Auditing seo
Skill lijinnair/claude-code-skillforge/examples/auditing-seo
Analyzes a single web page URL for SEO quality, identifying issues with title tags, meta descriptions, heading structure, and content. Use when the user says "audit this page", "check SEO for", or "analyze this URL for SEO". Outputs a structured audit report with prioritized fixes.From its SKILL.md
npx -y skills add lijinnair/claude-code-skillforge --skill auditing-seoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- fetches URLsInstructs the agent to fetch 1 URL, including $ARGUMENTS.
SKILL.md
1.7 KB, 317 tokens by cl100k_base, as published. Nobody here has run it
SEO Page Auditing SOP
Execution Steps
Step 1: Fetch Page Content
Use read_url_content to fetch and read the raw content of $ARGUMENTS (the URL provided by the user).
Step 2: Analyze On-Page SEO Elements
Check and score each of the following elements:
- Title Tag: Present? Under 60 characters? Contains primary keyword?
- Meta Description: Present? Under 160 characters? Has a call-to-action?
- H1: Exactly one H1 present? Does it match the topic of the title?
- Heading Hierarchy: Is H2 > H3 structure logical and sequential?
- Image Alt Text: Do all
<img>tags have descriptive alt attributes? - Internal Links: Are there at least 2 internal links present?
Step 3: Compile Prioritized Fix List
Organize the findings into 3 tiers:
- Critical: Issues that directly harm rankings (e.g., missing title, no H1).
- Important: Issues that limit performance (e.g., meta description too long).
- Suggestions: Nice-to-have improvements.
Step 4: Validate Completeness
Review the audit against the elements in Step 2. If any element was skipped or could not be assessed, note it explicitly. Re-check that every Critical item has a specific, actionable fix.
Step 5: Deliver the Report
Output the full audit as a formatted Markdown table with: Element | Status | Current Value | Recommended Fix.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most marketing audience skills give in 317 tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Said here and by no other author read
- score title tag presence and length
- score meta description presence and length
- check heading hierarchy is logical and sequential
- verify all image tags have alt text
- verify at least two internal links exist
- organize findings into critical, important, and suggestion tiers
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.