Menú
Synthetic second-device skill fixture; proves device homes inventory independently
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | Demo Skill On Device B |
| description | Synthetic second-device skill fixture; proves device homes inventory independently |
Device B skill body. Distinct from device A.
Use when a coding agent needs PDPP data (the user's email, finance, coding history, or other personal data exposed by a PDPP server) to answer a task. The skill teaches discovery-first capability lookup, scoped grant requests, project-local token caching, and grant-safe data consumption. Use this instead of asking the user for an owner bearer token, instead of guessing endpoints, and instead of broad unbounded scans.
Use ONLY when you are a trusted local owner agent that the operator has explicitly authorized to act as themselves against their own PDPP reference instance — for example a local assistant such as Daisy running on the owner's machine. This profile uses an owner-level REST/control-plane credential obtained through browser-mediated owner approval, and teaches token-efficient initial and incremental sync of all current and future owner data. This is owner-level local automation, not the default agent path. Routine third-party, coding-agent, and task-scoped assistants MUST use the grant-scoped pdpp-data-access skill instead.
Use this skill to generate well-branded interfaces and assets for PDPP (the Personal Data Portability Protocol), either for production or throwaway prototypes/mocks. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
Synthetic skill fixture for source-inventory tests
Synthetic Codex skill fixture for source-inventory tests
Use when a coding agent needs PDPP data (the user's email, finance, coding history, or other personal data exposed by a PDPP server) to answer a task. The skill teaches discovery-first capability lookup, scoped grant requests, project-local token caching, and grant-safe data consumption. Use this instead of asking the user for an owner bearer token, instead of guessing endpoints, and instead of broad unbounded scans.
