RM
Runway Monte Carlo
🔵 Stable🕐 updated 2026-07-06
🔷 SkillSpec L3
⚙ ships an executable helper
pm-calculators
Cash runway as a distribution, not a number — Monte Carlo simulated. Use when someone asks how long their cash lasts, when to start fundraising, or how burn/revenue volatility changes their runway; especially when the naive cash÷burn answer is driving a decision. Produces P10/P50/P90 runway, month-by-month death probabilities, and a real .xlsx with editable assumptions and a live naive-runway formula — via the bundled zero-dependency simulator.
What to give it
▸Cash today — and monthly gross burn — the two non-negotiables.
▸Monthly revenue (optional) — and monthly revenue growth (optional — zero for pre-revenue).
▸Volatility (optional) — (optional, defaults: burn σ 10%, growth σ 25% of the growth rate) — from the requester's history if they have it, defaults if not, stated either way.
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓The simulation actually ran (script output quoted) — percentiles were not eyeballed
✓P10 is the headline, with the raise-timing implication stated in months and dates
✓The naive cash÷burn number appears next to the distribution so the requester sees what volatility does to it
✓Assumptions and their sources (history vs default) are listed — defaults are labelled as defaults
✓Model limits stated: no fat tails, no seasonality, no modelled fundraise
⚠️ What it refuses to do
Do not report only the median — the median is the number that feels fine right up until the P10 path happens to you
Do not silently invent volatility — a made-up σ changes the answer more than the burn does; label defaults
Do not model the hoped-for fundraise inside the simulation — runway exists to time the raise, not assume it
Do not extend the horizon to make survival look better — report the horizon with the number
Do not present 56.8% survival as "about half" in one place and "likely fine" in another — one number, one interpretation, used consistently
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcpRelated skills
🔌 Embed this skill
Drop this on your blog, docs, or site — it renders a "Run this skill" card:
<div data-pm-skill="runway-monte-carlo"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>💬 Discussion
Runway Monte Carlo is one of 599 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog