The Agent Skills Directory

[SAFE]: The skill provides legitimate design guidance, UI components, and research workflows related to ADHD accessibility. The analysis of instructions and reference materials confirms the content is educational and functional for its stated purpose.
[PROMPT_INJECTION]: The skill includes instructions to ingest external research data, which presents an attack surface for indirect prompt injection.
Ingestion points: External websites and research documents retrieved via the mcp__firecrawl__firecrawl_search and WebFetch tools.
Boundary markers: None identified; instructions do not explicitly mandate delimiters or instructions to ignore embedded commands in fetched data.
Capability inventory: The agent can perform file system modifications via Write and Edit, and generate code using mcp__magic__21st_magic_component_builder.
Sanitization: There are no explicit filtering or validation steps described for external research content.

adhd-design-expert