KeywordGraph SEO Analysis Skill

A Claude skill for advanced SEO and content optimization based on the KeywordGraph text network analysis methodology. Use it as an extended prompt in Claude Web or in your favorite LLM client to perform keyword research, content gap analysis, and search intent analysis grounded in real Google data.

The skill is integrated with the KeywordGraph MCP Server, so it can pull real-time search supply and demand data, detect structural content gaps, and produce full SEO audits directly inside your workflow.

What It Does

The SEO Analysis skill performs comprehensive SEO analysis using a knowledge graph methodology to identify keyword opportunities, content gaps, and optimization strategies. It is suitable for both classic SEO and LLMO (optimization for AI/LLM search), and works in two modes:

• Topic Analysis — Given a topic, it maps the informational supply (what existing content covers) against the search demand (what people actually search for), then surfaces the supply–demand gaps where you can build topical authority and rank with unique content.

• Content Analysis — Given a document or website URL, it runs a full SEO audit: current keyword coverage, missing high-value keywords, content gap opportunities, and prioritized, actionable recommendations — including HTML structure, metadata, and header-hierarchy suggestions for structural semantic optimization.

It uses the KeywordGraph MCP server search intent and search results import functionalities for real Google data access, and falls back to web search when MCP tools are unavailable.

Installation

The skill works with any LLM client. Download it from the GitHub releases page and follow the instructions for your client below.

Step 1: Download the Skill

Option A — From Releases (Recommended)

1. Go to the Releases page
2. Download the .zip or .skill file for the SEO Analysis skill

Option B — Clone the Repository

1. Clone this repository or download the skill-seo-analysis folder
2. The folder contains all necessary files for the skill
3. Create a .zip of the folder contents if your client requires it

Step 2 (Optional): Get a KeywordGraph API Key

The skill can access the KeywordGraph MCP Server to perform more complex tasks and extract real-time data from external sources (e.g. search intent or search results). The MCP server provides free access for the first few iterations, but you'll need to get a KeywordGraph API key for more advanced workflows and to avoid hitting rate limits.

Step 3: Install to Your LLM Client

Claude Web / Desktop

1. Go to Settings → Capabilities
2. Activate "Code execution and file creation"
3. Scroll down to the Skills section and activate any default skills you find useful
4. Click "Upload Skill" to add the KeywordGraph SEO Analysis skill (.zip or .skill file downloaded in Step 1)

Claude Code

Copy the skill-seo-analysis folder to the ~/.claude/skills directory to make it available globally across all projects.

To scope the skill to a specific project, create a .claude/skills folder inside that project and copy the skill folder there instead.

Cursor / Windsurf / Other Code Editors

Copy the skill folder to your project's skills directory (e.g. .cursor/skills/ for Cursor) or to a global skills directory defined in the editor settings. The skill's SKILL.md file will be picked up automatically.

ChatGPT

ChatGPT doesn't support automatic skill installation, but you can use either of these approaches:

1. Custom GPT — Create a new Custom GPT and paste the contents of the skill's SKILL.md into the instructions. Save with a descriptive name. You can then start a new conversation with it or mention it in an existing chat using the @ sign.

2. Project prompt — Create a new project and paste the SKILL.md file (plus any additional reference files from the skill folder) into the project's system prompt. The skill will be active in every conversation within that project.

OpenClaw

OpenClaw is a local autonomous AI agent that uses skills and MCP servers via MCPorter.

Install via OpenClaw chat (recommended):

install this skill: https://github.com/noduslabs/claude-seo-skill/releases/download/v1.0.8/skill-seo-analysis.zip

Replace v1.0.8 with the latest release version.

Manual installation:

cp skill-seo-analysis.zip ~/.openclaw/skills/skill-seo-analysis.zip
unzip ~/.openclaw/skills/skill-seo-analysis.zip -d ~/.openclaw/skills/skill-seo-analysis

To scope the skill to a specific project, copy it to that project's skills folder instead.

Note: OpenClaw also needs MCPorter installed to access MCP server tools. See the full OpenClaw deployment guide for setting up MCPorter with OAuth or API key authentication.

Other LLM Clients

For any client not listed above, paste the contents of the skill's SKILL.md file into the project instructions or system prompt of the conversation where you want to use it. If the client supports custom assistants or GPTs, you can create one using the SKILL.md content and invoke it with an @ mention.

Using the Skill

Your LLM client will automatically infer when to use the skill from its description. However, you can also explicitly ask it to perform an SEO analysis, keyword research, content gap analysis, or search intent analysis.

If you find the skill is not activated as often as you'd like (or is activated too frequently), you can modify the description in SKILL.md and upload it again to your LLM client.

MCP Tool Reference

The skill works best with the following KeywordGraph MCP server tools. If they are unavailable, the skill falls back to web search and notes the limitations.

Tool	Purpose	When to Use
analyze_google_search_results	Map informational supply	Topic analysis Step 1
analyze_related_search_queries	Map search demand	Topic analysis Step 2
search_queries_vs_search_results	Find supply-demand gaps	Topic analysis Step 3
generate_seo_report	Full content SEO audit	Content analysis

Developing the Skill

1. Download or fork the repository

2. Use Claude Web or Desktop to develop the skill (they include the "skills_creator" skill)

3. To augment the skill, open the repo in Claude Code or Cursor AI and use KeywordGraph MCP to find content gaps or develop the content of the skill. It will use KeywordGraph's tools automatically to improve the structure and the content of the skill for you.

4. Ready to launch? If you tag a new version, pushing the commit to your repo triggers a GitHub action that generates a release with the .zip file you can use to add the skill to Claude Web and Desktop.

a. Create a new tag (e.g., v1.0.0, v1.0.1, v2.0.0)

git tag v1.0.0

b. Push the tag to GitHub

git push origin v1.0.0