Is the Content Quality Auditor skill free?

Yes. The skill itself is free from ViryaZheng/recomby-geo. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Content Quality Auditor SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Content Quality Auditor?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Content Quality Auditor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Content Quality Auditor

Scores content against an 80-item E-E-A-T rubric with veto checks before publishing

by ViryaZheng · ViryaZheng/recomby-geo

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · d88894f

Fetched SKILL.md and all 4 reference files (all HTTP 200) and read the full 80-item benchmark, weight table, and veto/cap runbook. Verified install in a temp HOME: clone+cp places SKILL.md and references/ at ~/.claude/skills/content-quality-auditor/. For the output test I wrote a short FlexiRise standing-desk review with a planted price contradiction ($299 intro vs $349 comparison table), a height-range contradiction (28-47in vs 30-45in), and an undisclosed Amazon affiliate link, then produced two artifacts. Baseline (no rubric) called it "Good to publish, ~7/10" and missed all three defects; the skill-followed audit caught both self-contradictions (R10 veto) and the undisclosed affiliate link (T04 veto), triggered the 2+-veto BLOCKED path, and returned "Cannot score yet — fix 2 critical issues" instead of a ship verdict. Not a 10 because many EEAT items are site-level (marked N/A when auditing pasted text) and the elaborate cap/handoff machinery is overhead beyond the core checklist value.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Content Quality Auditor does

Audits an article or URL against a fixed 80-item CORE-EEAT rubric (8 dimensions), producing per-item Pass/Partial/Fail scores, dimension and weighted totals by content type, veto detection for disclosure/clickbait/self-contradiction, and a prioritized fix plan. Triggers when the user asks whether content is ready to publish, wants an E-E-A-T or content-quality score, or asks to grade an article. Runs as a rubric in Claude's context; needs no external tools for pasted text (WebFetch only to audit a live URL).

How to install Content Quality Auditor

git clone --depth 1 https://github.com/ViryaZheng/recomby-geo.git /tmp/content-quality-auditor-src
mkdir -p ~/.claude/skills
cp -R /tmp/content-quality-auditor-src/plugins/recomby-geo/skills/content-quality-auditor ~/.claude/skills/content-quality-auditor
# Self-contained: references/ (core-eeat-benchmark.md, item-reference.md, fail-cap-worked-examples.md, cite-domain-rating.md) are copied with it.
# No extra deps for pasted content. allowed-tools: WebFetch — used only to fetch a live URL you ask it to audit.
# NOTE: SKILL.md links to sibling skills (content-refresher, seo-content-writer) and a PostToolUse validation hook that live in a DIFFERENT repo (aaron-he-zhu/seo-geo-claude-skills) and are NOT installed by this copy; the audit itself runs standalone.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Content Quality Auditor

/content-quality-auditor Scores content against an 80-item E-E-A-T rubric with veto checks before publishing

It also activates on plain-language prompts like these:

Audit this article's E-E-A-T score before publishing
Check if this content is ready to publish
Run the CORE-EEAT scoring on this page

Frequently asked questions

Is the Content Quality Auditor skill free?: Yes. The skill itself is free from ViryaZheng/recomby-geo. SkillProof publishes the install command and an independent test verdict at no cost.
Does Content Quality Auditor work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md and all 4 reference files (all HTTP 200) and read the full 80-item benchmark, weight table, and veto/cap runbook. Verified install in a temp HOME: clone+cp places SKILL.md and references/ at ~/.claude/skills/content-quality-auditor/. For the output test I wrote a short FlexiRise standing-desk review with a planted price contradiction ($299 intro vs $349 comparison table), a height-range contradiction (28-47in vs 30-45in), and an undisclosed Amazon affiliate link, then produced two artifacts. Baseline (no rubric) called it "Good to publish, ~7/10" and missed all three defects; the skill-followed audit caught both self-contradictions (R10 veto) and the undisclosed affiliate link (T04 veto), triggered the 2+-veto BLOCKED path, and returned "Cannot score yet — fix 2 critical issues" instead of a ship verdict. Not a 10 because many EEAT items are site-level (marked N/A when auditing pasted text) and the elaborate cap/handoff machinery is overhead beyond the core checklist value.
What is the Content Quality Auditor SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Content Quality Auditor?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Content Quality Auditor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.