The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for frontend architecture, implementation-ready guidance, and accessibility standards (WCAG 2.2). The instructions emphasize preserving project-specific conventions and avoiding disruptive changes.
[EXTERNAL_DOWNLOADS]: The skill contains references to documentation and specifications from well-known technology organizations and standards bodies, including the W3C (w3.org), Mozilla Developer Network (developer.mozilla.org), and the European Commission. These links are used for verifying technical and legal claims (e.g., CSS nesting, EAA compliance) and do not involve executable code downloads.
[COMMAND_EXECUTION]: The skill mentions the use of 'repository-native validation commands' for tasks like checking token contrast or accessibility audits. However, it explicitly instructs the agent only to run commands already provided by the repository's configuration and cautions against prescribing new dependencies or external audit targets.
[PROMPT_INJECTION]: The skill defines a process for ingesting project-local data which represents a theoretical surface for indirect prompt injection.
Ingestion points: Local design documentation files (e.g., Design.md, design.md) as described in SKILL.md and technical-reference.md.
Boundary markers: No specific delimiters or boundary markers are defined for the content of these files.
Capability inventory: The skill is restricted to generating text-based recommendations and documentation; it possesses no capabilities for file-writing, network exfiltration, or arbitrary command execution.
Sanitization: No specific sanitization or filtering is performed on the content ingested from the design files.

frontend-designer