kpi-tracker – skill Khác cho agent AI

KPI Tracker

What it is: KPIs by company, department, role and person with targets and actuals.

Overview

Works out the smallest useful KPI Tracker 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: Growth stage. Table code: n/a.

When to Use This Skill

• kpi tracker
• kpi dashboard spreadsheet
• target vs actual
• performance metrics tracker

Also use it when the user says "kpis by company, department, role and person with targets and actuals", 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 KPIs matter most?

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.

• Metrics - Which KPIs? / Company or team level? / How many to start?
• Shape - Target and actual? / Unit and direction? / Weight or equal?
• Cadence - How often reviewed? / Who reviews? / Data source?
• Current process - How do you track today? / Spreadsheet or dashboard? / Is it trusted?
• Outcome - What do you need? / A tracker, a dashboard or scoring?

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: kpi-tracker
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Metrics": null
  "Shape": null
  "Cadence": 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: Start with three to five metrics per level and a fixed review cadence. Use weights only with a defined aggregate score, including team or company scorecards; agree the formula before comparing results.

Why this one: KPI trackers fail from volume, not from schema. Fewer metrics reviewed on a schedule beats a full scorecard nobody opens.

Workflow: KPI definition → Target → Actual entry → Achievement → Review meeting

For this higher-is-better example with a positive target, achievement is 100 * actual / target; weighted score is achievement * weight / 100 in percentage points, rounded only for display. Lower-is-better, zero/negative targets, caps, missing actuals and composite metrics need an explicitly agreed formula; leave unknown scores blank rather than inventing zero. Validate weights in 0–100 and their total within each scorecard. These templates do not calculate or enforce the formula.

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.

KPI Name,KPI Level,Department,Job Title,Employee Name,Linked OKR,Unit,Direction,Target,Actual,Achievement %,Weight %,Weighted Score,Period,Data Source,Owner,Status,KPI ID
On-time delivery,Company,Delivery,Delivery Manager,Aarav Sharma,OKR-2026-Q1-02,Percent,Higher is better,95,88,92.63,30,27.79,2026-03,Manual,Sneha Iyer,Active,

CREATE TABLE kpi_tracker (
  kpi_name VARCHAR(255),
  kpi_level VARCHAR(100) NOT NULL,
  department VARCHAR(255),
  job_title VARCHAR(255),
  employee_name VARCHAR(255),
  linked_okr VARCHAR(255),  -- relation -> target record
  unit VARCHAR(255),
  direction VARCHAR(255),
  target NUMERIC NOT NULL,
  actual NUMERIC NOT NULL,
  achievement_pct NUMERIC NOT NULL,
  weight_pct NUMERIC NOT NULL,
  weighted_score NUMERIC NOT NULL,
  period VARCHAR(255),
  data_source VARCHAR(255),
  owner VARCHAR(255),
  status VARCHAR(100) NOT NULL,
  kpi_id SERIAL PRIMARY KEY,
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW()
);

CREATE INDEX idx_kpi_tracker_status ON kpi_tracker (status);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "KPI Tracker",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "KPI Name": { "type": "string" },
      "KPI Level": { "type": "string" },
      "Department": { "type": "string" },
      "Job Title": { "type": "string" },
      "Employee Name": { "type": "string" },
      "Linked OKR": { "type": "string" },
      "Unit": { "type": "string" },
      "Direction": { "type": "string" },
      "Target": { "type": "number" },
      "Actual": { "type": "number" },
      "Achievement %": { "type": "number" },
      "Weight %": { "type": "number" },
      "Weighted Score": { "type": "number" },
      "Period": { "type": "string" },
      "Data Source": { "type": "string" },
      "Owner": { "type": "string" },
      "Status": { "type": "string" },
      "KPI ID": { "type": "integer" }
  },
  "required": [
      "KPI Level",
      "Target",
      "Actual",
      "Achievement %",
      "Weight %",
      "Weighted Score",
      "Status"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| KPI Name | Title | Use as the database title |
| KPI Level | Select (add options after import) | Convert to Select, add options: "Company", "Department", "Role", "Individual" |
| Department | Text | Leave as Text |
| Job Title | Text | Leave as Text |
| Employee Name | Text | Leave as Text |
| Linked OKR | Relation (link to the target database) | Convert to Relation, link to the target database |
| Unit | Text | Leave as Text |
| Direction | Text | Leave as Text |
| Target | Number | Convert to Number |
| Actual | Number | Convert to Number |
| Achievement % | Number | Convert to Number |
| Weight % | Number | Convert to Number |
| Weighted Score | Number | Convert to Number |
| Period | Text | Leave as Text |
| Data Source | Text | Leave as Text |
| Owner | Text | Leave as Text |
| Status | Select (add options after import) | Convert to Select, add options: "Draft", "Active", "At Risk", "Retired" |
| KPI 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

|

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