capacity-workload-planner – skill Khác cho agent AI

Capacity & Workload Planner

What it is: Resource management.

Overview

Works out the smallest useful Capacity & Workload Planner 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: Scale stage. Table code: n/a.

When to Use This Skill

• capacity planning
• workload planner
• resource allocation sheet
• utilization tracker

Also use it when the user says "resource management", 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: How many people are billable?

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.

• Capacity - How many people? / Billable or not? / Weekly hours?
• Demand - How many live projects? / Who allocates? / Fixed dates?
• Method - Weekly or daily? / Utilisation target? / Overtime allowed?
• Current process - How do you plan now? / Spreadsheet or guess? / When is it too late?
• Outcome - What do you need? / A plan, alerts or a forecast?

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: capacity-workload-planner
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Capacity": null
  "Demand": null
  "Method": 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 weekly planning when it fits the work, and flag over-allocation; use daily detail when shift or delivery constraints require it.

Why this one: Weekly planning can be a useful starting point; confirm the actual planning horizon and avoid unsupported claims about how every team works.

Workflow: People → Available hours → Allocation by week → Over-allocation flag → Rebalance

Derived values - calculate, never ask for and never accept as typed:

Utilisation %    = Allocated Hours / Available Hours x 100, rounded once to the nearest whole number
Allocation Check = Over-allocated  when Allocated Hours > Available Hours
                   Within capacity when Allocated Hours = Available Hours
                   Under-allocated when Allocated Hours < Available Hours

The percentage is stored as a whole number: 80 means 80%, never 0.8. Round once, at this

step for display only. Compare unrounded hours for the flag: 40.1/40 displays 100% but is still over-allocated. Do not let rounding hide excess demand. If Available Hours is 0 the ratio is undefined: leave Utilisation % and

Allocation Check empty and flag the row for a human rather than dividing by zero or

defaulting to 0. A person on full leave has no capacity, which is not the same as having

spare capacity.

Approval gate: a week may only be Approved when capacity is positive and allocated hours do not exceed available hours; both Within capacity and Under-allocated may qualify.

An over-allocated week is a real finding, not a rounding error - raise it, do not approve it,

and do not quietly trim Allocated Hours to make it fit. Reallocate with the people affected,

or record why the over-allocation is accepted.

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.

Employee Name,Department,Project,Week Start,Available Hours,Allocated Hours,Utilisation %,Allocation Check,Leave Days,Status,Notes,Capacity ID
Example Employee,Delivery,Website Redesign,2026-01-05,32,38,119,Over-allocated,3,Draft,"Allocated 38 hours against 32 available, so this week needs a trade before it can be approved.",

CREATE TABLE capacity_workload_planner (
  employee_name VARCHAR(255),
  department VARCHAR(255),
  project VARCHAR(255),
  week_start DATE NOT NULL,
  available_hours NUMERIC NOT NULL,
  allocated_hours NUMERIC NOT NULL,
  utilisation_pct NUMERIC,
  allocation_check VARCHAR(100),
  leave_days NUMERIC NOT NULL,
  status VARCHAR(100) NOT NULL,
  notes TEXT,
  capacity_id SERIAL PRIMARY KEY,
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW(),
  -- Utilisation and the check are derived, so they stay nullable: zero capacity is undefined, not zero.
  CHECK (allocation_check IS NULL OR allocation_check IN ('Over-allocated', 'Within capacity', 'Under-allocated')),
  -- An over-allocated week is a finding to escalate, not a plan to sign off.
  CHECK (available_hours >= 0 AND allocated_hours >= 0 AND leave_days >= 0),
  CHECK (status <> 'Approved' OR (available_hours > 0 AND allocated_hours <= available_hours
    AND COALESCE(allocation_check IN ('Within capacity', 'Under-allocated'), FALSE)))
);

CREATE INDEX idx_capacity_workload_planner_status ON capacity_workload_planner (status);
CREATE INDEX idx_capacity_workload_planner_week_start ON capacity_workload_planner (week_start);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Capacity Workload Planner",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "Employee Name": { "type": "string" },
      "Department": { "type": "string" },
      "Project": { "type": "string" },
      "Week Start": { "type": "string", "format": "date" },
      "Available Hours": { "type": "number" },
      "Allocated Hours": { "type": "number" },
      "Utilisation %": { "type": "number" },
      "Allocation Check": { "type": "string" },
      "Leave Days": { "type": "number" },
      "Status": { "type": "string" },
      "Notes": { "type": "string" },
      "Capacity ID": { "type": "integer" }
  },
  "required": [
      "Week Start",
      "Available Hours",
      "Allocated Hours",
      "Leave Days",
      "Status"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Employee Name | Title | Use as the database title |
| Department | Text | Leave as Text |
| Project | Text | Leave as Text |
| Week Start | Date | Convert to Date |
| Available Hours | Number | Convert to

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