The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to facilitate its workflow.
Instructions in SKILL.md guide the agent to use git for update checks and cp/mkdir for file management.
The script scripts/validate-swiss-deck.mjs is executed via Node.js to ensure generated presentations adhere to design constraints.
[EXTERNAL_DOWNLOADS]: The skill relies on external sources for updates and runtime assets.
Updates are retrieved from the author's GitHub repository: https://github.com/op7418/guizang-ppt-skill.
Generated HTML decks reference reputable CDNs for static assets like fonts, icons (Lucide), and map components (MapLibre GL).
Animations utilize the Motion One library, with fallback support for jsDelivr CDN.
[SAFE]: No malicious patterns were identified during the audit.
Prompt instructions are focused on guiding the agent through a structured creative process without attempting behavior overrides.
No sensitive data paths or exfiltration methods were detected; shell usage is limited to the skill's operational scope.
Provenance and sponsorship information are clearly handled and not intended for output inclusion.

guizang-ppt-skill