The Agent Skills Directory

[SAFE]: The skill performs legitimate prompt engineering tasks without any detected malicious behavior.
[EXTERNAL_DOWNLOADS]: The skill provides a link to the official Stitch documentation hosted by Google for user reference. This is a reference to a well-known service for documentation purposes.
[INDIRECT_PROMPT_INJECTION]: The skill includes an ingestion surface by reading user input and local DESIGN.md files to generate prompts.
Ingestion points: User-provided UI ideas and the content of the DESIGN.md file (referenced in SKILL.md).
Boundary markers: The output is structured using markdown headers and specific sections (e.g., 'DESIGN SYSTEM (REQUIRED)'), which helps organize content but does not act as a security delimiter.
Capability inventory: The skill is configured with Read and Write tools to interact with local files within the project context.
Sanitization: No specific sanitization or filtering of the input content is performed before interpolation into the final prompt.
[COMMAND_EXECUTION]: The skill uses the Write tool to save generated prompts to local files (e.g., next-prompt.md) upon user request, which is a standard functional capability for this utility.

enhance-prompt