The Agent Skills Directory

[SAFE]: This skill provides purely instructional guidance for design system maintenance and refactoring. It contains no malicious patterns, hardcoded credentials, or attempts to bypass safety guardrails. While it has an indirect prompt injection surface by analyzing project files (Ingestion points: files searched via grep; Boundary markers: None; Capability inventory: File read/write; Sanitization: None), the instructions are benign and focused on standard development tasks.
[NO_CODE]: There are no scripts, binaries, or external dependencies associated with this skill. It relies entirely on the agent's existing tools to perform its tasks.

extract