Skip to main content
Cursor has native support for the AgentSkills standard. Skills installed via npx skills add are automatically discovered by Cursor Agent — no manual configuration needed.

How it works in Cursor

Cursor Agent loads skills from these directories and presents them as available capabilities: When a skill is installed, Agent reads its SKILL.md file and automatically decides when to apply it based on what you ask. You can also invoke any skill explicitly by typing /skill-name in the Agent chat. Skills are visible in Cursor Settings → Rules → Agent Decides.

Install the skills

The scripts in these skills are Node.js CLI tools that run in your terminal, not inside Cursor’s chat UI. Cursor Agent reads the skill instructions and executes scripts using its terminal tool when needed.

Set up environment variables

The scripts need two variables before Agent can use them:
Add these to your shell profile (~/.zshrc or ~/.bashrc) so they’re always available when Cursor’s terminal runs scripts. Alternatively, add a .env file to your project — Cursor Agent can read it if you reference it in your prompt.
Never commit NOTIFYER_API_TOKEN to Git. The .gitignore in the agent-skills repo already excludes .env and .env.* files.
For full environment variable reference, see Auth & environment.

Verify discovery

After installing, confirm Cursor can see the skills:
  1. Open Cursor SettingsRules
  2. Look for setup-notifyer, automate-notifyer, and chat-notifyer in the Agent Decides section
Or run in Cursor Agent chat:
Agent will display the skill instructions and confirm it’s loaded.

Example Agent prompts

Once installed, use natural language in Cursor Agent chat. Agent will identify the relevant skill and execute the appropriate scripts.

Workspace setup

Template management

Live chat operations

Broadcast campaigns


Manually invoking a skill

If Agent doesn’t pick up a skill automatically, invoke it with the / command:

How Agent runs the scripts

When you give Agent a task, it:
  1. Reads the relevant SKILL.md to understand available scripts and their flags
  2. Opens a terminal in the skill’s directory (skills/setup-notifyer/, etc.)
  3. Runs the script with the correct flags
  4. Parses the JSON output (ok/err structure) and summarises the result
All scripts output structured JSON, which Agent can read and act on — for example, it can check if isConnected: false and automatically suggest running refresh-connection.js.

Keeping skills up to date