Announcement Board

Announcement Board defines a small structure for distributing company news. The recommendation is to publish in one place, target the appropriate audience, and keep an expiry date so old announcements stop looking current. A clear owner and expiry policy help prevent clutter. Its suggested workflow runs from draft through approval and publication to reading or acknowledgement and expiry.

The skill first distinguishes an advice question, review, requested build, or conversion of an existing process. It answers advice directly and checks a shared process without automatically building a system. A build request produces artifacts after essential missing facts are resolved. By default, it recommends a workflow and offers the relevant template.

Questions cover audience, company-wide versus team or external readers, content and attachments, writers and approvals, scheduled posts, existing email or chat practices, and whether the desired result is a board, schedule, or archive. It asks one useful missing question at a time, skips facts already given, and leaves unknowns unknown.

Use it for an announcement board, company news feed, notice board, or internal-announcement process. The module belongs to the Engage layer and fits Starter stage. A request can be:

Company news goes out in chat and gets lost in a week.

It produces empty templates and does not send email or chat messages. Statuses such as Scheduled and Published are record fields, not an automatic publishing service. It provides no reminders, synchronization, or other automation, and does not calculate payroll, tax, leave balances, or KPIs.

The thirteen fields are Announcement Title, Acknowledged By, Ann ID, Author, Category, Department, Expiry Date, Priority, Publish Date, Status, Summary, Target Audience, and Views. Views is text rather than a computed counter; acknowledgement names are also a text field. Expiry and publication use date types, Summary uses long text, and the identifier is preserved when imported. No link fields are defined.

Category options start with Company, Department, Team, Location, and Role. Priority offers Low, Medium, High, and Urgent. Status offers Draft, Scheduled, Published, and Archived. These are starting sets that can be renamed to match the business.

Requested CSV, SQL DDL, JSON Schema, and Notion mapping derive from the same list. Display names remain consistent across CSV and JSON, with normalized SQL names documented. Excel-compatible CSV uses UTF-8 with a byte order mark; date columns still need formatting after import. A workbook is produced only if requested. Templates stay empty, and any requested example rows must be unmistakably synthetic.

Notion output goes to notion-manual-import for the CSV, property mapping, import steps, and verification checklist. A manual mapping requires no connection. Actual workspace writes need verified tool access, a confirmed target, and authorization; a mapping alone does not prove a live board exists.

Sensitive review material should be minimized, with qualified human review for privacy or disciplinary decisions and empty generated templates.