landing-forecast

Name: landing-forecast
Availability: InStock
Author: Senzo

Forecast delivery dates via Monte Carlo simulations on historical throughput data.

Updated Mar 30, 2026

Search Tags:#linear #throughput #jira #delivery #forecast #project-management #monte-carlo

Ready to run

npx skills add https://github.com/SenzoStack/product-delivery-skills --skill landing-forecast

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: landing-forecast
Source: https://github.com/SenzoStack/product-delivery-skills/tree/main/skills/landing-forecast
Command: npx skills add https://github.com/SenzoStack/product-delivery-skills --skill landing-forecast

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Replaces gut-feel delivery estimates with probabilistic forecasts derived from historical throughput data, enabling data-driven planning.

Core Features & Use Cases

Monte Carlo-based delivery forecasting using historical sprint data
Tracker-agnostic analysis for Jira or Linear projects, epics, or releases
Generates a landing window with 50%, 70%, and 90% confidence dates to inform priorities and risk
Provides safeguards for sparse history and detects throughput variability to adjust confidence

Quick Start

Connect Jira or Linear, then ask for a landing forecast for your target epic or project.

Frequently Asked Questions about landing-forecast

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How does Monte Carlo simulation improve project delivery forecasting?▼

Monte Carlo delivery forecasting uses historical throughput samples to simulate probable outcomes, generating a landing window with 50%, 70%, and 90% confidence dates. This replaces gut-feel estimates with probabilistic, data-driven planning.

Can I forecast delivery dates for Jira or Linear epics?▼

Yes, delivery forecasting supports both Jira and Linear trackers. You can forecast landing dates for epics, projects, or releases by analyzing historical sprint throughput and remaining work.

What data do I need to generate a Monte Carlo delivery forecast?▼

Generating a delivery forecast requires historical throughput samples, remaining work counts, and sprint length. An optional start date can be provided, and built-in safeguards handle sparse historical data.

How do I forecast delivery when my team has sparse sprint history?▼

When sprint history is sparse, the forecast includes built-in safeguards and fallback paths. It detects throughput variability and adjusts confidence dates to provide a viable delivery landing window.

Does Monte Carlo forecasting adapt to changing project scope and carryover?▼

Yes, Monte Carlo forecasting adapts to varying remaining scope and carryover patterns. By simulating historical throughput against current workloads, it recalculates the landing window as project parameters change.