content-optimization — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited content-optimization (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Guides on-page content optimization: word count, heading keywords, keyword density vs stuffing, multimedia, tables, and lists. Complements heading-structure (structure) and content-strategy (planning).
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for target keywords and content type.
Identify:
Google does not rank by word count. Length should match search intent and topic depth. A 1,000-word post that satisfies intent can outrank a 3,000-word thin piece.
For article word count by type (news, how-to, listicle, pillar, etc.), see article-content. Generic ranges:
| Content type | Word count | Notes |
|---|---|---|
| News / announcements | 300–600 | Time-sensitive; concise |
| Standard articles / how-tos | 1,000–1,500 | Single topic; actionable |
| Listicles / guides | 1,200–2,000 | "Top 10," "Best X" |
| Pillar / cornerstone | 2,000–3,500+ | Comprehensive; cluster hub |
| Practice | Purpose |
|---|---|
| Descriptive H2s | Search engines understand context; users scan |
| Answer-first | Place direct answer in first 40–50 words after H2 for Featured Snippets; see featured-snippet |
| Keyword variation | Use related terms; avoid repeating exact phrase in every H2 |
| Logical flow | H2s outline the article; support topical authority |
| Term | Meaning |
|---|---|
| Keyword density | (Keyword count / Total words) × 100; a metric, not a ranking factor |
| Keyword stuffing | Excessive, unnatural repetition to manipulate rankings; black-hat |
| Practice | Purpose |
|---|---|
| Alt, file names, captions | See image-optimization for full image SEO (alt, format, responsive, lazy loading, image sitemap, LCP, captions for Featured Snippets) |
| Original over stock | Unique images signal E-E-A-T — see eeat-signals |
Content placement: Put images near relevant text; captions support snippet thumbnails. See image-optimization for captions; featured-snippet for snippet context.
| Practice | Purpose |
|---|---|
| Embed + metadata | VideoObject schema, video sitemap, thumbnail; see video-optimization |
| YouTube | Google prioritizes YouTube in search; GEO citation; see youtube-seo, generative-engine-optimization |
| Featured Snippet (video) | Video schema; timestamps/chapters; see featured-snippet |
<table>, <thead>, <tbody>, clear column headers| Type | Use case | SEO / Snippet |
|---|---|---|
| Ordered (`<ol>`) | Steps, rankings, sequences, "Top 10" | List snippets (~19% of Featured Snippets); how-to; see featured-snippet |
| Unordered (`<ul>`) | Non-sequential items, features, options | Bullet snippets; definitions, options |
Best practices:
<ol> and <ul>; avoid divs styled as listsAnswer-first (direct answer in first 40–60 words after H2) supports both Featured Snippets and GEO. For article-level GEO (TL;DR, Key Takeaways, QAE pattern), see article-content and generative-engine-optimization. For Featured Snippet formats and optimization, see featured-snippet.
For article content audit (hook, QAE, product connection, CTA, references, gaps), see article-content. This skill covers generic content optimization (H2 keywords, multimedia, keyword density).
<ol> lists; HowTo vs FAQ~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.