The Agent Skills Directory

[PROMPT_INJECTION]: The skill provides meta-instructions to define the agent's role (e.g., 'co-design implementer, not autonomous coder'). These are intentional behavioral constraints designed to improve safety and predictability, rather than attempts to bypass platform-level safety filters.- [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files or perform network requests. The skill is entirely focused on providing structured prompts for local development workflows.- [COMMAND_EXECUTION]: While the skill mentions validation commands like 'pytest' and 'python -m app' in its examples, these are provided as documentation for how a user might verify the agent's work and are not automatically executed.- [NO_CODE]: The skill consists exclusively of Markdown documentation and prompt templates. It does not include scripts, binaries, or external dependencies.

designer-design-card