HAR Skills is designed from day one as an AI Agent Skill: the CLAUDE.md at the repository root is a progressive-disclosure document that an AI Agent reads to understand every capability and invoke it. This page explains how to onboard an LLM Agent (e.g. Claude Code) quickly.
$npx -y skills add cyberspacesec/har-skills --skill accessInstalls into the current project.
Run `npx skills use "https://github.com/cyberspacesec/har-skills" --skill "cyberspacesec/har-skills/access"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/cyberspacesec/har-skills" that are relevant to the current task. Run `npx skills add "https://github.com/cyberspacesec/har-skills"` and select the relevant skills, then follow their instructions.