design-taste-frontend (taste-skill)
Anti-slop frontend skill: reads the brief, infers a design direction, and ships non-templated landing pages.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for design-taste-frontend (taste-skill), derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
An 'anti-slop' frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, applies real design systems when applicable, does an audit-first pass on redesigns, and runs a strict pre-flight check before shipping. Part of a repo of ~13 related design skills (brandkit, brutalist, minimalist, redesign, stitch, etc.). Surface: injects design instructions and generates/edits frontend code.
Key features and capabilities
- Brief-driven, contextual (nothing fires automatically)
- Audit-first redesign flow with pre-flight checklist
- Ships from a repo of sibling design skills
Use cases
- Design a non-generic landing page or portfolio
- Audit and redesign an existing site's frontend