content-quality-auditor
Use when auditing content quality, E-E-A-T, publish readiness, or 内容质量/EEAT评分. Runs 80-item CORE-EEAT scoring with veto checks and fix plan.
npx skills add ViryaZheng/recomby-geo --skill content-quality-auditor --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Audits content quality against an 80-item CORE-EEAT benchmark, awarding Pass/Partial/Fail per item, and generates dimension scores (8 dimensions, 0-100 each), system scores (GEO/SEO), a prioritized Action Plan, and a Top 5 improvements list.
How it works
It is designed to be used when auditing content quality before publishing or evaluating existing content. It:
- Performs a full 80-item audit with per-item scoring (Pass = 10, Partial = 5, Fail = 0).
- Calculates Dimension Scores for 8 dimensions (0-100 each).
- Computes System Scores (GEO Score and SEO Score).
- Applies content-type-specific weights to produce weighted totals.
- Detects vetoes for critical trust issues (T04, C01, R10) and flags them.
- Produces a Top 5 improvements ranking and an actionable improvement plan.
- Exposes a Quick Start with prompts for auditing content or comparing with competitors.
When to use it
Use when content needs a quality check before publishing or when asked for E-E-A-T analysis or publish readiness. It is triggered by prompts such as "Audit Content" or related phrases and can be auto-triggered after content is written or edited as part of a hook.
What it can touch
The skill integrates with tools listed in the frontmatter for automated data collection (e.g., content from URLs or text inputs) and then outputs a CORE-EEAT audit report, a publish-readiness verdict, and a handoff summary. It also promotes veto items to memory caches and top improvements to memory/open-loops. The output includes a structured artifact ready for storage under memory/audits/content/.
Caveats
The skill enforces a gate verdict (SHIP / FIX / BLOCK) and must report any veto items immediately. It relies on access to target content and benchmark references; missing data may lead to Insufficient Data flags. The cap and veto handling rules, including how scores are adjusted to a maximum 60 in cap scenarios, are described in the included fail-cap framework references (not reproduced here).
# Content Quality Auditor > Based on [CORE-EEAT Content Benchmark](https://github.com/aaron-he-zhu/core-eeat-content-benchmark). Full benchmark reference: [references/core-eeat-benchmark.md](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. ## When This Must Trigger Use this when content needs a quality check before publishing — even if the user doesn't use audit terminology: - User asks "is this ready to publish" or "how good is this" - User just finished writing with seo-content-writer or content-refresher - **PostToolUse hook auto-triggers**: after content is written or substantially edited, the hook recommends this audit. When hook-triggered, skip setup questions — audit the content that was just produced. - 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 cit
- When This Must Trigger
- What This Skill Does
- Quick Start
- Audit Content
- Audit with Content Type
- Comparative Audit
- Skill Contract
- Data Sources
- Decision Gates
- Instructions
- Step 1: Preparation
- Step 2: CORE Audit (40 items)
- Step 3: EEAT Audit (40 items)
- §1 · Handoff Schema (authoritative)
What does the content-quality-auditor skill do?
Use when auditing content quality, E-E-A-T, publish readiness, or 内容质量/EEAT评分. Runs 80-item CORE-EEAT scoring with veto checks and fix plan.
How do I install it?
Run `npx skills add ViryaZheng/recomby-geo --skill content-quality-auditor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ViryaZheng/recomby-geo, a repository with 510 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.