{"id":17122,"plugin_id":"plugins_6a57ac5ce65c8191ae7bd0a51160eb7d","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:13:57.447Z","digest":"4ba50cf765504419c566765e392fb11f3a3eec48edbf6356b6629b4465893633","against":null,"payload":{"description":"Use when Vera must create or resume a durable client engagement, import a source, journal, or support file, search one client's callable Gmail connector, inspect a capability-gated WhatsApp Desktop chat, or search connected studio documents without mixing clients.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":346},{"relative_path":"references/marketplace-gmail.md","size_in_bytes":5764},{"relative_path":"references/whatsapp-desktop.md","size_in_bytes":8018}],"name":"studio-archive","skill_md_contents":"---\nname: studio-archive\ndescription: Use when Vera must create or resume a durable client engagement, import a source, journal, or support file, search one client's callable Gmail connector, inspect a capability-gated WhatsApp Desktop chat, or search connected studio documents without mixing clients.\n---\n\n<!-- VERA_OPENAI_ONBOARDING_BEGIN -->\nOnboarding is optional. Continue ordinary professional work immediately,\nincluding direct specialist invocation, without checking or completing a local\nonboarding profile. Missing, unfinished, inaccessible or corrupt onboarding state,\nor unavailable voice/window controls, must never block ordinary work. Do not\nautomatically start, resume or repeatedly offer onboarding.\nOnly for a user-requested tutorial or a native teaching handoff, read\n`../vera/references/local-onboarding.md`. A verified paired lesson worker\nexecutes only its bound lesson and token; never bypass tutorial validation.\nTutorial profiles, progress, examples and feedback remain local; never send a\nchange request, stamp a tutorial receipt or call hosted interviews for a tutorial.\nCurrent user requests take precedence over saved preferences.\n<!-- VERA_OPENAI_ONBOARDING_END -->\n\n## Surface routing\n\nIn ChatGPT, continue with connected Gmail when its read tools are callable and\nwith material supplied in the conversation. WhatsApp Desktop control and local\narchive indexing remain Codex Desktop capabilities. For those local routes,\ncomplete any useful preparation or review available in chat, recommend Codex\nusing the localized wording in `../vera/SKILL.md`, and continue in ChatGPT.\n\n# Archivio dello Studio\n\nFor a Geneva (CH-GE) mandate, read `../vera/references/localization/geneva.md` first and use this existing function’s Geneva adaptation in its resolved component skill. Language alone never selects jurisdiction.\n\n\nAfter substantive use of this workflow, read and follow the `Plugin Improvement Feedback` section in `../vera/SKILL.md`.\n\nFor the local client-work route, the customer folder is the portable source of\ntruth. Client selection, engagement creation, immutable import, exact run\npreparation, start, bound execution, artifact finalization, review/completion,\nrecovery, rename handling, and retention must remain separate explicit steps.\nThe machine-local index and configuration are rebuildable aids, not the run\nledger.\n\nChoose the route before resolving any module:\n\n1. When the user asks to inspect WhatsApp messages, confirm that Computer Use\n   can control the local WhatsApp Desktop application on the same computer.\n   - If it is available, read `references/whatsapp-desktop.md` completely and\n     follow it. Do not resolve the local document module as a workflow or call\n     its MCP. Resolve only the bundled Studio Archive\n     `scripts/whatsapp_desktop_guard.mjs` named by that reference; do not call a\n     WhatsApp MCP server, use a browser, or run any other WhatsApp script.\n   - If it is unavailable, explain that message inspection requires Codex\n     Desktop, Computer Use, and the user's already-authenticated WhatsApp\n     Desktop application. Complete any useful scope or question preparation in\n     chat, use the localized Codex recommendation in `../vera/SKILL.md`, and\n     continue the conversation. Do not fall back to WhatsApp Web, a Mparanza\n     server, exported chats, or an unofficial API.\n2. When the user asks to search Gmail or email, check whether Gmail\n   `get_profile`, `search_emails`, and `batch_read_email` are callable.\n   - If they are callable, read `references/marketplace-gmail.md` completely and\n     follow it. Do not resolve the local module, call Studio Archive MCP tools,\n     or run local scripts.\n   - If they are unavailable, say that the separately distributed OpenAI Gmail\n     connector must be installed, enabled, and connected on the current\n     surface. Do not use IMAP, browser scraping, or ask the user to save `.eml`\n     files.\n3. When the user asks to identify or create a client workspace, import or\n   resume a source, journal, or support engagement, or configure, refresh, or\n   search local studio documents, resolve `../../modules/studio-archive` from\n   this skill directory when it exists; otherwise resolve\n   `../../../studio-archive` in the repository. Read that module's\n   `skills/studio-archive/SKILL.md` completely and follow it. Treat the resolved\n   module root as the plugin working directory for local commands, scripts,\n   requirement files, MCP tools, and archive state.\n   When `list_studio_archive_clients` reports `configured: false` and\n   `setup_required: true`, tell the user that Vera will open the operating\n   system's folder chooser and call `setup_studio_archive` before asking for an\n   absolute path. Request a path manually only when that guided action returns\n   `archive_folder_picker_unavailable`; cancellation means no configuration was\n   written and should lead to an offer to reopen the chooser.\n\nThe Gmail, WhatsApp Desktop, and local document routes are independent. Gmail\nuses OpenAI's separately connected connector in ChatGPT or Codex. WhatsApp is\nan on-demand view of the local application through Computer Use. There is no\nVera or Mparanza WhatsApp webhook, background sync, hosted connector, message\ndatabase, or retention period. WhatsApp content read for the task may still\nenter the model context of the user's selected Codex or ChatGPT account.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}