The Agent Skills Directory

Command Execution (SAFE): The utility scripts analyze_onboarding_metrics.py and generate_tour_config.js are used for processing local data and generating configuration files. They do not invoke shell commands, spawn dangerous subprocesses, or execute arbitrary code.- External Downloads (SAFE): The skill references industry-standard frontend libraries including react-joyride, driver.js, and intro.js. These are reputable open-source projects used for UI walkthroughs and do not pose a security risk.- Data Exposure (SAFE): State management for onboarding (e.g., tracking if a tour was completed) is handled via localStorage, which is a safe and standard method for persisting non-sensitive user preferences in a browser environment.- Prompt Injection (SAFE): The skill's instructions and documentation focus entirely on technical implementation and do not contain any patterns designed to override AI safety filters or hijack agent behavior.

guiding-users