The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and templates for product design and UX workflows. There are no executable scripts (.sh, .py, .js), binaries, or configuration files that grant the agent tool-based capabilities.- [DATA_EXPOSURE]: The skill includes strong privacy and security guardrails in SKILL.md and references/usability-testing-and-privacy.md, explicitly instructing the agent to use synthetic fixtures like sample-user@example.test and INV-DEMO-042 and forbidding the request of real credentials, payments, or secrets.- [EXTERNAL_DOWNLOADS]: The references/source-index.md file contains informational links to established standards and government organizations (ISO, W3C, GOV.UK, and USWDS). These are for documentation purposes and do not involve remote code execution or automated downloads during skill operation.- [PROMPT_INJECTION]: The instructions do not contain any patterns attempting to override agent safety filters or system prompts. The 'Entry Check' and 'Guardrails' sections reinforce structured, evidence-based behavior rather than open-ended autonomy.

product-design-and-ux