Mohit Aggarwal Personal Board of Directors Skill
Good decisions survive five different kinds of scrutiny; most decisions get one (your own, on a good day). This skill convenes a standing board of five archetypes who each write a short memo, disagree where they honestly would, and vote — with the decision rule stated before the count.
What This Skill Produces
- Five advisor memos (~150 words each) in five genuinely different voices
- The disagreement map — where they split, and what fact would resolve each split
- The vote — with the decision rule declared first and what evidence would flip it
- The one question to answer before committing
Required Inputs
Ask for these if not provided:
- The decision — as a yes/no or A-vs-B; if it arrives vague ("should I do something about X?"), sharpen it into a decidable sentence first and confirm
- Stakes and reversibility — what's bet, and whether it can be undone
- Constraints — money, time, obligations, runway
- What the user is secretly hoping the answer is (optional — the board should know the bias it's correcting)
Framework: The Five Chairs
| Advisor | Lens | Their memo must contain | Their known bias (they self-disclose it) |
|---|---|---|---|
| The Operator | Can this actually be executed, by you, now? | The first 2 weeks, resourced honestly | Overweights logistics, underweights vision |
| The Skeptic | Why this fails | The single most likely kill condition, dated | Kills some winners |
| The CFO | Unit economics of the choice | Real numbers from the input, or named missing ones | Discounts the unquantifiable |
| The Coach | Energy, growth, season of life | What this costs the person, not the plan | Overweights feelings |
| The Customer | Would the intended beneficiary care? | The beneficiary's likely verdict, in their words | Ignores the founder's needs |
Decision rules (pick per stakes, state before voting): reversible + low stakes → simple majority · irreversible or high stakes → 4-of-5 supermajority · any advisor invokes a "stop-the-line" fact (a named, checkable disqualifier) → resolve that fact first, no vote.
Output Format
Board Session: [the decision, one sentence]
Memos
[Five memos, each headed by the advisor, each ending "Vote: FOR / AGAINST / ABSTAIN — flips if: [named evidence]"]
Disagreement Map
| Split | Advisors | The crux | What fact resolves it |
|---|
The Vote
Decision rule: [stated + why] · Count: [n–n] · Board recommendation: … The one question to resolve first: [the highest-leverage unknown, and how to answer it cheaply this week]
Quality Checks
- The five voices are distinguishable blind — cover the names and you can still tell who's who
- At least two advisors disagree, and the crux of the disagreement is named
- Every vote line names the evidence that would flip it
- The decision rule was stated before the count and matches the stakes
- The one question is answerable cheaply and quickly, not "do more research"
Anti-Patterns
- Do not let the advisors agree — forced consensus is the failure mode this skill exists to prevent
- Do not give all five the same voice with different hats — the CFO writes in numbers, the Coach doesn't
- Do not vote without naming what would flip each vote — an unflippable vote is a prejudice
- Do not let the board answer a vague question — sharpen it to decidable first
- Do not hide the recommendation in balance — the board exists to conclude, and the user can overrule it