The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the AI agent to execute shell commands using pnpm and npx. These include project initialization (pnpm project-setup), development server management (pnpm dev), site compilation (pnpm build), and port management (npx kill-port 1313 -y). These are standard operations within a Node.js and Hugo development environment.
[EXTERNAL_DOWNLOADS]: The skill references and facilitates the use of external Hugo Modules hosted at github.com/gethugothemes/hugo-modules. These modules provide common website functionalities like SEO, search, and PWA support. The skill instructs using pnpm update-modules to fetch these dependencies via Hugo's native module system.
[PROMPT_INJECTION]: As the skill is designed to manage and interpret local project files (markdown and configuration), it possesses an attack surface for indirect prompt injection from untrusted content.
Ingestion points: The agent reads and processes markdown files in the content/ directory and TOML/JSON configuration files.
Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for processing these files.
Capability inventory: The agent has the ability to execute shell commands (pnpm, npx) as part of its primary function.
Sanitization: No explicit sanitization or validation of file content is described before the agent acts upon the information. This risk is inherent to development assistants that interpret project data.

hugo-template-guidance