Seo content optimizer
Analyzes and rewrites content to maximize search engine visibility without sounding robotic.From its SKILL.md
npx -y skills add Notysoty/openagentskills --skill seo-content-optimizerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 9 stars9 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.
SKILL.md
2.5 KB, 544 tokens by cl100k_base, as published. Nobody here has run it
SEO Content Optimizer
What this skill does
This skill forces the agent to analyze text through an SEO lens, checking for keyword density, LSI (Latent Semantic Indexing) keywords, header hierarchy, and readability. It then rewrites the content to improve its ranking potential while maintaining a natural, human tone.
How to use
Claude Code / Antigravity
Copy this file to .agents/skills/seo-content-optimizer/SKILL.md in your project.
Then ask the agent: "Optimize the blog post in content/my-post.md using the SEO Content Optimizer skill. Target keywords: [keyword1], [keyword2]."
Cursor
Save this to your project's .cursorrules or reference it during a chat session.
The Prompt / Instructions for the Agent
When asked to optimize content for SEO, follow these rules strictly:
- Header Hierarchy: Ensure there is exactly one H1. Ensure H2s and H3s are used logically to break up text. Incorporate secondary keywords naturally into H2s.
- Keyword Placement: Ensure the primary keyword appears in the H1, the first 100 words, and the conclusion. Do not keyword stuff (keep density below 2%).
- Readability: Aim for a 6th-8th grade reading level. Keep paragraphs short (3-4 sentences max). Use bullet points where appropriate.
- Formatting: Suggest a title tag (under 60 chars) and meta description (under 160 chars).
- Output Format: Provide the response in this exact format:
### SEO Metadata
- **Title Tag:** [50-60 chars]
- **Meta Description:** [150-160 chars]
### Optimization Notes
- [What you changed and why]
### Optimized Content
[The newly rewritten content]
Example
Input to Agent:
"Optimize this draft about 'JSON Formatter tools'. It feels a bit dry and I want it to rank better on Google."
Output from Agent:
SEO Metadata
- Title Tag: Best JSON Formatter Tools for Developers (2026 Free Guide)
- Meta Description: Format, validate, and beautify your JSON data instantly. Discover the top free JSON formatter tools that respect your privacy and run locally.
Optimization Notes
- Added "validate" and "beautify" as LSI keywords.
- Broke up the long paragraph into scannable bullet points.
Optimized Content
(...The rewritten content...)
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 544 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
- Use exactly one H1 header
- Incorporate secondary keywords into H2s
- Maintain a 6th-8th grade reading level
- Provide the response in the specified markdown format
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.