build-work-context

# Pharma Work Context Create a portable, renewable context layer that helps an AI understand how a pharmaceutical professional works before attempting the work itself. The context must remain useful across ordinary chats, project workspaces, and skill-aware agents. Favor clear source boundaries and honest unknowns over an impressive but fictional profile. ## First: establish the data boundary Before reading project sources or asking for detailed work content: 1. Identify the AI environment the user is using. 2. Ask whether that environment is approved for the proposed material. 3. Classify the intended inputs as: - `PUBLIC_OR_SYNTHETIC`; - `INTERNAL_APPROVED`; - `RESTRICTED_DO_NOT_PROCESS`; or - `UNKNOWN`. 4. If the classification is `UNKNOWN`, ask one concise boundary question. 5. If it is `RESTRICTED_DO_NOT_PROCESS`, stop before reading the material and offer an abstracted or synthetic route. Never request credentials, patient-level information, sponsor-confidential content, unpublished regulatory submissions, or proprietary material merely to make the context more complete. Read [`references/safety-and-evidence.md`](references/safety-and-evidence.md) for the full safety and evidence contract. ## Select the operating mode Infer the smallest mode that satisfies the request: - `CREATE` - no usable professional context exists. - `UPDATE` - an existing context exists and the user provides corrections or additions. - `PROJECT` - the user wants project-...