policy-library – skill Lập trình cho agent AI

Policy Library

What it is: Company policies.

Overview

Works out the smallest useful Policy Library setup for the business in front of it, then

builds it only when asked. The default output is a short recommendation, not a

spreadsheet. Artifacts - CSV, SQL DDL, JSON Schema, Notion mapping - are produced on

request, from one field list so they cannot drift apart.

Layer: Layer 1: Foundation. Fits: Starter stage. Table code: n/a.

When to Use This Skill

• company policy template
• policy register
• hr policy database
• policy document library

Also use it when the user says "company policies", or describes the same process happening in a

spreadsheet, a document or someone inboxes.

Do not use it for: payroll calculation, tax filing, or legal advice. This skill produces

empty templates only - it never holds or processes real employee or customer data.

How It Works

Follow the shared execution contract. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.

Step 1 - Identify intent

Read the request and pick the intent before asking anything.

• "set up" or "build" or "create" -> the user wants artifacts; go to Step 2.
• "our process is ..." or "it is in a sheet" -> the user wants to move an existing process; capture it, then Step 2.
• "is this right" or "review" or "audit" -> the user wants a check, not a build; answer from what they share.
• "how do I ..." -> advice question; answer directly and offer the build only if it helps.

Ask only if this is the highest-value missing fact; otherwise proceed without an opener:

> Q: Which policies exist today?

Step 2 - Ask only what is missing

Skip anything the user already answered, in any earlier message. Ask the rest one at a

time, and stop as soon as the remaining answers would not change the output.

• Policies - Which policies exist? / Which are missing? / Company specific or generic?
• Ownership - Who approves each? / Who owns each? / Legal review needed?
• Lifecycle - Effective dates? / Review cycle? / Version history kept?
• Current process - Where do policies live now? / Shared drive or scattered? / Which are current?
• Outcome - What do you need? / A register, templates or both?

Never invent an answer. If the user does not know, record it as unknown and carry on.

Step 3 - Hold the internal context

Hold the answers in this shape. It stays internal - it is not shown to the user unless

they ask, and it never carries a value the user did not give.

module: policy-library
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Policies": null
  "Ownership": null
  "Lifecycle": null
  "Current process": null
  "Outcome": null
requested_outputs: []   # csv | sql | json | notion | xlsx - requested formats only
confirmed_facts: []     # only what the user actually said
open_questions: []      # the unanswered ones, in the order worth asking

Step 4 - Recommend the smallest workflow

If an artifact was requested, build it after resolving essential missing facts. Otherwise give a short recommendation and offer the relevant artifact.

Recommended approach: Build a register of policies with owner, version and review date. Write the missing policy drafts only for the ones you name.

Why this one: Most SMEs have policies in several places and no owner. A register with an owner and a review date makes the gap visible.

Workflow: Policy draft → Approve → Publish version → Assign → Review date

Step 5 - Build only on request

Once the user asks for it, derive the fields from the confirmed context and emit the

requested artifacts. For machine-readable text, keep prose outside the data; for files,

provide a usable link. Report material validation failures or limitations separately.

**A selected Notion output is rendered by notion-manual-import, so route the

Notion step there.** When the user selects Notion, hand that step to

@notion-manual-import: it holds the CSV, the property

mapping, the import steps and the verification checklist, and it renders the Field

Reference below instead of defining a table of its own. Do not restate the mapping

here and do not improvise the import steps. Manual CSV and mapping outputs need no

connection. For requested workspace changes, follow the shared contract: verify actual

tool access and the target before writing. A user saying "connected" is not tool evidence.

Never ask for a Notion password or token.

For an Excel-compatible CSV, use UTF-8 with a byte order mark so Excel opens the

text correctly. A CSV is not an .xlsx workbook; create .xlsx only when the user

requests a workbook.

A CSV carries no types, so after it, name the columns

that need a number, date or currency format applied.

Policy Name,Acknowledgement Required,Applies To,Approver,Category,Compliance Framework,Effective Date,Next Review,Policy ID,Policy Owner,Status,Summary,Version,Acknowledgements
Code of Conduct,FALSE,All employees,Sneha Iyer,HR,ISO 27001,2026-01-15,2026-01-15,,Sneha Iyer,Published,"Code of conduct, version 2.1, reviewed in January.",v1.0,11

CREATE TABLE policy_library (
  policy_name VARCHAR(255),
  acknowledgement_required BOOLEAN NOT NULL,
  applies_to VARCHAR(255),
  approver VARCHAR(255),
  category VARCHAR(100) NOT NULL,
  compliance_framework VARCHAR(255),
  effective_date DATE NOT NULL,
  next_review DATE NOT NULL,
  policy_id SERIAL PRIMARY KEY,
  policy_owner VARCHAR(255),
  status VARCHAR(100) NOT NULL,
  summary TEXT,
  version VARCHAR(255),
  acknowledgements NUMERIC NOT NULL,
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

CREATE INDEX idx_policy_library_status ON policy_library (status);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Policy Library",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "Policy Name": { "type": "string" },
      "Acknowledgement Required": { "type": "boolean" },
      "Applies To": { "type": "string" },
      "Approver": { "type": "string" },
      "Category": { "type": "string" },
      "Compliance Framework": { "type": "string" },
      "Effective Date": { "type": "string", "format": "date" },
      "Next Review": { "type": "string", "format": "date" },
      "Policy ID": { "type": "integer" },
      "Policy Owner": { "type": "string" },
      "Status": { "type": "string" },
      "Summary": { "type": "string" },
      "Version": { "type": "string" },
      "Acknowledgements": { "type": "number" }
  },
  "required": [
      "Acknowledgement Required",
      "Category",
      "Effective Date",
      "Next Review",
      "Status",
      "Acknowledgements"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Policy Name | Title | Use as the database title |
| Acknowledgement Required | Checkbox | Convert to Checkbox |
| Applies To | Text | Leave as Text |
| Approver | Text | Leave as Text |
| Category | Select (add options after import) | Convert to Select, add options: "HR", "Finance", "Security", "Safety", "Legal", "Operations" |
| Compliance Framework | Text | Leave as Text |
| Effective Date | Date | Convert to Date |
| Next Review | Date | Convert to Date |
| Policy ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
| Policy Owner | Text | Leave as Text |
| Status | Select (add options after import) | Convert to Select, add options: "Draft", "In Review", "Published", "Under Revision", "Retired" |
| Summary | Text | Leave as Text |
| Version | Text | Leave as Text |
| Acknowledgements | Number | Convert to Number |

The rows above are documentation examples only. Emit empty templates unless the user explicitly requests examples. Money stays currency, dates stay date,

and anything pointing at another table stays relation.

Field Reference

| # | Field | Type | SQL | JSON Schema | Notion | CSV example |

|---:|---|---|---|---|---|---|

| 1 | Policy Name | text | VARCHAR(255) | string | Text | Code of Conduct |

| 2 | Acknowledgement Required | checkbox | BOOLEAN | boolean | Checkbox | FALSE |

| 3 | Applies To | text | VARCHAR(255) | string | Text | All employees |

| 4 | Approver | text | VARCHAR(255) | string | Text | Sneha Iyer |

| 5 | Category | select | VARCHAR(100) | string | Select (add options after import) | HR |

| 6 | Compliance Framework | text | VARCHAR(255) | string | Text | ISO 27001 |

| 7 | Effective Date | date | DATE | string, format: date | Date | 2026-01-15 |

| 8 | Next Review | date | DATE | string, format: date | Date | 2026-01-15 |

| 9 | Policy ID | id | SERIAL PRIMARY KEY | integer | Text (preserve source ID) | (blank) |

| 10 | Policy Owner | text | `VARCH

… (nội dung đầy đủ có trong gói tải về)