The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: Ingestion points: The skill instructs the agent to read various CLAUDE.md files located in the app/Filament/ and tests/Feature/ directories to resolve project context. Boundary markers: No delimiters or explicit instructions to ignore embedded commands are provided. Capability inventory: The skill assists in generating and reviewing Filament dashboard code, widgets, and navigation logic. Sanitization: No sanitization or validation is applied to the content of these documentation files. These files represent an ingestion surface where local content could theoretically influence agent behavior, though they are standard local project files intended for this purpose.

filament-dashboard