announcement-board – skill Dữ liệu & Khoa học cho agent AI

Announcement Board

What it is: News distribution.

Overview

Works out the smallest useful Announcement Board 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 6: Engage. Fits: Starter stage. Table code: n/a.

When to Use This Skill

• announcement board
• company news feed
• notice board
• internal announcements

Also use it when the user says "news distribution", 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: Who needs to read your announcements?

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.

• Audience - Who reads these? / Whole company or a team? / Any external readers?
• Content - What gets posted? / Announcements or both? / Attachments used?
• Approval - Who writes them? / Approval needed? / Scheduled posts?
• Current process - How do you share news now? / Email, chat or both? / What gets missed?
• Outcome - What do you need? / A board, a schedule or archives?

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: announcement-board
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Audience": null
  "Content": null
  "Approval": 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: Publish in one place and keep an expiry date, so old announcements stop looking current. Target the audience rather than broadcasting.

Why this one: Announcement boards fail from clutter, not from missing posts. An expiry date and a clear owner keep the board readable.

Workflow: Draft → Approval → Publish → Read or acknowledged → Expiry

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.

Announcement Title,Acknowledged By,Ann ID,Author,Category,Department,Expiry Date,Priority,Publish Date,Status,Summary,Target Audience,Views
Office closed on 15th,"Example Person 1, Example Person 2",,Example Author,Company,Delivery,2026-01-15,Low,2026-01-15,Published,Office closed on the 15th for the public holiday.,All employees,184

CREATE TABLE announcement_board (
  announcement_title VARCHAR(255),
  acknowledged_by VARCHAR(255),
  ann_id SERIAL PRIMARY KEY,
  author VARCHAR(255),
  category VARCHAR(100) NOT NULL,
  department VARCHAR(255),
  expiry_date DATE NOT NULL,
  priority VARCHAR(100) NOT NULL,
  publish_date DATE NOT NULL,
  status VARCHAR(100) NOT NULL,
  summary TEXT,
  target_audience VARCHAR(255),
  views VARCHAR(255),
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

CREATE INDEX idx_announcement_board_status ON announcement_board (status);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Announcement Board",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "Announcement Title": { "type": "string" },
      "Acknowledged By": { "type": "string" },
      "Ann ID": { "type": "integer" },
      "Author": { "type": "string" },
      "Category": { "type": "string" },
      "Department": { "type": "string" },
      "Expiry Date": { "type": "string", "format": "date" },
      "Priority": { "type": "string" },
      "Publish Date": { "type": "string", "format": "date" },
      "Status": { "type": "string" },
      "Summary": { "type": "string" },
      "Target Audience": { "type": "string" },
      "Views": { "type": "string" }
  },
  "required": [
      "Category",
      "Expiry Date",
      "Priority",
      "Publish Date",
      "Status"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Announcement Title | Title | Use as the database title |
| Acknowledged By | Text | Leave as Text |
| Ann ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
| Author | Text | Leave as Text |
| Category | Select (add options after import) | Convert to Select, add options: "Company", "Department", "Team", "Location", "Role" |
| Department | Text | Leave as Text |
| Expiry Date | Date | Convert to Date |
| Priority | Select (add options after import) | Convert to Select, add options: "Low", "Medium", "High", "Urgent" |
| Publish Date | Date | Convert to Date |
| Status | Select (add options after import) | Convert to Select, add options: "Draft", "Scheduled", "Published", "Archived" |
| Summary | Text | Leave as Text |
| Target Audience | Text | Leave as Text |
| Views | Text | Leave as Text |

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 | Announcement Title | text | VARCHAR(255) | string | Text | Office closed on 15th |

| 2 | Acknowledged By | text | VARCHAR(255) | string | Text | Example Person 1, Example Person 2 |

| 3 | Ann ID | id | SERIAL PRIMARY KEY | integer | Text (preserve source ID) | (blank) |

| 4 | Author | text | VARCHAR(255) | string | Text | Example Author |

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

| 6 | Department | text | VARCHAR(255) | string | Text | Delivery |

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

| 8 | Priority | select | VARCHAR(100) | string | Select (add options after import) | Low |

| 9 | Publish Date | date | DATE | string, format: date | Date | 2026-01-15 |

| 10 | Status | select | VARCHAR(100) | string | Select (add options after import) | Published |

| 11 | Summary | long_text | TEXT | string | Text | `Office closed on

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