The Agent Skills Directory

[SAFE]: The skill provides instructional material, templates, and reference documentation to assist developers in using the Unistyles library. All code patterns follow standard React Native development practices.
[PROMPT_INJECTION]: The skill operates on the user's codebase, which presents a surface for indirect prompt injection if the processed files contain malicious instructions. However, this is an inherent characteristic of coding assistant tools and not a specific vulnerability introduced by this skill.
Ingestion points: Reads source code and project configuration files via Read, Grep, and Glob tools.
Capability inventory: The agent has the ability to modify project files (Write, Edit) and execute shell commands via Bash (restricted to npx commands).
Boundary markers: The skill does not define specific delimiters or "ignore" instructions for processing user-supplied code content.
Sanitization: No specific sanitization or validation of the ingested code content is performed.

react-native-unistyles-conventions