Skip to content
Operations · Playbook

Rank the manual tasks by hours saved, not by how much they irritate you.

A ranked shortlist of tasks worth automating, with yearly hours, effort, payback, and a clear list of what should stay manual.

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

Automation tends to start with whatever annoys someone. A clever automation gets built for a ten-minute weekly job while a daily copy-paste carries on, and nobody counted the hours or asked who fixes it when it breaks.

Automation Audit lists every repetitive task with frequency and minutes, converts to yearly hours, and screens out work that is unstable or needs judgment. It estimates build effort, upkeep, and the cost of a silent failure, then ranks by net hours saved with a payback period and a first small step for each.

What you get

What it produces.

  • →A task inventory with yearly hours, marked estimated or measured
  • →A screen showing which tasks should stay manual, and why
  • →A ranked shortlist of three to five with net hours and payback
  • →A later list, a never list, and the one measurement to take before starting
Who it's for
  • ✦Operations managers choosing where to spend limited setup time
  • ✦Owner-managers whose team lives in spreadsheets and copy-paste
  • ✦Anyone asked what the team could automate
Next to a Tool

This Playbook ranks tasks by hours saved. It does not map how a process actually runs, so it does not trace handoff delays, rework loops, or steps that should be removed before anything is automated. The Process Audit Tool does that diagnosis: it finds where a working process quietly loses time, money, or quality. Automation Audit does not include that, and it builds nothing.

See the Process Audit Tool ($99) →
What's included
  • →automation-audit.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →automation-audit-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 operations for a 12-person property management office, and my team loses roughly 25 hours a week on manual work. We copy tenant payments from bank exports into a shared spreadsheet, retype maintenance requests from emails into a tracker, and build monthly owner reports by hand. What should we automate first?

Start with the tenant payment copying. You gave me three tasks and 25 hours a week in total, but not the split, so here is my working guess: payments are probably the biggest block, since it recurs daily or weekly and touches every tenant, while the monthly owner reports are large per run but happen only 12 times a year. Rank by hours, not irritation, and the payments lead the list, with maintenance retyping second and reports third.

Payments also pass the stability screen best. A bank export is structured, the matching rules (tenant, unit, amount, date) are fixed, and judgment is rare. Maintenance emails are the opposite: free text, inconsistent detail, and a tenant who writes "the thing in the bathroom is leaking again" still needs a human to read it. Reports depend on clean upstream data, so automating them before the payment sheet is reliable would just produce tidy reports from messy numbers.

Mind the failure cost. A silent mismatch in rent records is worse than a slow spreadsheet, so build it with a human check on anything the match cannot confidently place, and name one person who owns it when it breaks.

Next move: this week, have whoever does the copying log minutes per session for five working days. That replaces my guess with a measured figure and tells you whether payback is weeks or months before you spend any setup time.

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 lists popular automation ideas for your industry. This ranks your own tasks by net hours after build and upkeep, screens out unstable ones, asks who owns the fix, and tests whether the ranking survives if your estimates are half right.

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. This Playbook ranks tasks by hours saved. It does not map how a process actually runs, so it does not trace handoff delays, rework loops, or steps that should be removed before anything is automated. The Process Audit Tool does that diagnosis: it finds where a working process quietly loses time, money, or quality. Automation Audit does not include that, and it builds nothing.

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.