Policy Library

Policy Library defines a company-policy register with an owner, version and review date. Missing policy drafts are written only for the policies the user names. This makes gaps visible when documents are scattered across folders and have no clear owner. The proposed lifecycle runs from policy draft to approval, publication of a version, assignment and a review date. These are stages in the recommended business process, rather than automatic publication actions by the skill.

The default deliverable is a short recommendation. An explicit setup, build or conversion request produces artifacts after essential missing facts are resolved. Advice receives a direct answer, while a review works from the material provided. This keeps the size of the proposed setup tied to the requested outcome.

Use it for a company-policy template, policy register, HR policy database or policy-document library. It does not provide legal templates or jurisdiction-specific wording. Payroll, tax, leave-balance and KPI calculations are outside its scope.

This is an empty-template workflow, not processing of real employee or customer records. Automation, reminders and synchronization require the separate integration layer. Sensitive decisions and adjustments require qualified human review before anything is acted on.

Intake establishes existing and missing policies, company-specific versus generic needs, approvers and owners, and whether legal review is required. It confirms effective dates, review cycles and version history, identifies which documents are current and where they live, and distinguishes a register from policy templates or a need for both. Questions are asked one at a time, excluding anything already answered in earlier messages. Unknown facts stay unknown. Intent, confirmed facts, open questions and requested formats remain internal unless the user asks to inspect them; no missing answer is invented.

The field model includes Policy Name (text); Acknowledgement Required (checkbox); Applies To (text); Approver (text); Category (select); Compliance Framework (text); Effective Date (date); Next Review (date); Policy ID (id); Policy Owner (text); Status (select); Summary (long_text); Version (text); Acknowledgements (number).

Category starts with HR, Finance, Security, Safety, Legal, Operations. Status starts with Draft, In Review, Published, Under Revision, Retired.

Requested CSV, SQL DDL, JSON Schema and Notion mappings derive from one field list. Display names remain identical across CSV and JSON, and normalized SQL identifiers are documented. Relation fields keep their relational meaning, dates remain dates and money remains currency. Machine-readable data is separated from explanation, with validation failures and limitations reported separately.

One supplied SQL example is:

CREATE INDEX idx_policy_library_status ON policy_library (status);

Excel-compatible CSV uses UTF-8 with a byte order mark. Because CSV has no column types, numeric, date and currency formatting is identified after the data. A CSV is not an .xlsx workbook; the latter is generated only when requested. Example rows require an explicit request and must be clearly synthetic. Sensitive identifiers are not unnecessarily repeated in a review, and generated templates remain empty.

Notion output goes to notion-manual-import for the CSV, property mapping, import steps and verification checklist. Manual mappings require no connection. Requested workspace changes require verified tool access, the actual target and authorization; a claimed connection is insufficient evidence. Notion relation columns resolve only after both databases have been imported. Select options are an initial vocabulary that can be renamed to match the business. people-directory supplies the related employee master record; notification-reminder-hub is the separate due-date reminder module. Personal identifiers and sensitive financial details stay out of generated templates.