A short checklist where every line exists because that step failed once.
A checklist for a recurring task, built from the failures and near misses you describe, trimmed to the few checks that matter.
Checklists written from imagination are long. They cover every step anyone can think of, nobody reads past the third line, and the item that actually caused last month's problem is buried at line 19.
Checklist Builder starts with the evidence: what went wrong, where, and what would have caught it. It turns each failure into one observable check, cuts anything that has never failed, and aims for five to nine lines. It picks the checklist type, puts the costliest failure first, and tests the list against a recent run.
What it produces.
- →A list of past failures traced to the check that would have caught each
- →A final checklist of five to nine verb-first, checkable items
- →A recommendation on checklist type and where it sits in the task
- →A review date to remove items that never fire
- ✦Team leads who repeat a task monthly and keep missing one step
- ✦Event, launch, and onboarding owners
- ✦Operators who want a one-page check people will use
- →checklist-builder.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →checklist-builder-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
What it does with a real question.
I run the monthly close for our 12-person accounting team, and it has gone wrong three times since January: a vendor accrual got missed in March, the bank rec was done before the last wires posted in April, and payroll was booked to the wrong period in May. Can you build me a checklist that guards those spots?
Short list, built from three failures. Your three misses share a pattern: each one is about timing, not technique. The accrual was missed, the rec ran too early, and payroll landed in the wrong period. None of these are skill problems, which is why a checklist fits. Its job is to catch a competent person who is rushed.
I would keep it to five items, each tied to a pause point rather than the whole close. Before accruals are finalized: vendor accrual listing compared against open POs and goods received through period end. Before the bank rec starts: all wires dated in the period confirmed posted at the bank, with the cutoff time noted on the rec. Before payroll is booked: pay period dates on the register match the target accounting period. Before sign-off: a named reviewer confirms those three checks were initialed. Add one more only if a fourth failure earns it.
Make it a confirm-do list. Your team knows the work, so they do it, pause at each gate, then check. Put the bank rec first, since an early rec forces rework across the most accounts and costs the most.
Your next move: have the three owners of those tasks walk through April and May with the list this week. If any item would not have caught its failure, rewrite it until it would, then set a review for July to cut anything that never fired.
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.
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
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude writes a thorough checklist of everything that could go wrong. This builds the list backward from your actual failures, cuts the obvious and the never-failed, and tests it against a recent run to see what it would and would not have caught.
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.