What do I need to use Schedule Monte Carlo?

The task list with three-point estimates; Simulation count and seed (optional).

Is Schedule Monte Carlo free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Schedule Monte Carlo

Q: How do I know the Schedule Monte Carlo output is good?

The skill verifies itself against its own quality checks: The simulation ran (output quoted); percentiles were never eyeballed; The deterministic-vs-P50 gap is stated explicitly and first — it is the finding most rooms need; Criticality is reported per task and drives the "watch these" recommendation; Pessimistic estimates were interrogated: if every task's pessimistic is likely×1.2, say the inputs are optimistic theatre and the output inherits it.

🟢 Production-Ready🕐 updated 2026-10-06 ✅ 4.8/5 🔷 SkillSpec L3 ⚙ ships an executable helper pm-calculators

Project completion as a distribution, not a date — Monte Carlo over the task graph. Use when a plan's finish date came from summing 'likely' estimates (it's wrong, mathematically), when leadership needs a commit date, or when you need to know which tasks actually control the timeline. Produces P10/P50/P90 completion, per-task criticality (how often each task sits on the critical path), and a real .xlsx — via the bundled zero-dependency simulator, deterministic with a seed.

▶ Run it free — no key needed 📝 Grade your existing draft 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“When will this project really finish?”“Leadership needs a commit date.”“Simulate our schedule instead of summing estimates.”“Which tasks actually drive the end date?”

What to give it

▸The task list with three-point estimates — per task: optimistic / likely / pessimistic (any consistent unit) and dependencies. Honest pessimistics are the whole game: "what if the API vendor ghosts us for two weeks" belongs in that number.

▸Simulation count and seed (optional) — (optional; defaults 5,000 and a fixed seed — results are reproducible).

✅ 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 ran (output quoted); percentiles were never eyeballed

✓The deterministic-vs-P50 gap is stated explicitly and first — it is the finding most rooms need

✓Criticality is reported per task and drives the "watch these" recommendation

✓Pessimistic estimates were interrogated: if every task's pessimistic is likely×1.2, say the inputs are optimistic theatre and the output inherits it

✓Internal-vs-external commitment dates are both named

⚠️ What it refuses to do

Do not present P50 as "the date" — the median loses half the time, by definition

Do not let uniform ±20% estimates pass silently — real uncertainty is lumpy, and flat inputs mean nobody thought about failure modes

Do not hide the deterministic number — showing plan-math next to real-math is how the method earns adoption

Do not add hidden buffers on top of P90 — the whole point is replacing padding with arithmetic

Do not simulate a 200-task plan at task granularity — roll up to workstreams; precision theatre at that scale is its own lie

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 -p pm-claude-skills pm-claude-skills-mcp

Start with

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="schedule-monte-carlo"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Schedule Monte Carlo is one of 1307 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog