Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Calculate cash runway, burn, and the zero-cash date — and whether you're default alive or dead. Use when asked to work out runway, monthly burn, when the money runs out, or how much to raise/cut to reach a target. Produces a computed runway summary (net burn, months of runway, zero-cash date, default alive/dead) plus what it takes to extend it.
.claude/skills/mohitagw15856-runway-calculator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 108% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-01 | ✓→✗ | ▼ Worse | -71% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 167% | 0% |
For any company spending more than it makes, one number governs everything: how many months of cash are left. This skill computes net burn, runway, and the zero-cash date from your cash and P&L, judges whether you're default alive or dead (Paul Graham's test — would you reach profitability on current cash at current growth?), and shows the raise-or-cut needed to hit a target runway.
Ask for these only if they aren't already provided:
1. The numbers (computed via the helper):
| Metric | Value | |---|---| | Net monthly burn | | | Cash in bank | | | Runway (months) | | | Zero-cash date | | | Default alive? | yes / no |
2. Default alive or dead — on current cash and growth, do you reach profitability before the cash runs out? State it plainly; it's the question investors ask first.
3. To extend it — the concrete moves and their effect: cut $X/mo → +Y months; raise $Z → +W months; or the growth rate needed to turn default-alive. Show the trade-off.
4. Caveats — flag if burn is rising (these numbers assume flat burn), and the buffer to keep (don't plan to zero — most raises take months).
scripts/runway.py (stdlib only) computes runway and the zero-cash date:
bash# in.json: {"cash": 600000, "monthly_revenue": 40000, "monthly_expenses": 110000, "revenue_growth": 0.08} python3 scripts/runway.py in.json python3 scripts/runway.py in.json --json
Startup cash-management practice — net burn, runway, and "Default Alive or Dead" (Paul Graham, Y Combinator).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | pass→pass | 17,208 | 17,536 | +2% | 1 | 1 | 0% | 2,336 | 3,232 | +38% | 0 | 0 | — |
case-01 | pass→fail | 36,360 | 18,401 | -49% | 1 | 1 | 0% | 5,522 | 1,588 | -71% | 0 | 0 | — |
case-02 | fail→fail | 31,934 | 22,582 | -29% | 1 | 1 | 0% | 4,772 | 1,738 | -64% | 0 | 0 | — |
case-03 | fail→fail | 31,609 | 30,969 | -2% | 1 | 1 | 0% | 5,123 | 6,920 | +35% | 0 | 0 | — |
case-04 | pass→pass | 19,470 | 14,694 | -25% | 1 | 1 | 0% | 2,565 | 3,453 | +35% | 0 | 0 | — |
case-05 | pass→pass | 16,116 | 23,311 | +45% | 1 | 1 | 0% | 2,514 | 4,409 | +75% | 0 | 0 | — |
case-06 | pass→pass | 13,013 | 16,621 | +28% | 1 | 1 | 0% | 1,754 | 2,640 | +51% | 0 | 0 | — |
case-07 | pass→pass | 14,259 | 27,183 | +91% | 1 | 1 | 0% | 1,828 | 4,611 | +152% | 0 | 0 | — |
case-08 | pass→pass | 10,948 | 26,516 | +142% | 1 | 1 | 0% | 1,818 | 4,726 | +160% | 0 | 0 | — |
case-09 | pass→pass | 18,354 | 32,079 | +75% | 1 | 1 | 0% | 2,610 | 5,301 | +103% | 0 | 0 | — |
case-10 | pass→fail | 12,583 | 29,740 | +136% | 1 | 1 | 0% | 2,385 | 6,362 | +167% | 0 | 0 | — |
case-11 | pass→pass | 20,089 | 26,410 | +31% | 1 | 1 | 0% | 2,442 | 4,840 | +98% | 0 | 0 | — |
case-12 | fail→pass | 34,047 | 46,916 | +38% | 1 | 1 | 0% | 4,333 | 9,031 | +108% | 0 | 0 | — |
case-13 | pass→pass | 17,281 | 28,401 | +64% | 1 | 1 | 0% | 2,694 | 5,257 | +95% | 0 | 0 | — |
case-14 | fail→pass | 12,553 | 11,986 | -5% | 1 | 1 | 0% | 1,246 | 2,009 | +61% | 0 | 0 | — |
case-16 | pass→pass | 17,468 | 20,444 | +17% | 1 | 1 | 0% | 3,044 | 3,932 | +29% | 0 | 0 | — |
case-17 | fail→pass | 23,336 | 31,727 | +36% | 1 | 1 | 0% | 2,924 | 3,892 | +33% | 0 | 0 | — |
case-18 | pass→pass | 19,579 | 23,113 | +18% | 1 | 1 | 0% | 2,006 | 4,168 | +108% | 0 | 0 | — |
case-19 | pass→pass | 15,172 | 15,125 | -0% | 1 | 1 | 0% | 1,430 | 2,601 | +82% | 0 | 0 | — |
case-20 | pass→pass | 11,727 | 20,640 | +76% | 1 | 1 | 0% | 923 | 3,443 | +273% | 0 | 0 | — |
case-21 | pass→pass | 17,018 | 21,863 | +28% | 1 | 1 | 0% | 1,700 | 3,184 | +87% | 0 | 0 | — |
case-22 | fail→fail | 79,301 | 61,456 | -23% | 1 | 1 | 0% | 6,603 | 9,029 | +37% | 0 | 0 | — |
case-23 | pass→pass | 11,183 | 26,700 | +139% | 1 | 1 | 0% | 1,398 | 3,817 | +173% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 21 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +4 percentage points is the difference between those two pass rates over the 21 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.