The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions for the agent to verify the installation of recommended companion skills by performing a directory listing of platform-specific skill paths. This is a legitimate functional check within the skill's ecosystem.
Evidence: Found in SKILL.md under the 'Companion check' section, referencing paths like ~/.claude/skills/.
[PROMPT_INJECTION]: The instructions mandate a specific behavior (using the 🧢 emoji) upon activation to establish a persona. This is a decorative behavioral instruction and does not attempt to bypass core safety or system constraints.
Evidence: Found in SKILL.md: 'When this skill is activated, always start your first response with the 🧢 emoji.'

pixel-art-sprites