Read like the buyer who's looking for a reason to say no.
The tool that stress-tests your proposal against what the buyer actually decides on: the unaddressed objection, the price that lands before the value does, and whoever else has to say yes after you leave the room.
Most proposal review is copyediting: tighten the language, check the logo placement. That's not what decides the deal. A buyer is running a specific, often unstated checklist: does this understand my real problem, is the price justified, what happens if it goes wrong, who else signs off.
This tool reads the proposal the way a skeptical buyer does, finds the specific place it fails to earn the next step, and tells you what to fix before you send it, not after you lose the deal wondering why.
Same proposal, read the way the buyer actually reads it.
Same document, same deal, run two ways.
A consultant is sending a $45k proposal for a six-month operations overhaul. The main contact is the VP of Operations; the CFO controls budget approval.
You ask Claude to review the proposal. You get feedback on clarity and tone, maybe a suggestion to tighten the executive summary.
The proposal reads better and still doesn't address the CFO's actual question, whether this pays for itself, because nothing in the review was checking for that specifically.
It reads the proposal against what this specific buyer decides on:
- →Price appears before any specific value is established: reorder, don't just add more justification after
- →No ROI framing anywhere, and a CFO sits in the approval chain
- →Ends with "happy to discuss further" instead of a specific next action
The rewrite adds the missing ROI framing, a one-paragraph executive summary the VP can forward to the CFO with no added context, and a specific proposed date for a decision call instead of an open-ended close.
The cold version made it read better. This made it answer the question that actually decides the deal.
- ✦Consultants and founders sending proposals for deals that matter
- ✦Anyone reusing a proposal template that converts inconsistently
- ✦Salespeople who suspect a lost deal died on an unaddressed objection, not price
- →proposal-review.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →proposal-review-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, Gemini, and the API
What it does with a real question.
I am about to send a $48,000 proposal to a retailer for a six-month website rebuild. It opens with our agency history, lists deliverables, shows a timeline and a fee table, and ends with our team bios. The buyer is a head of ecommerce who must get sign-off from a finance director. Please stress-test it.
The proposal is built for the wrong reader. It opens with your agency, then moves through deliverables, timeline, fees and bios. That is a seller's inventory, and it never shows the head of ecommerce their own problem. Nothing in it tells them what the current site is costing them, so by the time the $48,000 appears in the fee table, it has nothing to be weighed against. A number with no comparison feels arbitrary, and that is a structural flaw, not a pricing one.
The bigger danger is the finance director. Your buyer has to defend this spend to someone who will skim for one thing: what do we get back? A six-month rebuild with no stated outcome, no conversion or revenue framing, and no early checkpoint invites the obvious objection, "how do we know this pays for itself," and the document leaves it with no answer. If your contact forwards it without a note, it reads as a cost line with a team photo gallery.
Don't add more content to fix this. Reorder. Open with the problem in the buyer's own words, whatever they said about the current site's performance, then a conservative estimate of what it costs them, then the outcome, and only then the fee. Move agency history and bios to the back.
Next move: write a half-page executive summary framed as cost of inaction versus investment, with a defined 30-day checkpoint, that the head of ecommerce can forward to finance untouched.
The full Tool runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Tool 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 reviews a proposal for clarity and tone. This checks it against the buyer's actual decision criteria, finds the unaddressed objection and the price-ordering problem, and flags whether it gives a second decision-maker anything to defend the deal on their own.
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 Tool 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.
Proposal Review is a strategic document review tool. Not a guarantee of a specific close rate, which depends on relationship, timing, and fit as much as document quality.