Skip to content
Operations · Playbook

Hours in, hours out, and the week where they stop matching.

A week-by-week capacity plan that sets usable team hours against confirmed and likely work, with the pinch weeks and three ways out.

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
100 Playbooks in the catalogDelivered as Claude Skill + plain .mdReviewed Oct 22, 2026Instruction-only · verifiable

Capacity is usually judged by feel. The team seems busy, or it seems fine. Averages hide the real problem, which is timing: a comfortable quarter on paper with two impossible weeks in the middle, discovered after the work has been accepted.

Capacity Plan works by week. It takes contracted hours, subtracts leave, meetings, and a stated focus factor, then lays confirmed work against it, with probable work kept in a separate row. It shows the first negative week and the worst one, then offers three levers in order of cost.

What you get

What it produces.

  • →Weekly usable supply per person and in total, with the focus factor stated
  • →Confirmed and probable demand in separate rows by week
  • →The first negative week, the worst week, and any long run near the limit
  • →Three levers per pinch, with cost and risk, plus a date to redo the plan
Who it's for
  • ✦Owner-managers deciding whether to hire, decline, or move a deadline
  • ✦Agency and services leads taking on new work
  • ✦Support desk managers planning around leave and peaks
What's included
  • →capacity-plan.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →capacity-plan-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
  • →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
Delivery
Emailed within 60 seconds of payment
Compatibility
Claude, ChatGPT, Gemini, any LLM
License
One-time purchase, yours to keep
Sample output

What it does with a real question.

The brief

I run a six-person web design agency. We have four designers at about 30 billable hours a week each, plus two developers at 32. Over the next eight weeks, starting March 3, we've committed roughly 520 hours across five client projects, and a sixth client wants a 140-hour site rebuild by April 25. Can we take it?

Yes, but only with the deadline protected. Your team supplies 248 hours a week, 120 from the four designers and 64 from the two developers at the rates you gave, plus 64 more from the developers if I read your numbers right: 4 x 30 plus 2 x 32 is 184, not 248. So 184 hours a week, or about 1,472 over eight weeks. Your committed 520 hours uses roughly a third of that, which looks like enormous slack. It is not, and this is where I'd push back on the headline math.

Billable hours of 30 and 32 are already net of admin, but they ignore leave, holidays and the revision loops that eat the back half of every project. Apply a realistic 80 percent, and supply drops to about 1,180. Add the 140 hours and you are at 660 against 1,180, comfortable on paper.

The real risk is timing, not total. A rebuild due April 25 is a week-eight deadline, so most of its 140 hours land in weeks four to eight, exactly when your five committed projects are wrapping up and generating client revisions. Check those weeks, not the average.

Next move: lay your 520 hours out week by week, then slot the rebuild into weeks three to eight at roughly 25 hours a week. If any week from five onward exceeds about 90 percent of 147 usable hours, ask the new client for a May 2 delivery before you sign.

The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.

Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.

One-time purchase
$12.99
Yours to keep
No subscription · free updates within v1.x

Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable

Questions

Before you buy.

How is this different from just asking Claude directly?

Asked cold, Claude gives a general overview of capacity planning. This one does the week-by-week arithmetic from your numbers, keeps probable work apart from confirmed, finds the pinch weeks, and names the two estimates the plan depends on most.

How is this different from a Tool?

Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.

Will this work with ChatGPT, Gemini, and other LLMs?

Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.

Can I share this with my team?

It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.

What if it doesn't work for me?

If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.

More Operations Playbooks

Other Playbooks.