Install the MaxoPerf skill

The MaxoPerf skill is a small, shippable bundle that teaches a skill-aware AI agent (Claude Code, Claude Desktop, and compatible tools) how to use MaxoPerf: it wires up the MCP connector and gives the agent the workflow knowledge — how to pick a test type, where secrets go, what a healthy run looks like — that would otherwise take a long prompt to explain.

Install

1. Get a MaxoPerf API key first — see Get an API key. Keep it handy; the installer will ask for it.

2. Run the installer from a terminal where your agent (Claude Code, etc.) is available:

   npx @maxoperf/agent-skill install

3. Paste your API key when prompted. The installer stores it the same way you would in a manual MCP config — it is never printed back out or logged.

4. Restart or reload your agent so it picks up the new skill and MCP connector.

You can also start from the console: Settings → Connect AI tools (/settings/connect-ai-tools) shows the same install command with a copy button, plus links to this page.

Prefer manual MCP config?

The skill installer is the fast path. If you’d rather wire up the connector by hand, or your tool doesn’t support skills, see Connect AI tools for per-client MCP configuration.

First run

After installing, ask your agent something concrete — “create a load test against my staging checkout endpoint” or “show me the last run for project X.” The skill gives the agent enough context to:

• Pick an appropriate test type — see Choosing an executor for how it decides between API-style and browser-style engines.
• Avoid inlining credentials in generated test files — see Secrets and environments.
• Explain each MCP tool call in plain language before it runs anything destructive.

Safety

Same rule as manual MCP setup: an API key grants full-account access. Review your agent’s tool-call log before approving create/run/delete actions, especially the first few times. See Get an API key for the full guidance on scoping and rotating keys.

Uninstall or update

Re-run npx @maxoperf/agent-skill install at any time — it’s idempotent and updates the skill in place. To remove it, follow your agent’s normal skill-removal flow (for example, Claude Code’s /skills management) and revoke the API key from Settings → API keys if you no longer need it.

Where to go next

• Connect AI tools — the manual MCP setup this skill automates.
• Choosing an executor — what the agent picks between when it creates a test.
• Secrets and environments — how the agent should handle credentials in generated tests.