improve-retention

Diagnose retention and activation problems using the Fogg Behavior Model B=MAP framework.

Updated Jul 8, 2026
One-click install
npx skills add https://github.com/HafidJoss/Lummy --skill improve-retention-hafidjoss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve-retention
Source: https://github.com/HafidJoss/Lummy/tree/main/agent/skills/improve-retention
Command: npx skills add https://github.com/HafidJoss/Lummy --skill improve-retention-hafidjoss

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Users sign up but fail to stick around: activation rates stall, onboarding creates friction, and cohort retention curves drop after day one. This Skill diagnoses why target behaviors are not happening and prescribes concrete fixes using behavior design. ## Core Features & Use Cases - B=MAP Diagnosis: Evaluate any product behavior against Motivation, Ability, and Prompt to find which element sits below the Action Line. - Ability Chain Friction Audits: Rate six simplicity factors (time, money, physical effort, mental effort, social deviance, non-routine) to locate the weakest link blocking activation. - Tiny Habits & Prompt Design: Build anchor-based habit recipes with Starter Steps and celebration, and design event-based prompts that avoid notification fatigue. - Use Case: A SaaS team sees day-7 drop-off. The Skill maps the metric to a B=MAP diagnosis (motivation wave receded, core action too hard), runs a friction audit on onboarding, and prescribes a Starter Step plus anchor-based prompts. ## Quick Start Ask the assistant to diagnose why new users are not completing onboarding and to recommend fixes using the B=MAP behavior model.

Frequently Asked Questions about improve-retention

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

FAQPage Schema
How do I diagnose why users drop off after signing up?

Map the failing behavior to B=MAP: check whether a prompt exists, then audit ability across six friction factors, and only then examine motivation. Day-1 drop-off usually indicates a prompt failure, while day-7 drop-off signals the behavior is too hard to survive the motivation trough.

What is the Fogg Behavior Model B=MAP?

B=MAP states that behavior occurs when Motivation, Ability, and a Prompt converge at the same moment. Behaviors above the Action Line succeed when prompted; below it, no prompt works. The reliable strategy is increasing ability rather than motivation.

How do I reduce onboarding friction in a SaaS product?

Run a friction audit rating six Ability Chain factors: time, money, physical effort, mental effort, social deviance, and non-routine. Fix the lowest-rated factor first, shrink the first action to a Starter Step completable in under 60 seconds, and use smart defaults.

When should I use behavior design versus the Hook Model?

Use B=MAP for diagnosis when a specific behavior is not happening and you need to find the failing element. Use the Hook Model for designing self-reinforcing habit loops with triggers, variable rewards, and investment. For intrinsic motivation analysis, use a self-determination framework.

Why do push notifications fail to re-engage users?

Notifications fail when sent to users below the Action Line who lack motivation or ability, making them spam. Switch from time-based schedules to event-based prompts tied to real user activity, and reduce frequency to prevent prompt fatigue.