- Home
- Skills
- Marketing & SEO
- seo-content-quality-gate
Seo Content Quality Gate
Pre-publish SEO audit. 60+ checks: keywords, structure, metadata, links, schema.org, readability. 0-100 score with fix list.
Free
Works with the AI tools you already use
seo-content-quality-gate
Example session with this skill installed
Audit my markdown draft about 'best wireless headphones 2024' and give me a fix list based on the target keyword.
- Read your context and instructions
- Compiled the seo-content-quality-gate
Score: 72/100. Fix 3 Critical issues: Add keyword to H1, include a meta description, and add 2 internal links. Expected traffic lift: +25%. See report.md for details.
Connects securely to your tools. The creator never sees your data.
About this skill
SEO Content Quality Gate
Catch the on-page SEO issues before you hit publish. This skill audits your article draft against 60+ ranking factors, scores it 0-100, and tells you exactly what to fix.
What it does
A single pass through your markdown / HTML article that checks:
- Keyword optimization — title tag, H1, H2s, first 100 words, density, LSI keywords
- Structure — heading hierarchy, paragraph length, list/table usage
- Metadata — title length, meta description, OG tags, Twitter cards
- Links — internal links (count + quality), external links (no-follow balance), broken anchors
- Readability — Flesch reading ease, sentence length, passive voice, transition words
- Schema.org — Article, BreadcrumbList, FAQPage, HowTo detection
- Media — image alt text, captions, compression hints
- Technical — canonical URL, robots meta, hreflang, mobile-friendly signals
Returns a 0-100 score with a prioritized fix list and an "expected rank boost" estimate per fix.
When to use it
- You publish content regularly and want a consistent quality bar
- Your traffic plateaued and you don't know what's wrong
- You use AI to draft articles and need a quality filter
- You're submitting guest posts and want to maximize acceptance
- Your agency delivers content to clients and wants a sign-off report
Why it's better than ad-hoc prompting
Most "review my article for SEO" prompts give 3 generic tips. This skill is different:
- Quantitative — every check has a threshold and a score, not a feeling
- Comprehensive — 60+ checks, not 5
- Actionable — every failure has a copy-paste fix
- Prioritized — ranks fixes by expected traffic impact
- Reproducible — same article → same score
Architecture
┌─────────────────────────────────────────────────────────┐
│ Agent (Claude/Cursor) │
│ - Reads article file + target keyword │
│ - Calls audit script │
│ - Synthesizes fix list │
└───────────────┬─────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ skills/seo-content-quality-gate/ │
│ scripts/ │
│ ├── audit.py # Main auditor (all checks) │
│ ├── readability.py # Flesch, sentence stats │
│ ├── link_checker.py # Internal/external link scan │
│ ├── schema_validator.py # JSON-LD validation │
│ └── scorer.py # 0-100 scoring + report │
│ references/ │
│ ├── checklist-2026.md # 60+ checks explained │
│ ├── keyword-strategy.md │
│ └── schema-templates.md │
│ data/ │
│ └── stop_words.json # For keyword density │
└─────────────────────────────────────────────────────────┘
Quick start
# 1. Install
pip install beautifulsoup4 lxml
# 2. Audit a markdown article
python scripts/audit.py article.md --keyword "rf frontend design"
# 3. Audit HTML with full metadata
python scripts/audit.py article.html --keyword "seo audit" --format markdown > report.md
# 4. Score only
python scripts/scorer.py article.md --keyword "..."
Sample output (excerpt)
# SEO Content Quality Gate — Report
**Article**: article.md
**Target keyword**: "rf frontend design"
**Word count**: 2,847
**Score**: 78/100 (Good — publish after fixing 4 issues)
## Critical (must fix)
- ❌ H1 missing target keyword (impact: +18% organic traffic)
- ❌ Meta description missing entirely (impact: +12% CTR)
- ❌ No internal links in first 500 words (impact: +8% crawl depth)
## Important (should fix)
- ⚠️ Title tag is 68 chars (target 50-60) — will truncate in SERP
- ⚠️ Only 1 external link; add 2-3 to authority domains
- ⚠️ No schema.org markup (add Article + BreadcrumbList)
- ⚠️ 12 images without alt text
## Nice to have
- 💡 First paragraph is 89 words — break into 2
- 💡 4 sentences over 30 words — split for readability
- 💡 Add a FAQ section with 3-5 Q&A → FAQPage schema
## Expected post-fix score: 92/100
## Expected traffic lift: +30-45% over 90 days
The 60+ checks (categories)
Keyword optimization (8 checks)
- Title tag contains keyword, length 50-60
- H1 contains keyword (and matches title)
- H2s use semantic variations
- First 100 words mention keyword
- Keyword density 0.5-2.5% (not stuffed)
- LSI keywords present (top 3-5 from SERP)
- Keyword in URL slug
- Keyword in meta description
Structure (10 checks)
- Single H1, no skipped heading levels
- 3+ H2 sections
- Paragraphs < 150 words average
- Lists/tables for scannable content
- Table of contents for > 2000 words
- Conclusion/summary section
- FAQ section for informational queries
- Bullet points for features/steps
- Quote/callout blocks for emphasis
- Reading time / word count visible
Metadata (10 checks)
- Title tag 50-60 chars, unique
- Meta description 150-160 chars
- OG title, description, image, type
- Twitter card meta (summary_large_image)
- Canonical URL set
- Author markup
- Published / modified date
- Article schema JSON-LD
- BreadcrumbList schema
- OpenSearch / favicon
Links (8 checks)
- 2-5 internal links per 1000 words
- 1-3 external links to authority sites
- Nofollow on user-generated / paid links
- No broken anchor text (empty)
- Descriptive anchor text (not "click here")
- Deep links (not just homepage)
- No 404s (requires live crawl)
- Link to related content
Readability (10 checks)
- Flesch reading ease 60+ (8th grade level)
- Avg sentence length < 20 words
- No sentences > 30 words
- Passive voice < 10%
- Transition words every 3-4 sentences
- Subheadings every 300 words
- Active voice dominant
- Concrete nouns over abstract
- Concrete examples / numbers
- Conversational tone (contractions OK)
Media (8 checks)
- All images have alt text
- Alt text descriptive, not "image"
- Captions on key images
- File names descriptive (not IMG_1234)
- Compression / next-gen formats
- Width/height attrs set
- Lazy loading for below-fold
- WebP or AVIF format
Technical (8 checks)
- Mobile-friendly viewport meta
- HTTPS canonical
- Hreflang for multi-language
- Structured data validates
- No render-blocking JS in head
- No orphan pages (no internal links pointing in)
- URL is clean (no params, no session IDs)
- 404/410 handling for removed content
Pricing
Single-purchase, lifetime access. $7.00.
Includes:
- 5 Python audit scripts
- 60+ check reference (with thresholds)
- 3 reference docs (checklist, keyword strategy, schema templates)
- Stop-word list for density calc
- Future updates for the same major version
Example usage
"Here's a draft about 'RF frontend design for IoT'. Audit it for SEO."
The skill will:
- Read the markdown
- Run all 60+ checks
- Score the article 0-100
- List critical/important/nice-to-have fixes
- Estimate traffic lift per fix
- Output
report.mdyou can attach to your content calendar
Compatibility
Works with any agent that supports the SKILL.md standard and can execute Python: Claude Code, OpenClaw, Codex CLI, Cursor, Gemini CLI, Cline, Windsurf, Aider. Tested on Linux, macOS, Windows. Supports both Markdown and HTML input.
Tags
seo, content, audit, on-page, schema-org, readability, meta-tags, content-marketing, technical-seo
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
6 installs
Downloaded by developers to date
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 3 months ago
- Free to download with an account