Read it the way the director who asks the uncomfortable question will.
The tool that checks your board pack's narrative against its numbers, finds what's missing, and names the three hardest questions a skeptical director is going to ask before they ask them live.
A board pack written by the team it's about inherits that team's blind spots: the improving metric gets a chart, the declining one gets a softer caption. An experienced board isn't fooled by this, and being caught costs credibility.
This tool reads the pack the way a skeptical director does: checking the narrative against the actual numbers, finding what's missing, and naming the pointed questions before the meeting does it for you.
The pack, read the way the hardest director will.
Same pack, same board, run two ways.
A Series B founder is preparing a Q3 board pack. Revenue growth slowed from 22% to 8% quarter over quarter, and churn ticked up slightly.
You ask Claude to review the pack for clarity. You get feedback on slide structure and formatting, maybe a note to tighten the executive summary.
The deck looks cleaner and still frames the growth slowdown as "continued solid momentum," which an attentive board will catch immediately from the chart regardless of the caption.
It checks the narrative against the numbers and finds what's missing:
- →Growth narrative doesn't acknowledge a deceleration to a third of the prior quarter's rate
- →No cohort retention data included, despite a churn uptick that begs the question
- →The budget ask appears only on the final slide with no earlier framing
The review names the three hardest likely questions, what changed, is churn concentrated anywhere, what's the plan and by when, and flags that none currently has a prepared answer in the pack.
The cold version tightened the slides. This found the three questions that were going to derail the meeting.
- ✦Founders and executives preparing a board pack
- ✦Directors preparing questions ahead of a board meeting
- ✦Anyone whose board packs have gotten routine and may be getting a softer read than they deserve
- →board-pack-review.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →board-pack-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.
Here is the draft board pack for our quarterly meeting: a 4-page CEO summary, a financial dashboard showing revenue 8% under budget, a product roadmap update, a hiring plan, and an appendix on risks. One director has already questioned our cash forecast twice. I want to read it as that director would.
Read it as the director who's asked twice. That director has already told you what they're looking for, and a pack that doesn't answer the cash question up front will read as evasive. The most likely problem is structural: the 8% revenue miss sits in a dashboard, the CEO summary probably softens it, and the risks are in an appendix. A skeptical director will read the summary, flip to the dashboard, and check whether the language matches the number. If the summary says "slightly behind plan" or leans on the roadmap's momentum, you've lost credibility before page five.
The bigger exposure is what's absent. Nothing you've described connects the revenue shortfall to cash. A director who doubted your forecast twice will immediately ask what an 8% miss does to runway, which assumptions changed since the last forecast, and why this one should be trusted. If the pack leaves that to be discovered live, silence on the topic will be read as more suspicious than a bad number shown plainly.
Also, the hiring plan will be read as a cash question first. If it assumes the original budget, expect it to be challenged.
Next move: add a one page cash bridge right after the CEO summary. Show the revenue miss, its effect on runway, the forecast assumptions
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 board pack for clarity and formatting. This checks the narrative against the actual numbers, finds what an experienced board would expect to see that's missing, and names the three hardest questions likely to come up live, with a note on whether the pack currently has an answer.
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.
Board Pack Review is a document and narrative preparation tool. It is not financial or investment advice, and it does not evaluate the underlying business or investment decision itself.