The Agent Skills Directory

[SAFE]: The skill provides standard documentation setup guides and configuration templates for widely used frameworks like Docusaurus. The instructions align with documented best practices for those tools.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx create-docusaurus and npm install to download and set up the documentation framework. These operations target the official npm registry, which is a well-known service.
[COMMAND_EXECUTION]: Provides standard shell commands for development workflows, including project initialization, dependency management, and site deployment (e.g., npm start, npm run build, npm run deploy).
[CREDENTIALS_UNSAFE]: The configuration templates for search functionality (Algolia) correctly use placeholders such as YOUR_APP_ID and YOUR_SEARCH_API_KEY rather than hardcoding actual credentials.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process Markdown files which could theoretically be used for indirect prompt injection, it does not include any specific exploitation patterns. The risk is consistent with standard agent interactions with project source files.
Ingestion points: Processes documentation files (.md) and configuration files (.js) in the project directory.
Boundary markers: Not explicitly defined in the provided templates.
Capability inventory: The skill allows for shell command execution via npm and npx for project maintenance.
Sanitization: No specific sanitization logic is implemented in the static templates.

documentation-site-setup