Index of every page on this site: llms.txt
All skills
aaron-he-zhu avatar

/content-quality-auditor

@3a1578a
Run it yourself

Signpost → the 16 SEO/GEO agent skills live in aaron-marketing-skills; this repo's standalone 20-skill line is preserved at tag v9.9.12. Install: npx skills add aaron-he-zhu/aaron-marketing-skills

Use this Skill: https://skilld.dev/gh/aaron-he-zhu/seo-geo-claude-skills/content-quality-auditor

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈56 tokens for metadata: the name and description. ≈246 when used: this file.

SKILL.md has missing or invalid fields
  • The name in the SKILL.md header is missing or is not text.
  • The description in the SKILL.md header is missing or is not text.
Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

content-quality-auditor has moved

[!IMPORTANT] seo-geo-claude-skills is now a signpost repo — its skills are no longer developed here. This file exists only so older links to cross-cutting/content-quality-auditor/ keep resolving.

Active version: seo-geo/optimize/content-quality-auditor in the aaron-marketing-skills bundle.

Frozen standalone copy (unchanged, tag v9.9.12): cross-cutting/content-quality-auditor/SKILL.md.

Install the active skill from the bundle:

npx skills add aaron-he-zhu/aaron-marketing-skills -s content-quality-auditor

Full 20 → 16 mapping: see the repo README.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning6mo5 checks · Risk SAFE
  • Gen Agent Trust Hub6mo

    The skill is a comprehensive content quality auditor designed to evaluate text or web content against SEO and E-E-A-T standards. It includes built-in security instructions to prevent the misuse of fetched content as instructions. No malicious activity or vulnerabilities were detected.

  • Socket6mo

    No alerts

  • Snyk6mo

    Risk: MEDIUM · 1 issue

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 3a1578a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 5 months ago
  • SEO
  • content-quality
  • e-e-a-t
  • core-eeat
  • audit
  • publish-readiness
  • helpful-content
  • content-scoring

README badge

README badge for aaron-he-zhu/seo-geo-claude-skills/content-quality-auditor

Evaluates content against 80 standardized CORE-EEAT criteria across 8 dimensions, producing dimension scores, veto checks for critical trust violations, and a prioritized action plan. Targets publish-readiness assessment and quality benchmarking before content goes live.

Generated from the current SKILL.md.

What is CORE-EEAT and how does this skill score it?
CORE-EEAT is an 80-item content benchmark split into 8 dimensions: C, O, R, E (CORE) and Exp, Ept, A, T (EEAT). Each item is scored Pass (10 points), Partial (5 points), or Fail (0 points), then aggregated into dimension scores (0-100) and a final weighted score based on content type.
Does this skill audit on-page SEO elements like headers and meta tags?
No. This skill focuses on content quality and E-E-A-T criteria. Use on-page-seo-auditor for structural tags and headers, or domain-authority-auditor for domain and citation trust.
What does the SHIP/FIX/BLOCK verdict mean?
SHIP means no critical issues and dimension scores above threshold. FIX means issues were found but none are critical trust violations. BLOCK means a critical veto item (T04, C01, or R10) failed and must be addressed before publishing.
Can I audit content without providing a URL?
Yes. You can paste content text directly or provide a file path. The skill will run the full 80-item audit with provided data and note which items could not be fully evaluated due to missing access (e.g., backlink data or schema markup).
What happens if my content is too short?
The skill will state the actual word count and ask whether to expand to minimum (blog/guide: 300 words; product/landing page: 150 words), continue with Insufficient Data flags, or cancel the audit.

Generated from the current SKILL.md. These answers refresh after source changes.