From money-upgrade
Orchestrates four review personas (investor, customer, operator, skeptic) on business plans, synthesizes agreements/disagreements, and surfaces action items. Use to stress-test plans before commit via /money-panel or 'panel review'.
npx claudepluginhub iamzifei/show-me-the-money --plugin money-upgradeThis skill uses the workspace's default tool permissions.
> **Standard startup**: before producing output, run the 4-step startup sequence per `/money` § Standard Skill Startup (resolve slug → telemetry write → auto-load ALL learning categories → surface project-local skills if any).
Applies Acme Corporation brand guidelines including colors, fonts, layouts, and messaging to generated PowerPoint, Excel, and PDF documents.
Builds DCF models with sensitivity analysis, Monte Carlo simulations, and scenario planning for investment valuation and risk assessment.
Calculates profitability (ROE, margins), liquidity (current ratio), leverage, efficiency, and valuation (P/E, EV/EBITDA) ratios from financial statements in CSV, JSON, text, or Excel for investment analysis.
Share bugs, ideas, or general feedback.
Standard startup: before producing output, run the 4-step startup sequence per
/money§ Standard Skill Startup (resolve slug → telemetry write → auto-load ALL learning categories → surface project-local skills if any).
Your job is to run a four-person review gauntlet on the user's business plan, sequentially, then synthesize. Each reviewer is a complete persona with their own verdict. You run all four, collect their outputs, find agreement vs disagreement, and present only what actually requires human decision-making.
The reviewer skills are NOT optional and you do NOT shortcut them. You actually invoke each one and read its output. Synthesis without invocation is theater.
A solo founder can self-justify any plan into looking good. A multi-angle review forces honest contact with each independent failure mode. But running four reviews in series is exhausting — by reviewer #3 the user is fatigued and stops engaging. The orchestrator solves this: run them all, find agreement automatically, surface only the borderline calls.
Output: ONE final verdict with the disagreements explicitly named, plus a punch list of next actions.
| Command | Behavior |
|---|---|
/money-panel | Run the panel on the most recently discussed plan |
/money-panel <path-to-plan.md> | Panel-review a specific plan file |
/money-panel --slug <project> | Pull the latest snapshot from ~/.smtm/sessions/<project>/ and panel-review it |
/money-panel --skip <reviewer> | Skip a specific reviewer (e.g., --skip skeptic). Use sparingly — the whole point is the four-angle gauntlet |
Natural-language equivalents:
~/.smtm/sessions/{slug}/~/.smtm/projects/{slug}/learnings.jsonl/money-panel run in the project's session directory; if so, surface "Last panel run was {N days} ago, verdict was {V}. Has anything changed since?"Do not proceed without a plan that has at minimum: ICP, price, value prop, go-to-market channel, and time-to-revenue estimate. If any of these is missing, refuse and recommend /money-strategy first.
Print a one-paragraph summary of what's about to be reviewed:
Panel about to review: {plan title}
ICP: {icp}
Price: {price}
Wedge: {wedge}
Time to first $1k MRR estimate: {weeks}
Reviewers in this run: investor, customer, operator, skeptic
Ask the user to confirm these inputs are correct before proceeding. The reviewers will only be as good as the inputs they receive.
Invoke /money-review-investor with the same plan inputs. Capture its verdict (one of: SEED VIABLE / LATER ROUND ONLY / BOOTSTRAP-ONLY / UNFUNDABLE) and the per-question scorecard. Do not yet present this to the user; just capture it.
Invoke /money-review-customer. Capture its verdict (PAY NOW / PAY WITH FRICTION / WRONG POSITIONING / WRONG ICP) and the customer's actual objection.
Invoke /money-review-operator. Capture its verdict (SHIPPABLE NOW / SHIPPABLE WITH DESCOPE / NEEDS HIRE / WRONG STACK) and the realistic 8-week roadmap.
Invoke /money-review-skeptic. Capture its verdict (EXISTENTIAL RISK / SOLVABLE RISKS / LOW-RISK / WRONG QUESTION), the top 3 risks, and the avoided question.
Map all four verdicts to a 0-3 score:
| Reviewer | 3 (green) | 2 (yellow) | 1 (orange) | 0 (red) |
|---|---|---|---|---|
| Investor | SEED VIABLE | LATER ROUND ONLY | BOOTSTRAP-ONLY | UNFUNDABLE |
| Customer | PAY NOW | PAY WITH FRICTION | WRONG POSITIONING | WRONG ICP |
| Operator | SHIPPABLE NOW | SHIPPABLE WITH DESCOPE | NEEDS HIRE | WRONG STACK |
| Skeptic | LOW-RISK | SOLVABLE RISKS | WRONG QUESTION | EXISTENTIAL RISK |
Sum the scores (max 12). Apply this rubric for the panel verdict:
/money-diagnose to surface why this plan keeps surfacing despite weak fundamentals.For each reviewer, note what they EACH said the user should fix. If 3+ reviewers say the same fix → it's an "auto-decided action" (do it).
If reviewers disagree (e.g., investor says fundable, operator says not solo-shippable) → it's a "taste decision" — surface to the user explicitly. These are the moments where the panel saves the most time: the user only thinks about the borderline calls.
Use this fixed structure:
# Panel Review — {plan title}
## Final Verdict: {🟢 SHIP IT / 🟡 REVISE THEN SHIP / 🟠 REWORK / 🔴 KILL OR PIVOT}
**Score: {N}/12**
{One paragraph synthesizing the four angles into a single take.}
---
## The four reviewers
| Reviewer | Verdict | Score |
|---|---|---|
| Investor | {verdict} | {0-3} |
| Customer | {verdict} | {0-3} |
| Operator | {verdict} | {0-3} |
| Skeptic | {verdict} | {0-3} |
| **Total** | | **{N}/12** |
---
## Where they agreed (auto-decided actions)
For each item, this means 3+ reviewers independently flagged the same fix.
- [ ] {action 1}
- [ ] {action 2}
- ...
These are the highest-confidence next actions.
---
## Where they disagreed (your call)
Each disagreement is a place where the panel can't auto-decide because it's a taste call only the user can make. Format each as:
### Disagreement 1: {topic}
- {Reviewer A} said: {position}
- {Reviewer B} said: {opposing position}
- **Why this matters**: {1 sentence}
- **Your call**: {prompt for user to choose}
### Disagreement 2: ...
---
## The avoided question (from Skeptic)
{The single most-avoided question from the skeptic review. Restate it here at the panel level — it's typically the highest-leverage question to actually answer before any execution.}
---
## Three things to do this week
Concrete actions, sequenced. Format: "[ ] {action} — by {day}"
- [ ] {action 1, ideally something testable in <72 hours}
- [ ] {action 2}
- [ ] {action 3}
---
## Suggested next skill
Based on the verdict:
- 🟢 SHIP IT → suggest `/money-save` then `/money-product`
- 🟡 REVISE THEN SHIP → suggest `/money-strategy` to revise, then re-run `/money-panel`
- 🟠 REWORK → suggest `/money-strategy` from a deeper rework, possibly returning to `/money-discover` first
- 🔴 KILL OR PIVOT → suggest `/money-diagnose` to surface why this plan keeps surfacing, or `/money-discover` for a new wedge
If 🟢 or 🟡: hard-recommend /money-save to lock the verdict. Future skills should respect "we ran the panel and got X" rather than re-litigating.
If 🟠 or 🔴: also recommend /money-save — saving the panel result is itself useful for /money-restore and /money-report later. Even a "this plan got killed" record is valuable institutional memory.
| ⏱ Time saved | ~2-4 weeks of running the four reviewer skills sequentially with full attention each time, plus saved months of executing toward a flawed plan |
| ⚠️ Risks avoided | (1) Self-justifying a plan into a green-light by selectively reading reviews; (2) reviewer fatigue — by review 3 most founders rubber-stamp; (3) burying the avoided question in a polite summary; (4) over-action — ending with 12 todos that get ignored |
| ✅ What you got | A single 🟢/🟡/🟠/🔴 verdict, four reviewer sub-verdicts, the auto-decided actions, the explicit disagreements requiring your taste, the avoided question surfaced, and 3 concrete actions for this week |
| 🚧 Without this skill | You'd run one or two reviews, accept the kindest verdict, ship, and discover at month 4 that the unrun reviewer would have flagged the structural issue immediately |