skills/onboarding-designer/SKILL.md
Design the first-run experience (FRE) for mobile apps. Sequence permission requests, define feature discovery flows, plan empty states, and create retention-focused day 1-3 scenarios.
npx skillsauth add fatih-developer/fth-skills onboarding-designerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You only get one chance to make a first impression. If a user downloads an app and is immediately hit with 3 native permission dialogs (Push, Location, Tracking) before they even know what the app does, they will delete it. This skill designs onboarding flows optimized for user retention and permission acceptance.
Core principle: Show value before asking for trust.
1. Map the required app permissions and account creation needs
2. Design the "Aha!" Moment (Value Proposition)
3. Sequence the Soft & Hard Permission Prompts
4. Design the Empty States (Day 0)
5. Plan the Day 1 to Day 3 Retention Hooks
What does the app absolutely need to function?
Instead of a stationary 4-page swipe carousel that no one reads, design progressive disclosure.
Never trigger the OS-level permission dialog blindly.
The moment after onboarding, the app is usually empty (no friends, no data, no history).
Design the communication strategy to bring them back.
# 🚀 Onboarding & First-Run Experience Plan
## 🎯 The "Aha!" Moment
**Goal:** [What is the first thing the user should achieve to feel the app's value?]
**Time to Value:** [e.g., Under 60 seconds]
## 🚦 Registration Strategy
- **Flow:** [e.g., Deferred Login. Let users browse nearby restaurants without an account. Only ask for login when they click 'Order'.]
## 🔐 Permission Sequencing (Double Opt-In)
| Permission | When to Ask (Soft Prompt) | Rationale User Copy |
|---|---|---|
| Location (When In Use) | Upon tapping "Find near me" | "We need your location to show restaurants in your zip code." |
| Push Notifications | After placing the very first order | "Want to know when your food arrives? Enable notifications." |
## 🪹 Empty State Design
**Screen:** [e.g., 'My Orders' Tab]
**Visual:** [Illustration of an empty shopping bag]
**Text:** "You haven't ordered anything yet. Hungry?"
**Action (CTA):** [Button: "Browse Popular Places"]
## 🪝 Day 1-3 Retention Loop
- **Day 1 Trigger:** [If user generated an order: Do nothing. If not: "Still deciding? Here is a $5 promo code."]
- **Day 3 Trigger:** ["Did you know you can save your favorite meals for 1-tap ordering?"]
See references/EXAMPLES.md for a worked case.
tools
Create, optimize, critique, and programmatically structure prompts for AI systems. Use this skill whenever the user is designing or improving a static prompt, system prompt, coding prompt, agent prompt, workflow prompt, MCP-oriented prompt package, or an algorithmic prompt optimization pipeline. Also use it when the user asks to turn vague AI behavior into a precise instruction set, tool policy, agent spec, evaluation metric, or prompt architecture.
testing
Assumption-first architecture review skill to stress-test project plans and expose hidden risks.
testing
Enforce and manage DESIGN.md specifications, extract design systems from URLs, and combine design reasoning with token roles to prevent drift.
testing
Forces the agent to act with a Claude-like product mindset, prioritizing user journey, UX states, and visual quality before coding.