dei-dashboard – skill Khác cho agent AI

DEI Dashboard

What it is: Diversity & inclusion.

Overview

Works out the smallest useful DEI Dashboard 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: Scale stage. Table code: n/a.

When to Use This Skill

• dei dashboard
• diversity reporting
• workforce diversity metrics
• inclusion tracker

Also use it when the user says "diversity & inclusion", 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 stages of hiring do you want to look at?

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.

• Scope - Hiring, progression or both? / Which stages? / By department or overall?
• Data - What data exists today? / Voluntary self-ID? / Anonymised?
• Baselines - Compare against what? / External benchmark? / Internal target?
• Current process - Anything tracked now? / HRIS or a sheet? / Is it anonymised?
• Outcome - What do you need? / A metric set or a dashboard view?

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: dei-dashboard
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Scope": null
  "Data": null
  "Baselines": 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: Use voluntary, anonymised data and aggregate to groups large enough to protect people. Skip any breakdown that would identify someone.

Why this one: Diversity data is easy to collect and easy to misuse. Anonymity and minimum group size are conditions of doing it at all, not nice-to-haves.

Workflow: Voluntary data → Anonymised aggregation → Stage metrics → Review → Action

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.

Metric,Department,Period,Measure Type,Value,Target,Group Size,Minimum Group Size Met,Data Source,Notes,Metric ID
Net revenue,Delivery,2026-03,Count,139240,95,12,TRUE,Manual,"Baseline captured in February; headcount denominators still exclude the contract workforce.",

CREATE TABLE dei_dashboard (
  metric VARCHAR(255),
  department VARCHAR(255),
  period VARCHAR(255),
  measure_type VARCHAR(100) NOT NULL,
  value NUMERIC NOT NULL,
  target NUMERIC NOT NULL,
  group_size NUMERIC NOT NULL,
  minimum_group_size_met BOOLEAN NOT NULL,
  data_source VARCHAR(255),
  notes TEXT,
  metric_id SERIAL PRIMARY KEY,
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "DEI Dashboard",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "Metric": { "type": "string" },
      "Department": { "type": "string" },
      "Period": { "type": "string" },
      "Measure Type": { "type": "string" },
      "Value": { "type": "number" },
      "Target": { "type": "number" },
      "Group Size": { "type": "integer", "minimum": 0 },
      "Minimum Group Size Met": { "type": "boolean" },
      "Data Source": { "type": "string" },
      "Notes": { "type": "string" },
      "Metric ID": { "type": "integer" }
  },
  "required": [
      "Measure Type",
      "Value",
      "Target",
      "Group Size",
      "Minimum Group Size Met"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Metric | Title | Use as the database title |
| Department | Text | Leave as Text |
| Period | Text | Leave as Text |
| Measure Type | Select (add options after import) | Convert to Select, add options: "Count", "Percentage", "Ratio", "Average" |
| Value | Number | Convert to Number |
| Target | Number | Convert to Number |
| Group Size | Number | Convert to Number |
| Minimum Group Size Met | Checkbox | Convert to Checkbox |
| Data Source | Text | Leave as Text |
| Notes | Text | Leave as Text |
| Metric 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.

Field Reference

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

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

| 1 | Metric | text | VARCHAR(255) | string | Text | Net revenue |

| 2 | Department | text | VARCHAR(255) | string | Text | Delivery |

| 3 | Period | text | VARCHAR(255) | string | Text | 2026-03 |

| 4 | Measure Type | select | VARCHAR(100) | string | Select (add options after import) | Count |

| 5 | Value | number | NUMERIC | number | Number | 139240 |

| 6 | Target | number | NUMERIC | number | Number | 95 |

| 7 | Group Size | number | NUMERIC | number | Number | 12 |

| 8 | Minimum Group Size Met | checkbox | BOOLEAN | boolean | Checkbox | TRUE |

| 9 | Data Source | text | VARCHAR(255) | string | Text | Manual |

| 10 | Notes | long_text | TEXT | string | Text | Baseline captured in February; headcount denominators still exclude the contract workforce. |

| 11 | Metric ID | id | SERIAL PRIMARY KEY | integer | Text (preserve source ID) | (blank) |

A threshold checkbox does not anonymize data. Define the threshold, denominator and suppression policy explicitly; suppress small cells and complementary totals/breakdowns that permit re-identification. Do not infer protected characteristics or use this template to rank individuals.

Select Options

Measure Type

Count | Percentage | Ratio | Average

Relations

Link fields: none

Examples

Prompt

We want to see where our hiring process drops people out.

Context first - one question per message, nothing already answered:

> Q: Which stages?

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