people-directory – Other skill for AI agents

People Directory

What it is: Employee master data.

Overview

Works out the smallest useful People Directory 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 3: Onboard. Fits: Starter stage. Table code: n/a.

When to Use This Skill

• employee directory
• people directory template
• employee master data
• staff database

Also use it when the user says "employee master data", 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

The upstream shared contract is not bundled; follow the explicit intake, artifact and authorization rules below. 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: How many people are in the company 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.

• People - How many people? / Full time, part time, contractors? / Any remote?
• Data - Store salary on it? / Store emergency contacts? / What is sensitive?
• Structure - Reporting lines? / Grades or bands? / Locations?
• Current process - Where is the list now? / HR system or spreadsheet? / How stale is it?
• Outcome - What do you need? / A directory, a master record or reporting?

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: people-directory
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "People": null
  "Data": null
  "Structure": 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: One person record per human, with the sensitive fields separated out. Most modules should link to it, not duplicate it.

Why this one: A people directory is the root record. If it is wrong, leave, assets, payroll and reviews are all wrong, so it is worth doing properly once.

Workflow: Joiner → Person record → Links to other modules → Change → Exit record

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.

Full Name,Annual CTC,Currency,Date of Birth,Department,Email,Accounts,Emergency Contact,Emergency Phone,Employee ID,Employment Type,End Date,Grade Level,KPIs,Job Title,Access Role,LinkedIn,Manager,Nationality,Notes,Phone,Probation Status,Profile Photo URL,Skills,Start Date,Status,Time Zone,Work Location
Aarav Sharma,1200000.00,INR,1991-04-18,Delivery,[email protected],"Payroll portal, HRIS",Anil Sharma,+91 98xxxxxx34,EMP-001,Full Time,2027-03-31,L1,On-time delivery %,Delivery Manager,Line manager,https://linkedin.com/in/aarav-sharma-example,Sneha Iyer,Indian,Joined from a competitor; notice period is one month.,+91 98xxxxxx21,Passed,https://example.com/photo.jpg,"Excel, SQL, Client Handling",2021-03-08,Active,IST (UTC+5:30),Bengaluru

CREATE TABLE people_directory (
  full_name VARCHAR(255),
  annual_ctc NUMERIC(14,2),  -- optional restricted HR data, omit from shared directory
  currency VARCHAR(255),
  date_of_birth DATE,  -- optional restricted HR data, omit from shared directory
  department VARCHAR(255),
  email VARCHAR(255),
  accounts VARCHAR(255),
  emergency_contact VARCHAR(255),
  emergency_phone VARCHAR(255),
  employee_id VARCHAR(255) PRIMARY KEY,
  employment_type VARCHAR(100) NOT NULL,
  end_date DATE,
  grade_level VARCHAR(100) NOT NULL,
  kpis VARCHAR(255),
  job_title VARCHAR(255),
  access_role VARCHAR(255),
  linkedin TEXT,
  manager VARCHAR(255),
  nationality VARCHAR(255),
  notes TEXT,
  phone VARCHAR(255),
  probation_status VARCHAR(100) NOT NULL,
  profile_photo_url TEXT,
  skills VARCHAR(255),
  start_date DATE NOT NULL,
  status VARCHAR(100) NOT NULL,
  time_zone VARCHAR(255),
  work_location VARCHAR(255),
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

CREATE INDEX idx_people_directory_status ON people_directory (status);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "People Directory",
  "type": "object",
  "additionalProperties": false,
  "properties": {
    "Full Name": {
      "type": "string"
    },
    "Annual CTC": {
      "type": "number"
    },
    "Currency": {
      "type": "string"
    },
    "Date of Birth": {
      "type": "string",
      "format": "date"
    },
    "Department": {
      "type": "string"
    },
    "Email": {
      "type": "string",
      "format": "email"
    },
    "Accounts": {
      "type": "string"
    },
    "Emergency Contact": {
      "type": "string"
    },
    "Emergency Phone": {
      "type": "string"
    },
    "Employee ID": {
      "type": "string"
    },
    "Employment Type": {
      "type": "string"
    },
    "End Date": {
      "type": "string",
      "format": "date"
    },
    "Grade Level": {
      "type": "string"
    },
    "KPIs": {
      "type": "string"
    },
    "Job Title": {
      "type": "string"
    },
    "Access Role": {
      "type": "string"
    },
    "LinkedIn": {
      "type": "string",
      "format": "uri"
    },
    "Manager": {
      "type": "string"
    },
    "Nationality": {
      "type": "string"
    },
    "Notes": {
      "type": "string"
    },
    "Phone": {
      "type": "string"
    },
    "Probation Status": {
      "type": "string"
    },
    "Profile Photo URL": {
      "type": "string",
      "format": "uri"
    },
    "Skills": {
      "type": "string"
    },
    "Start Date": {
      "type": "string",
      "format": "date"
    },
    "Status": {
      "type": "string"
    },
    "Time Zone": {
      "type": "string"
    },
    "Work Location": {
      "type": "string"
    }
  },
  "required": [
    "Employee ID",
    "Employment Type",
    "Grade Level",
    "Probation Status",
    "Start Date",
    "Status"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Full Name | Title | Use as the database title |
| Annual CTC | Number (format: currency) | Convert to Number, set format to Currency |
| Currency | Text | Leave as Text |
| Date of Birth | Date | Conve

… (full content is in the download package)