The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were identified in the skill. The instructions focus on legitimate business modeling tasks.
[COMMAND_EXECUTION]: The skill mentions access to a 'Bash' tool for file management. However, its use is strictly scoped to creating the project structure in the './business/' directory. The skill also explicitly defines a 'Simulacion' mode that disables file-writing and execution tools for safe testing.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it processes data from previously generated project files and user input.
Ingestion points: Reads context from './business/01-problema-hipotesis/' and processes user-provided interview responses.
Boundary markers: Uses code blocks for deliverables and clear 'Puerta obligatoria' (mandatory gates) for user approval.
Capability inventory: Utilizes 'Write', 'Edit', and 'Bash' tools to create business documentation files.
Sanitization: Implements strict 'una pregunta a la vez' (one question at a time) logic and explicit validation checkpoints before advancing between phases.

solution-design