

Instructions

操作步骤

When a user requests a content quality audit:
当用户请求内容质量审核时：

Step 1: Preparation

步骤1：准备工作

markdown
undefined
markdown
undefined

Audit Setup

审核设置

Content: [title or URL] Content Type: [auto-detected or user-specified] Dimension Weights: [loaded from content-type weight table]
内容：[标题或URL] 内容类型：[自动检测或用户指定] 维度权重：[从内容类型权重表加载]

Veto Check (Emergency Brake)

否决项检查（紧急制动）

Veto ItemStatusAction
T04: Disclosure Statements✅ Pass / ⚠️ VETO[If VETO: "Add disclosure banner at page top immediately"]
C01: Intent Alignment✅ Pass / ⚠️ VETO[If VETO: "Rewrite title and first paragraph"]
R10: Content Consistency✅ Pass / ⚠️ VETO[If VETO: "Verify all data before publishing"]

If any veto item triggers, flag it prominently at the top of the report and recommend immediate action before continuing the full audit.
否决项状态操作
T04: 披露声明✅ 通过 / ⚠️ 否决[若否决："立即在页面顶部添加披露横幅"]
C01: 意图匹配✅ 通过 / ⚠️ 否决[若否决："重写标题和第一段"]
R10: 内容一致性✅ 通过 / ⚠️ 否决[若否决："发布前验证所有数据"]

若任何否决项触发，需在报告顶部显著标记，并建议立即采取行动后再继续完整审核。

Step 2: CORE Audit (40 items)

步骤2：CORE审核（40项）

Evaluate each item against the criteria in references/core-eeat-benchmark.md.
Score each item:
  • Pass = 10 points (fully meets criteria)
  • Partial = 5 points (partially meets criteria)
  • Fail = 0 points (does not meet criteria)
markdown
undefined
对照references/core-eeat-benchmark.md中的标准评估每一项。
为每一项打分：
  • 通过 = 10分（完全符合标准）
  • 部分通过 = 5分（部分符合标准）
  • 不通过 = 0分（不符合标准）
markdown
undefined

C — Contextual Clarity

C — 语境清晰度

IDCheck ItemScoreNotes
C01Intent AlignmentPass/Partial/Fail[specific observation]
C02Direct AnswerPass/Partial/Fail[specific observation]
............
C10Semantic ClosurePass/Partial/Fail[specific observation]
C Score: [X]/100
ID检查项得分备注
C01意图匹配通过/部分通过/不通过[具体观察结果]
C02直接答案通过/部分通过/不通过[具体观察结果]
............
C10语义完整性通过/部分通过/不通过[具体观察结果]
C维度得分：[X]/100

O — Organization

O — 组织结构

IDCheck ItemScoreNotes
O01Heading HierarchyPass/Partial/Fail[specific observation]
............
O Score: [X]/100
ID检查项得分备注
O01标题层级通过/部分通过/不通过[具体观察结果]
............
O维度得分：[X]/100

R — Referenceability

R — 可参考性

[Same format]
R Score: [X]/100
[相同格式]
R维度得分：[X]/100

E — Exclusivity

E — 独特性

[Same format]
E Score: [X]/100
undefined
[相同格式]
E维度得分：[X]/100
undefined

Step 3: EEAT Audit (40 items)

步骤3：EEAT审核（40项）

Same format for Exp, Ept, A, T dimensions.
markdown
undefined
Exp、Ept、A、T维度采用相同格式。
markdown
undefined

Exp — Experience

Exp — 体验

IDCheck ItemScoreNotes
Exp01First-Person NarrativePass/Partial/Fail[specific observation]
............
Exp Score: [X]/100
ID检查项得分备注
Exp01第一人称叙事通过/部分通过/不通过[具体观察结果]
............
Exp维度得分：[X]/100

Ept — Expertise

Ept — 专业性

[Same format]
[相同格式]

A — Authority

A — 权威性

[Same format]
[相同格式]

T — Trust

T — 可信度

[Same format]

**Note**: Some EEAT items (A01 Backlink Profile, A05 Brand Recognition, A07 Knowledge Graph Presence, etc.) may require site-level data not available from content alone. Score what is observable; mark unverifiable items as "N/A — requires site-level data" and exclude from dimension average.
[相同格式]

**注意**：部分EEAT项（A01反向链接档案、A05品牌认知度、A07知识图谱存在性等）可能需要仅从内容无法获取的站点级数据。对可观察到的项进行打分；将无法验证的项标记为"不适用 — 需要站点级数据"，并从维度平均分中排除。

Step 4: Scoring & Report

步骤4：评分与报告

Calculate scores and generate the final report:
markdown
undefined
计算得分并生成最终报告：
markdown
undefined

CORE-EEAT Audit Report

CORE-EEAT审核报告

Overview

概述

  • Content: [title]
  • Content Type: [type]
  • Audit Date: [date]
  • Total Score: [score]/100 ([rating])
  • GEO Score: [score]/100 | SEO Score: [score]/100
  • Veto Status: ✅ No triggers / ⚠️ [item] triggered
  • 内容：[标题]
  • 内容类型：[类型]
  • 审核日期：[日期]
  • 总分：[得分]/100 ([评级])
  • GEO得分：[得分]/100 | SEO得分：[得分]/100
  • 否决状态：✅ 无触发项 / ⚠️ [项]已触发

Dimension Scores

维度得分

DimensionScoreRatingWeightWeighted
C — Contextual Clarity[X]/100[rating][X]%[X]
O — Organization[X]/100[rating][X]%[X]
R — Referenceability[X]/100[rating][X]%[X]
E — Exclusivity[X]/100[rating][X]%[X]
Exp — Experience[X]/100[rating][X]%[X]
Ept — Expertise[X]/100[rating][X]%[X]
A — Authority[X]/100[rating][X]%[X]
T — Trust[X]/100[rating][X]%[X]
Weighted Total[X]/100
Score Calculation:
  • GEO Score = (C + O + R + E) / 4
  • SEO Score = (Exp + Ept + A + T) / 4
  • Weighted Score = Σ (dimension_score × content_type_weight)
Rating Scale: 90-100 Excellent | 75-89 Good | 60-74 Medium | 40-59 Low | 0-39 Poor
维度得分评级权重加权得分
C — 语境清晰度[X]/100[评级][X]%[X]
O — 组织结构[X]/100[评级][X]%[X]
R — 可参考性[X]/100[评级][X]%[X]
E — 独特性[X]/100[评级][X]%[X]
Exp — 体验[X]/100[评级][X]%[X]
Ept — 专业性[X]/100[评级][X]%[X]
A — 权威性[X]/100[评级][X]%[X]
T — 可信度[X]/100[评级][X]%[X]
加权总分[X]/100
得分计算方式:
  • GEO得分 = (C + O + R + E) / 4
  • SEO得分 = (Exp + Ept + A + T) / 4
  • 加权得分 = Σ (维度得分 × 内容类型权重)
评级标准：90-100 优秀 | 75-89 良好 | 60-74 中等 | 40-59 较差 | 0-39 糟糕

Per-Item Scores

逐项得分

CORE — Content Body (40 Items)

CORE — 内容主体（40项）

IDCheck ItemScoreNotes
C01Intent Alignment[Pass/Partial/Fail][observation]
C02Direct Answer[Pass/Partial/Fail][observation]
............
ID检查项得分备注
C01意图匹配[通过/部分通过/不通过][观察结果]
C02直接答案[通过/部分通过/不通过][观察结果]
............

EEAT — Source Credibility (40 Items)

EEAT — 来源可信度（40项）

IDCheck ItemScoreNotes
Exp01First-Person Narrative[Pass/Partial/Fail][observation]
............
ID检查项得分备注
Exp01第一人称叙事[通过/部分通过/不通过][观察结果]
............

Top 5 Priority Improvements

前5项优先级优化点

Sorted by: weight × points lost (highest impact first)
  1. [ID] [Name] — [specific modification suggestion]
    • Current: [Fail/Partial] | Potential gain: [X] weighted points
    • Action: [concrete step]
  2. [ID] [Name] — [specific modification suggestion]
    • Current: [Fail/Partial] | Potential gain: [X] weighted points
    • Action: [concrete step]
3–5. [Same format]
排序依据：权重 × 丢失分数（影响程度从高到低）
  1. [ID] [名称] — [具体修改建议]
    • 当前状态：[不通过/部分通过] | 潜在提升：[X]加权分
    • 操作：[具体步骤]
  2. [ID] [名称] — [具体修改建议]
    • 当前状态：[不通过/部分通过] | 潜在提升：[X]加权分
    • 操作：[具体步骤]
3–5. [相同格式]

Action Plan

行动计划

Quick Wins (< 30 minutes each)

快速完成项（每项<30分钟）

  • [Action 1]
  • [Action 2]
  • [操作1]
  • [操作2]

Medium Effort (1-2 hours)

中等难度（1-2小时）

  • [Action 3]
  • [Action 4]
  • [操作3]
  • [操作4]

Strategic (Requires planning)

战略性优化（需规划）

  • [Action 5]
  • [Action 6]
  • [操作5]
  • [操作6]

Recommended Next Steps

推荐后续步骤

  • For full content rewrite: use seo-content-writer with CORE-EEAT constraints
  • For GEO optimization: use geo-content-optimizer targeting failed GEO-First items
  • For content refresh: use content-refresher with weak dimensions as focus
  • For technical fixes: run 
    /seo:check-technical
    for site-level issues
undefined
  • 如需完整重写内容：使用带CORE-EEAT约束的seo-content-writer
  • 如需GEO优化：使用针对未通过GEO优先项的geo-content-optimizer
  • 如需内容更新：使用以薄弱维度为重点的content-refresher
  • 如需技术修复：运行
    /seo:check-technical
    检查站点级问题
undefined

Validation Checkpoints

验证检查点

Input Validation

输入验证

  • Content source identified (text, URL, or file path)
  • Content type confirmed (auto-detected or user-specified)
  • Content is substantial enough for meaningful audit (≥300 words)
  • If comparative audit, competitor content also provided
  • 已识别内容来源（文本、URL或文件路径）
  • 已确认内容类型（自动检测或用户指定）
  • 内容足够详实以进行有意义的审核（≥300词）
  • 若为对比审核，已提供竞品内容

Output Validation

输出验证

  • All 80 items scored (or marked N/A with reason)
  • All 8 dimension scores calculated correctly
  • Weighted total matches content-type weight configuration
  • Veto items checked and flagged if triggered
  • Top 5 improvements sorted by weighted impact, not arbitrary
  • Every recommendation is specific and actionable (not generic advice)
  • Action plan includes concrete steps with effort estimates
  • 所有80项已打分（或标记为不适用并说明原因）
  • 所有8个维度得分计算正确
  • 加权总分与内容类型权重配置匹配
  • 已检查否决项并在触发时标记
  • 前5项优化点按加权影响排序，而非随意排序
  • 每一项建议均具体且可执行（非通用建议）
  • 行动计划包含带工作量预估的具体步骤

Example

示例

User: "Audit this article about email marketing best practices for CORE-EEAT quality"
Output: [Full audit report following the structure above, with all 80 items scored, dimension and total scores calculated using Blog Post weights (C:25%, O:10%, R:10%, E:20%, Exp:10%, Ept:10%, A:5%, T:10%), Top 5 improvements identified, and action plan generated]
用户："审核这篇关于电子邮件营销最佳实践的文章的CORE-EEAT质量"
输出：[遵循上述结构的完整审核报告，使用博客文章权重（C:25%, O:10%, R:10%, E:20%, Exp:10%, Ept:10%, A:5%, T:10%）计算所有80项得分、维度和总分，确定前5项优化点并生成行动计划]

Tips for Success

成功技巧

  1. Start with veto items — T04, C01, R10 are deal-breakers regardless of total score
  2. Focus on high-weight dimensions — Different content types prioritize different dimensions
  3. GEO-First items matter most for AI visibility — Prioritize items tagged GEO 🎯 if AI citation is the goal
  4. Some EEAT items need site-level data — Don't penalize content for things only observable at the site level (backlinks, brand recognition)
  5. Use the weighted score, not just the raw average — A product review with strong Exclusivity matters more than strong Authority
  6. Re-audit after improvements — Run again to verify score improvements and catch regressions
  1. 先检查否决项 — T04、C01、R10是无论总分如何都需要优先处理的关键项
  2. 聚焦高权重维度 — 不同内容类型优先的维度不同
  3. GEO优先项对AI可见性最重要 — 若目标是AI引用，优先处理标记为GEO 🎯的项
  4. 部分EEAT项需要站点级数据 — 不要因仅能在站点级观察到的内容（反向链接、品牌认知度）而惩罚内容
  5. 使用加权得分而非原始平均分 — 产品评测中独特性得分高比权威性得分高更重要
  6. 优化后重新审核 — 再次运行审核以验证得分提升情况并发现倒退问题

Related Skills

相关技能

  • seo-content-writer — Write content that scores high on CORE dimensions
  • geo-content-optimizer — Optimize for GEO-First items
  • content-refresher — Update content to improve weak dimensions
  • on-page-seo-auditor — Technical on-page audit (complements this skill)
  • memory-management — Store audit results for tracking over time
  • seo-content-writer — 撰写在CORE维度得分高的内容
  • geo-content-optimizer — 针对GEO优先项进行优化
  • content-refresher — 更新内容以提升薄弱维度
  • on-page-seo-auditor — 技术页面内SEO审核（补充本技能）
  • memory-management — 存储审核结果以跟踪长期变化 ",