The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were found. The skill operates purely as an instructional framework for the AI agent.
[NO_CODE]: The skill does not contain any scripts, dependencies, or command execution logic. All functionality is handled through natural language instructions and Markdown templates.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted user data for presentation planning.
Ingestion points: User-provided topic, audience, and objectives in SKILL.md (Step 1).
Boundary markers: Absent.
Capability inventory: The skill itself has no sensitive capabilities; it prepares data for handoff to keynote or pptx skills.
Sanitization: Absent.

presentation-designer