gist

Structure product goals into ideas, steps, and tasks using the GIST evidence-guided planning framework.

Updated May 31, 2026
One-click install
npx skills add https://github.com/ithaloazevedo/pm-loadout --skill gist-ithaloazevedo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gist
Source: https://github.com/ithaloazevedo/pm-loadout/tree/main/.agents/skills/gist
Command: npx skills add https://github.com/ithaloazevedo/pm-loadout --skill gist-ithaloazevedo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Product teams often commit to feature roadmaps based on opinion rather than evidence, wasting effort on ideas that fail. This Skill replaces opinion-based roadmaps with Gilad's GIST framework (Goals, Ideas, Steps, Tasks), keeping planning outcome-focused and evidence-driven. ## Core Features & Use Cases - Goal Setting: Define up to 3 quarterly goals derived from North Star metrics or OKRs in the format "Improve [metric] from [current] to [target] by [date]". - Idea Bank with ICE Scoring: Generate and hold ideas loosely, scoring them with ICE where confidence maps to evidence levels (0.1 opinion to 0.9 launched), and rescore after every experiment. - Step Design with MoSCoW: Break top ideas into time-boxed evidence-building steps tagged Must/Should/Could/Won't, following a confidence ladder from assessment to launch. - Use Case: A PM with a retention goal uses this Skill to generate ten hypotheses, ICE-score them, design a small experiment for the top idea, and kill ideas when evidence turns negative instead of following a fixed feature roadmap. ## Quick Start Use the gist skill to turn my quarterly retention goal into an evidence-guided plan with scored ideas and experiment steps.

Frequently Asked Questions about gist

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

FAQPage Schema
How do I plan a product roadmap with the GIST framework?▼

GIST planning starts with up to 3 quarterly goals derived from North Star metrics or OKRs, then generates hypothetical ideas scored with ICE, designs small evidence-building steps for top ideas, and executes tasks only for the current step. Ideas are killed or pivoted when evidence is negative.

How does ICE scoring work in GIST planning?▼

ICE scores ideas on Impact, Confidence, and Ease, where confidence maps to evidence levels rather than gut feel: 0.1 means opinion only, 0.5 means data supports it, 0.7 means tested, and 0.9 means launched. Scores are updated after every experiment.

What is the difference between GIST and a feature roadmap?▼

A feature roadmap lists features with dates, while GIST treats goals as outcomes, ideas as hypotheses, and steps as experiments. If a GIST board looks like a feature list with dates, the framework is being applied incorrectly.

How does MoSCoW prioritization apply to GIST steps?▼

Each step is tagged Must, Should, Could, or Won't. When a delivery timebox is exceeded, scope is flexed by cutting Could and Won't items before compromising Must or Should items, keeping the timebox fixed.

When should I kill an idea in evidence-guided planning?▼

Kill or pivot an idea when a step produces negative evidence, regardless of sunk cost. After each step completes, ICE scores are updated, ideas are re-ranked, and those below the threshold are removed.