Agent skill

Runway Monte Carlo

by mohitagw15856 in mohitagw15856/pm-claude-skills

Cash runway as a distribution, not a number — Monte Carlo simulated.

MITAuto-check passedBusiness, Finance & HR

Install Runway Monte Carlo

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill runway-monte-carlo -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills runway-monte-carlo --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/runway-monte-carlo .claude/skills/runway-monte-carlo && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
runway-monte-carlo
GitHub stars
1.4k
Token cost
~973 tokens
SKILL.md length
474 words
Files
2 (incl. scripts)
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Cash runway as a distribution, not a number — Monte Carlo simulated.

  • Works in 4 steps: The distribution — P10 (unlucky), P50… → The death curve — % of simulated paths… → The decision line — the one that… → …
  • Someone asks how long their cash lasts
  • SKILL.md covers Required Inputs, Output Format, Programmatic Helper and Quality Checks, plus 2 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Runway Monte Carlo is an agent skill from mohitagw15856/pm-claude-skills. 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.

Its SKILL.md is about 970 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/runway_sim.py`).

It sits in Business, Finance & HR, covering Excel spreadsheets and Fundraising and pitch decks. It works with Microsoft Excel. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Someone asks how long their cash lasts
  • To start fundraising
  • How burn/revenue volatility changes their runway
  • Especially when the naive cash÷burn answer is driving a decision

Example prompts

  • “/runway-monte-carlo”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. The distribution — P10 (unlucky), P50 (median), P90 (lucky) runway in months, the survival probability at the horizon, and the naive…
  2. The death curve — % of simulated paths out of cash by each month; the months where it steepens are the danger window.
  3. The decision line — the one that matters: raise while P10 exceeds your fundraise time (6-9 months for most), not P50. Say explicitly when…
  4. Stated model limits — normal noise (no fat tails), no seasonality, no fundraise events modelled. If their reality has lumpy enterprise…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Runway Monte Carlo loads about 973 tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 474 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~973

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 474 words, ~973 tokens.

Download SKILL.mdSave it as .claude/skills/runway-monte-carlo/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
runway-monte-carlo
description
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.

Runway Monte Carlo

"Cash divided by burn" is one path through a fan of thousands. Real burn wobbles, revenue growth compounds or doesn't, and the difference between the median path and the unlucky-decile path is the difference between a calm raise and a bridge round. This skill runs the simulation — thousands of paths, actual random draws by the bundled script — and reports runway the way it actually behaves: as percentiles.

Required Inputs

  • Cash today and monthly gross burn — the two non-negotiables.
  • Monthly revenue and monthly revenue growth (optional — zero for pre-revenue).
  • Volatility (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.
  • Horizon (default 36 months) and simulation count (default 5,000).

Output Format

  1. The distribution — P10 (unlucky), P50 (median), P90 (lucky) runway in months, the survival probability at the horizon, and the naive cash÷net-burn number alongside for contrast.
  2. The death curve — % of simulated paths out of cash by each month; the months where it steepens are the danger window.
  3. The decision line — the one that matters: raise while P10 exceeds your fundraise time (6-9 months for most), not P50. Say explicitly when the P10 clock crosses that line.
  4. Stated model limits — normal noise (no fat tails), no seasonality, no fundraise events modelled. If their reality has lumpy enterprise revenue, say the P10 is optimistic.

Programmatic Helper

This skill ships scripts/runway_sim.py — zero dependencies, deterministic with --seed:

bash
python3 scripts/runway_sim.py run runway.xlsx --cash 2400000 --burn 210000 --burn-vol 0.12 \
    --revenue 60000 --rev-growth 0.05 --rev-vol 0.3

It prints the percentiles (naive=16.0mo P10=19 P50=>36 P90=>36 survive(36mo)=56.8%) and writes an .xlsx with an Assumptions sheet (editable cash/burn/revenue cells, live naive-runway formula) and a Death curve sheet. Requires a code-execution environment.

Show full SKILL.md (197 more words)Show less

Quality Checks

  • 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

Anti-Patterns

  • 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

Example Trigger Phrases

  • "How long does our cash really last?"
  • "When should we start fundraising?"
  • "Simulate our runway with volatile revenue."
  • "Give me runway as a range, not one number."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/runway-monte-carlo of mohitagw15856/pm-claude-skills.

  • SKILL.md
  • scripts/runway_sim.py

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Runway Monte Carlo next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Runway Monte Carlo compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Runway Monte Carlo this skillmohitagw15856/pm-claude-skills1.4k—~973Automated safety check: PassMIT
Datapack Builderw95/awesome-claude-corporate-skills2441 repos~6kAutomated safety check: PassMIT
Cn Ib Diligence WorkpaperQiushenZou/cn-investment-banking-skills102—~1.4kAutomated safety check: PassApache-2.0
Officecli Commonly TemplatesTeam-Commonly/commonly1.4k—~1.7kAutomated safety check: PassApache-2.0
Investment Due Diligence Reportxiaoyuge886/aigc198—~2.1kAutomated safety check: PassMIT
Mx Finance Datahiboys/ExploreFinance365—~518Automated safety check: PassNone

Similar skills

  • Datapack Builder

    w95/awesome-claude-corporate-skills

    Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers.

    244 GitHub starsUsed in 1 repo~6k tokens
    Business, Finance & HRAuto-check passed
  • Cn Ib Diligence Workpaper

    QiushenZou/cn-investment-banking-skills

    Structure Chinese investment-banking due-diligence materials into traceable schedules, testing workpapers, exception logs, and closure records.

    102 GitHub stars~1.4k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Officecli Commonly Templates

    Team-Commonly/commonly

    A skill your agent uses when producing a polished, Commonly-branded deliverable (.docx brief / memo, .xlsx data matrix, .pptx deck) and you do not have specific brand guidance from the user.

    1.4k GitHub stars~1.7k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • 投资尽调报告专业生成工具。当用户需要撰写投资尽调报告、尽职调查报告、投资分析报告时使用此skill。支持处理Excel财务数据、PDF文档等多种格式数据源,自动生成包含执行摘要、业务分析、财务分析、风险提示、投资建议等核心章节的专业报告。无论用户明确要求"写报告"还是提到"分析投资标的"、"评估项目"、"做DD"等相关需求时,都应使用此skill。

    198 GitHub stars~2.1k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed
  • Mx Finance Data

    hiboys/ExploreFinance

    基于东方财富数据库,支持自然语言查询金融数据,覆盖A港美、基金、债券等多种资产,含实时行情、公司信息、估值、财务报表等,可用于投资研究、交易复盘、市场监控、行业分析、信用研究、财报审计、资产配置等场景,适配机构与个人多元需求。返回结果包含数据说明及 xlsx 文件。Natural language query for financial data across all markets…

    365 GitHub stars~518 tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Excel Dcf Modeler

    jeremylongshore/tons-of-skills-marketplace

    Build discounted cash flow (DCF) valuation models in Excel. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~593 tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Runway Monte Carlo

What does Runway Monte Carlo do?

Cash runway as a distribution, not a number — Monte Carlo simulated. Runway Monte Carlo is an agent skill from mohitagw15856/pm-claude-skills. Cash runway as a distribution, not a number — Monte Carlo simulated.

When should I use Runway Monte Carlo?

Runway Monte Carlo fits situations like: someone asks how long their cash lasts; to start fundraising; how burn/revenue volatility changes their runway; especially when the naive cash÷burn answer is driving a decision.

How do I install Runway Monte Carlo in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill runway-monte-carlo -a claude-code`. Or copy the skill folder (skills/runway-monte-carlo in mohitagw15856/pm-claude-skills) into .claude/skills/runway-monte-carlo in your project. Claude Code loads it when a task matches its description.

How do I install Runway Monte Carlo in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill runway-monte-carlo -a codex`. Or copy the skill folder (skills/runway-monte-carlo in mohitagw15856/pm-claude-skills) into .agents/skills/runway-monte-carlo in your project. Codex loads it when a task matches its description.

Can I use Runway Monte Carlo in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill runway-monte-carlo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/runway-monte-carlo, .gemini/skills/runway-monte-carlo, .github/skills/runway-monte-carlo and .opencode/skills/runway-monte-carlo in your project.

What does Runway Monte Carlo need to run?

Going by SKILL.md and its folder, Runway Monte Carlo needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Runway Monte Carlo access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Runway Monte Carlo safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Runway Monte Carlo use?

Runway Monte Carlo is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Runway Monte Carlo use?

About 973 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Runway Monte Carlo?

Skills that share tags, products or a category with Runway Monte Carlo: Datapack Builder (w95/awesome-claude-corporate-skills, 244 stars), Cn Ib Diligence Workpaper (QiushenZou/cn-investment-banking-skills, 102 stars), Officecli Commonly Templates (Team-Commonly/commonly, 1.4k stars) and Investment Due Diligence Report (xiaoyuge886/aigc, 198 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Runway Monte Carlo?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.