The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill mentions installation commands using npx from a known repository (pedroromeroluna/ai-first-product-skills) and links to the author's official GitHub repository. These are documented as standard setup procedures for the toolset and do not involve untrusted third-party sources.
[COMMAND_EXECUTION]: The skill documents command-line examples for installing additional components (npx skills add ...). These are provided as user-facing documentation for setup rather than hidden or automated execution patterns.
[INDIRECT_PROMPT_INJECTION]: The skill defines a structured interview process (Socratic method) for processing user input. While it ingests external text, it implements strict formatting rules (e.g., specific hypothesis structures) and validation gates (Metric gate) that reduce the surface for accidental or malicious instruction following within the data pipeline.
[SAFE]: The skill references other local skills via relative paths (.claude/skills/...) to maintain modularity, which is a standard structural pattern for this platform.

product-strategy