The Agent Skills Directory

[SAFE]: The skill is a documentation-based code reviewer that guides the agent to perform audits on local source files using standard tools like grep and npm. It does not perform network operations, exfiltrate data, or attempt to access sensitive system configurations.
[COMMAND_EXECUTION]: The skill suggests the use of standard development commands, including npm run lint, npm run typecheck, and various grep patterns to identify specific Mantine anti-patterns. These commands are executed locally within the project context and are appropriate for the skill's stated purpose.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted source code provided in the project repository.
Ingestion points: The skill reads content from .tsx, .ts, and .css files using grep (found in SKILL.md and CHECKLIST.md).
Boundary markers: No specific boundary markers or 'ignore' instructions are defined for the analyzed file content.
Capability inventory: The skill relies on pattern matching via grep and standard project scripts via npm, which do not interpret the input code as instructions for the agent itself.
Sanitization: No sanitization is performed on the code content prior to analysis.

mantine-reviewing