AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Ops Capacity Planner

Sizes queued-work ops teams with Erlang-C math: required FTE, utilization risk bands, and a 12-month ramp- and attrition-aware hiring sequence.

Data & AnalyticsIntermediate★ 24,151⑂ 3,405AI score 8/10Last updated: Aug 9, 2026

What it does

  • Capacity sizing: Erlang-C model of required FTE across 70/80/90% utilization against P50/P90/P99 demand, with P(SLA breach) at each point and a SAFE/WATCH/AT_RISK/CRITICAL risk band, shrinkage-adjusted.
  • Utilization health: per-member traffic lights plus a team verdict (HEALTHY/SQUEEZED/OVERLOADED/UNBALANCED); a spread over 30 percentage points means rebalance before hiring.
  • 12-month quarterly hiring plan: ramp curves, attrition replacement, QoQ demand growth, max-hires-per-quarter limits, and an automatic manager-hire trigger past 7 ICs per manager.
  • Seven forcing questions covering bottleneck confirmation, service trade-offs, P90/P99 gap, breach probability, attrition backfill, span of control, and the P99 surge plan.
  • Three stdlib-only Python scripts (capacity_modeler.py, utilization_analyzer.py, hiring_sequencer.py) with --sample, --input, and --output flags, plus canon references and a fill-out brief template.

Who it's for

  • Support, CX, Customer Success, BizOps, IT Ops, and Finance Ops leaders whose teams handle queued work (tickets, cases, work items).
  • Teams running sustained utilization above 80% or growing more than 50% in 12 months.
  • Anyone who has to defend a headcount ask to a CFO with arithmetic instead of intuition.
  • Not for engineering throughput (DORA/cycle time) or 1–5 year strategic workforce planning.

Example uses

  1. Annual planning (Oct–Nov): pull 90 days of daily ticket P50/P90/P99 from Zendesk, run capacity_modeler.py --profile support, and use the 80%-utilization row as next year's sizing point.
  2. SLA slippage diagnostic: a team at 88% utilization is missing SLA — utilization_analyzer.py tells you whether it's undersizing or an unbalanced workload distribution.
  3. Budget sequencing: 20 FTE today, 28 by year-end, 30% attrition, 60-day ramp → hiring_sequencer.py front-loads Q1 hires and names the quarter you must add a manager.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alirezarezvani/claude-skills/HEAD/.gemini/skills/capacity-planner/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the .gemini/skills/capacity-planner folder from the GitHub repo alirezarezvani/claude-skills into my ~/.claude/skills/capacity-planner/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alirezarezvani/claude-skills.git && mkdir -p ~/.claude/skills && cp -r claude-skills/.gemini/skills/capacity-planner ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and go to your working directory.
  2. Clone the repo: git clone https://github.com/alirezarezvani/claude-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r claude-skills/.gemini/skills/capacity-planner ~/.claude/skills/
    • Verify with ls ~/.claude/skills/capacity-planner that scripts/, references/, and assets/ came along. If not, locate them with find . -name capacity_modeler.py inside the repo and copy them in.
  5. Confirm Python 3 is available: python3 --version
  6. Smoke-test it: cd ~/.claude/skills/capacity-planner && python3 scripts/capacity_modeler.py --sample
  7. Restart Claude Code, then ask something like "size my support team for P90 demand at 80% utilization".
  8. Before real use, gather 90+ days of demand distribution (P50/P90/P99), average handle time, SLA target, current FTE, and your shrinkage percentage.
View source on GitHub ↗License: MIT