The Agent Skills Directory

[SAFE]: The skill functions as a template-based assistant that generates project planning documentation. It does not contain executable code itself, but rather guides the AI agent in creating Markdown files for project architecture.
[COMMAND_EXECUTION]: The skill generates documentation containing shell commands for project initialization and deployment (e.g., npm create cloudflare, npx wrangler). These commands target official tools for Cloudflare, a well-known and trusted service provider, and are intended for user review and manual execution.
[CREDENTIALS_UNSAFE]: The ENV_VARIABLES.md template includes placeholders for various API keys (e.g., sk_test_... for Clerk). The skill explicitly warns against committing these files to version control and provides guidance on using production secrets management via the wrangler secret put command.
[INDIRECT_PROMPT_INJECTION]: The skill processes project requirements provided by the user to generate custom documentation. While this creates a data ingestion surface, the skill maintains safe operation by outputting structured text for user review and using clear boundary markers in its templates.

project-planning