Skip to content
Operations · Playbook

Write the scorecard before the demos. Then see which vendor actually wins.

A side-by-side comparison of two to five vendors, scored against weighted criteria you fix in advance, with total cost shown separately.

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

The demo comes first and the criteria arrive afterward. By the time the scorecard exists, it describes whichever vendor impressed the room. Price is whatever was on the first page, and the one-time fees nobody mentioned show up in month two.

Vendor Comparison reverses the order. You state the need, split must-haves from weighted criteria, and agree on what a 1, 3, and 5 look like before looking at a single brochure. Unknowns stay marked unknown, with the question to ask. Cost is calculated over a fixed period and shown beside the score.

What you get

What it produces.

  • →A one-sentence need statement and a list of pass or fail must-haves
  • →Weighted criteria totaling 100 with plain-language scoring rules
  • →A vendor grid with unknowns marked and the questions that resolve them
  • →Scores, total cost over 12 or 36 months, and a note on any surprising ranking
Who it's for
  • ✦Operations leads buying software or services several times a year
  • ✦Office managers asked to justify a supplier change
  • ✦Founders who want to choose without a week of spreadsheet work
What's included
  • →vendor-comparison.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →vendor-comparison-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'm the operations lead at a 40-person logistics company, and we need to replace our shipment tracking software before our current contract expires on March 31. I've shortlisted three vendors, which I'll call Vendor A, B, and C, with quotes between $18,000 and $31,000 a year. Before I see any more demos, my criteria are API access, support response time, and total three-year cost.

Fix the scorecard before the next demo. You have already done the hard part by naming your criteria before the sales material arrives, but three criteria with no weights and no scoring rules will still bend toward whichever vendor performs best in the room. Weight them to 100 now. For a logistics firm, I would put API access near 40, support response time near 30, and cost at 30, because tracking software that cannot feed your other systems costs you more than any quote gap. If your team will not touch the API for a year, shift weight to support. Whichever split you choose, commit to it in writing today.

Then add one pass or fail line: the contract must let you exit or scale seats without a penalty. With a March 31 expiry, a renewal with your current vendor is also a fourth option worth pricing, since it gives you leverage.

Define a 1, 3, and 5 for each criterion in observable terms. For support, a 5 might be a documented four-hour response on a weekend ticket. For API access, a 5 might be public documentation and a working sandbox you can test yourself.

On cost, compare three-year totals including setup, training, and per-seat add-ons, kept beside the score and not blended into it. A $18,000 quote can end up above a $31,000 one once fees land.

Next move: send all three vendors the same two written questions, support response time and API documentation access, before booking any demo.

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 produces a comparison table of whatever it knows about each vendor, which may be out of date. This one scores only the facts you supply, never guesses features or prices, and tests the ranking by finding which weight is driving it.

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.