The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from workshop results (pasted text, exports, or transcriptions). It mitigates risk by instructing the agent to treat this input strictly as data and never as instructions, specifically identifying and reporting any attempts to command the agent within the input data.
[COMMAND_EXECUTION]: The documentation includes npx commands to install additional skills from the author's official package (pedroromeroluna/ai-first-product-skills). These are documented installation steps for the vendor's toolkit.

ideation-engine