Claude Skills: Extended Prompts for Your Agentic AI Workflows

Claude Skills is a relatively new feature available in Anthropic LLM clients that allows you to write the extended prompts with code blocks to perform specific tasks or follow a certain logic. The models automatically select which skills to use depending on the context of the conversation.

We developed a free collection of skills that have access to InfraNodus MCP tools to perform insight generation, SEO analysis, content optimization workflows using our methodologies, tools, and real-time data imports.

You can also use Claude skills in other applications such as ChatGPT, Cursor, or OpenClaw also. The setup is slightly different from Claude, but we provide the installation instructions below for each LLM client / agent.

Get Started

1

Create an Account

Sign up for a free InfraNodus account to get access to the knowledge graph tools and your API key.

Create a Free Account

2

Get InfraNodus MCP

https://mcp.infranodus.com

Add this URL as a connector via Settings > Connectors in Claude Web / Desktop and authenticate with your InfraNodus API key via OAuth.

https://mcp.infranodus.com

Open the ChatGPT Apps page > Advanced Settings > enable Developer Mode > Create App, paste this URL (leave the OAuth fields empty), click Connect, and authenticate with your InfraNodus API key. Full guide: ChatGPT setup.

claude mcp add infranodus -s user --transport http https://mcp.infranodus.com/mcp

Then open Claude Code in terminal, run /mcp and pick "Authenticate" — it opens the browser OAuth flow where you will need to put in your InfraNodus API key to connect to the MCP server.

{
  "mcpServers": {
    "infranodus": {
      "url": "https://mcp.infranodus.com"
    }
  }
}

Add this to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project) — or use Cursor Settings > MCP > New MCP Server. Then click "Login" next to the server to authenticate with your InfraNodus API key.

codex mcp add infranodus --url https://mcp.infranodus.com
codex mcp login infranodus

Run these commands in your terminal — the login command opens the browser OAuth flow where you enter your InfraNodus API key. (You can also add the server to ~/.codex/config.toml manually.)

{
  "mcpServers": {
    "infranodus": {
      "command": "npx",
      "args": ["-y", "infranodus-mcp-server"],
      "env": {
        "INFRANODUS_API_KEY": "your-api-key"
      }
    }
  }
}

Add this to your LLM client's MCP configuration file, replacing your-api-key with your InfraNodus API key. See our deployment guides for client-specific instructions (n8n, Make.com, local setup, and more).

3

Install the Skills

/plugin marketplace add infranodus/skills
/plugin install infranodus-all@infranodus-skills

Run these two commands in the Claude Code prompt to install all the skills as a plugin. Or use npx in your terminal:

npx skills add infranodus/skills -g -a claude-code -y

To install only one specific skill, add its name — e.g. --skill infranodus — to the command above.

npx skills add infranodus/skills -g

When prompted, select the agents where you want to add the skills — e.g. claude-code, codex, or cursor. To install only one specific skill, add its name — e.g. --skill infranodus — to the command above.

This installs our free skills collection into your Claude Code client. For other LLM clients, choose "All Other Agents". For manual installation, see the full installation instructions below.

Didn't work? You can simply download the skills from our GitHub repository and add them to your LLM client manually — see the step-by-step instructions below.

Learn More about the InfraNodus Claude Skills:

How Skills Work

How Claude skills augment AI with custom logics, methodologies, and workflows.

Skills Collection

The full collection of InfraNodus skills with use cases and examples.

FAQ

Troubleshooting, skills vs MCP, skills vs Custom GPTs, and best practices.

Improve Skills with InfraNodus MCP

Use the InfraNodus MCP Server to find gaps and improve your skills.

Explore the InfraNodus Claude Skills:

InfraNodus Skill

The main skill: knowledge graphs, content gaps, GraphRAG, and repo & vault graphing for AI agents.

SEO Claude Skill

Step-by-step SEO methodology: search intent, content gaps, and optimization.

Knowledge Graph Skill

Turn your Obsidian vault or AI second brain into a queryable knowledge graph with grounded responses.

Cognitive Variability Skill

Adaptive thinking across scale and intent to evolve ideas and avoid getting stuck.

CLI Skill for OpenClaw / AI Agents

Full tool catalog and setup for using InfraNodus MCP tools via MCPorter in OpenClaw.

LLM Wiki Skill

Build a personal, LLM-maintained knowledge base from your source documents with InfraNodus gap analysis.

Ontology Creator Skill

Generate ontologies and knowledge graphs with [[wikilinks]] and semantic relations from any topic or text.

How to Install the Skills to Your LLM Client

Claude skills will work with any LLM client, but Claude has a more automatic support for them. There are two ways to install our skills collection: the quick npx command that works for most LLM clients and agents, or a manual download from our GitHub repository if you want to pick individual skills or your client requires a different setup.

1

Install via npx (Recommended)

npx is a package runner that comes bundled with Node.js — a very useful tool that lets you run open-source applications directly from your terminal without installing them permanently. If you don't have it yet, install Node.js first and npx will be available automatically.

Then run this command in your terminal:

/plugin marketplace add infranodus/skills
/plugin install infranodus-all@infranodus-skills

Run these two commands in the Claude Code prompt to install all the skills as a plugin. Or use npx in your terminal:

npx skills add infranodus/skills -g -a claude-code -y

To install only one specific skill, add its name — e.g. --skill infranodus — to the command above.

npx skills add infranodus/skills -g

When prompted, select the agents where you want to add the skills — e.g. claude-code, codex, or cursor. To install only one specific skill, add its name — e.g. --skill infranodus — to the command above.

It will fetch the latest version of our skills collection and install it into your Claude Code client. For other LLM clients, choose "All Other Agents".

2

Or Download the Skills Manually

Alternatively, you can download each skill as a .zip file from the releases page of our GitHub repository:

https://github.com/infranodus/skills/releases

and then follow the instructions below for your particular LLM client.

Installing Skills to Claude Web / Desktop

To install the Claude Skills to Claude Web / Desktop client, you need to:
1) go to the Settings > Capabilities (or Menu > Customize in newer UI),
2) activate the "Code execution and file creation"
3) scroll down to the "Skills" section and activate some of the default skills you find useful
4) you can also download the InfraNodus skills collection and upload each individual skill (.zip or .skill file) by clicking "Upload Skill" or clicking the + button

Installing Skills to Claude Code

In this case, you will need to manually move each skill's folder (e.g. `skill-cognitive-variability`) to the `~/.claude/skills` directory in your home directory. In this case, the skills will be available for all your projects.

If you want the skill to be available in a specific project, you need to create the `.claude/skills` folder in that project and copy the skills folders there.

Installing Skills to ChatGPT

ChatGPT doesn't have an automatic skill installation procedure. However, there are two ways you can install them manually:

1) You can create a Custom GPT and add the instructions from the SKILL.md file there. Then save the Custom GPT with a descriptive name you choose and start a new conversation with it or mention it in an existing one using the @ sign.

2) You can create a new project and paste the SKILL.md file (and additional files from the skill folder) into the system prompt of this project.

Installing Skills to OpenClaw

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

Install via OpenClaw Chat (recommended)

Run the following command in the OpenClaw chat (replace the version number v1.4.0 with the latest one):

install this skill: https://github.com/infranodus/skills/releases/download/v1.4.4/infranodus.zip

Manual Installation

Download the infranodus.zip from the InfraNodus skills repository.

To make the skill available globally:

cp infranodus.zip ~/.openclaw/skills/infranodus.zip
unzip ~/.openclaw/skills/infranodus.zip -d ~/.openclaw/skills/infranodus

To make the skill available in 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.

Installing Skills to Other LLM Clients

To install the skills to any other LLM client, you can upload it to the Project's instructions / specific chat where you want to use them or create a Custom GPT in ChatGPT to use that skill (using the content of the SKILL.md file). Then you can invoke the still in that particular project / chat, or if it's a custom GPT, you can invoke it with the @skill_name mention.

3

Optional, but Recommended: Get an InfraNodus API Key

Some of the skills above can access the InfraNodus MCP Server to perform more complex tasks and extract real-time data from external sources (e.g. search intent or search results). While the MCP server provides free access for the first few iterations, you'll need to get an InfraNodus API key to use it for more advanced tasks and workflows and to avoid hitting the rate limits.

Sign Up for InfraNodus

What's Next

Skills Collection (GitHub) InfraNodus MCP Server

Claude Skills

Overview

Skill Use Cases

Reference