attendance – skill Dữ liệu & Khoa học cho agent AI

Attendance

What it is: Daily check-in, check-out, late and absent records.

Overview

Works out the smallest useful Attendance 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 4: Manage. Fits: Starter stage. Table code: n/a.

When to Use This Skill

• attendance tracker
• daily attendance sheet
• check in check out log
• absent and late tracker

Also use it when the user says "daily check-in, check-out, late and absent records", 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: What are your working hours?

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.

• Hours - Shift timings? / Flexible or fixed? / Any night shift?
• Method - Check in, check out or both? / How recorded? / Self or auto?
• Rules - Late tolerance? / Half day rules? / Geofence needed?
• Current process - How is it done now? / Biometric, app or paper? / What gets disputed?
• Outcome - What do you need? / A record, payroll input or reports?

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: attendance
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Hours": null
  "Method": null
  "Rules": 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: Collect one row per person per day, and only build rules for the cases that actually happen. Overtime and payroll join later if needed.

Why this one: Attendance fails when corrections have no owner. Add a regularisation step and the record stays trustworthy without surveillance.

Workflow: Daily log → Late or absent flag → Correction request → Manager approval → Monthly report

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.

Attendance Record,Employee Name,Department,Date,Check-in Time,Check-out Time,Hours Worked,Work Mode,Attendance Status,Late (Minutes),On Approved Leave,Manager,Regularisation Requested,Notes,Attendance ID
ATT-EXAMPLE-001,Example Employee,Delivery,2026-01-15,09:58,18:30,8.5,Office,Present,12,FALSE,Example Manager,FALSE,"Late arrivals cluster on Mondays; discussed with the team rather than logged as a penalty.",

CREATE TABLE attendance (
  attendance_record VARCHAR(255),
  employee_name VARCHAR(255),
  department VARCHAR(255),
  date DATE NOT NULL,
  check_in_time VARCHAR(255),
  check_out_time VARCHAR(255),
  hours_worked NUMERIC NOT NULL CHECK (hours_worked >= 0),
  work_mode VARCHAR(255),
  attendance_status VARCHAR(100) NOT NULL,
  late_minutes NUMERIC NOT NULL CHECK (late_minutes >= 0),
  on_approved_leave BOOLEAN NOT NULL,
  manager VARCHAR(255),
  regularisation_requested BOOLEAN NOT NULL,
  notes TEXT,
  attendance_id SERIAL PRIMARY KEY,
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Attendance",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "Attendance Record": { "type": "string" },
      "Employee Name": { "type": "string" },
      "Department": { "type": "string" },
      "Date": { "type": "string", "format": "date" },
      "Check-in Time": { "type": "string" },
      "Check-out Time": { "type": "string" },
      "Hours Worked": { "type": "number", "minimum": 0 },
      "Work Mode": { "type": "string" },
      "Attendance Status": { "type": "string" },
      "Late (Minutes)": { "type": "number", "minimum": 0 },
      "On Approved Leave": { "type": "boolean" },
      "Manager": { "type": "string" },
      "Regularisation Requested": { "type": "boolean" },
      "Notes": { "type": "string" },
      "Attendance ID": { "type": "integer" }
  },
  "required": [
      "On Approved Leave",
      "Regularisation Requested",
      "Date",
      "Hours Worked",
      "Attendance Status",
      "Late (Minutes)"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Attendance Record | Title | Use as the database title |
| Employee Name | Text | Leave as Text |
| Department | Text | Leave as Text |
| Date | Date | Convert to Date |
| Check-in Time | Text | Leave as Text |
| Check-out Time | Text | Leave as Text |
| Hours Worked | Number | Convert to Number |
| Work Mode | Text | Leave as Text |
| Attendance Status | Select (add options after import) | Convert to Select, add options: "Present", "Late", "Absent", "On Leave", "Half Day", "Holiday" |
| Late (Minutes) | Number | Convert to Number |
| On Approved Leave | Checkbox | Convert to Checkbox |
| Manager | Text | Leave as Text |
| Regularisation Requested | Checkbox | Convert to Checkbox |
| Notes | Text | Leave as Text |
| Attendance ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |

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.

Hours Worked and Late are supplied values, not calculated by this template. Define approved shift, breaks, rounding, timezone and overnight-date rules before deriving them; do not infer hours from time-only strings or impose automatic penalties. The sample row is independent of the later conversational example.

Field Reference

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

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

| 1 | Attendance Record | text | VARCHAR(255) | string | Text | ATT-EXAMPLE-001 |

| 2 | Employee Name | text | VARCHAR(255) | string | Text | Example Employee |

| 3 | Department | text | VARCHAR(255) | string | Text | Delivery |

| 4 | Date | date | DATE | string, format: date | Date | 2026-01-15 |

|

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