Mobile Product Brief logo

Mobile Product Brief

Community
Xinvtech
mobile-product-brief

Turn an early mobile app idea, feature request, or product concept into an actionable, assumption-aware product brief for UX and UI design. Use when Codex needs to clarify target users, problem, jobs, value proposition, activation, core loop, MVP scope, constraints, risks, success signals, or handoff requirements before mobile flows, wireframes, UI, prototyping, or implementation.

Overview

PublisherXinvtech
Repositorymobile-design-os
Skill namemobile-product-brief
Stars
4
Forks
0
Bundled files
7
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Xinvtech on GitHub. Read the source before you install it.

Installation

Install the Mobile Product Brief AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Xinvtech/mobile-design-os/tree/main/skills/mobile-product-brief
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Xinvtech/mobile-design-os.git /tmp/mobile-design-os
mkdir -p .claude/skills
cp -r /tmp/mobile-design-os/skills/mobile-product-brief .claude/skills/mobile-product-brief
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile Product Brief in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mobile Product Brief on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mobile Product Brief is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Mobile Product Brief

Convert ambiguous product intent into a bounded design contract. Preserve uncertainty: separate user-provided facts, external evidence, assumptions, hypotheses, and product decisions.

Choose the brief mode

  • Create: produce a new brief from an idea or rough request.
  • Refine: resolve contradictions and missing decisions in an existing brief.
  • Feature: define a feature inside an existing product without rewriting the whole product strategy.

Do not perform competitive UI analysis in this skill. When references or screenshots drive the request, use analyze-mobile-ui first and cite its output as evidence.

Collect the minimum input

Establish when available:

  • Product idea or requested change.
  • Target users and situation.
  • Desired user outcome.
  • Target platforms and devices.
  • Business, legal, privacy, technical, time, or brand constraints.
  • Existing evidence, product context, and explicit non-goals.

Proceed with partial input when a reversible assumption can preserve momentum. Ask only when a missing choice would materially change the product, audience, safety boundary, or scope. Record every assumption that remains.

Follow the workflow

1. Build the source ledger

Assign stable IDs to user statements, existing documents, research, and prior analyses. Classify each important input as:

  • fact: directly stated by the user or supported by a cited source.
  • assumption: plausible but unverified condition used to proceed.
  • hypothesis: testable belief about user behavior or product value.
  • decision: chosen product direction and its owner or rationale.

Do not turn a user request into a market fact. Do not invent demand, demographics, conversion, retention, or competitor performance.

2. Frame the problem and audience

Write the problem as a user situation, friction, and consequence. Define a primary audience narrow enough to design for, then list secondary or excluded audiences only when useful.

Read references/product-framing.md for framing tests and anti-patterns.

3. Define jobs and outcomes

Capture functional, emotional, and social jobs only when relevant. Express desired outcomes without prescribing a feature. Distinguish the user's outcome from the buyer's or business outcome.

4. State the value proposition and principles

Write one falsifiable value proposition:

text
For [primary user] in [situation], [product] helps [progress] by [mechanism], unlike [current alternative], while [important boundary].

Add three to five design principles. Each principle must change a product or UX decision; reject slogans such as “simple,” “delightful,” or “seamless” without consequences.

5. Bound the product mechanism

Define:

  • Entry point and trigger.
  • Activation moment in observable user terms.
  • Core loop as ordered action and feedback.
  • Accumulated value and return trigger.
  • MVP capabilities required for that loop.
  • Explicit non-goals and later ideas.

Keep the MVP as the smallest coherent value loop, not the smallest screen count.

6. Specify constraints and trust boundaries

Cover applicable platform, accessibility, privacy, permission, sensitive-data, moderation, child-safety, financial, medical, legal, localization, connectivity, and operational constraints.

For iOS and Android, describe outcome parity separately from implementation parity. Do not assume widgets, background work, permissions, navigation, or system surfaces behave identically.

7. Record risks and hypotheses

For each material risk or hypothesis, state:

  • What is uncertain.
  • Why it matters.
  • Earliest low-cost validation method.
  • Decision or threshold the result will inform.

Prioritize tests that can invalidate the core value or safety model before visual refinement.

8. Define success and guardrails

Use observable success signals tied to user progress and product health. Mark numeric targets TBD unless supplied or derived from credible evidence. Include guardrail signals for harm, confusion, privacy, or exclusion where relevant.

Do not replace an outcome with vanity metrics such as downloads, page views, or raw session time.

9. Create the UX handoff

List:

  • Primary scenarios and actors.
  • Required entry, happy-path, empty, error, offline, permission, destructive, and recovery states.
  • Objects and their important lifecycle states.
  • Platform integrations and known differences.
  • Open decisions that block UX architecture.
  • Acceptance signals a reviewer can observe.

This handoff defines what mobile-ux-architect must solve without prescribing screen layouts.

10. Produce and validate the brief

When files are requested or this skill is part of a design workflow, create:

Run python3 scripts/validate_product_brief.py <path-to-product-brief.json> and fix every error before delivery. Treat warnings as review prompts.

When responding only in conversation, keep the same section order but avoid unnecessary files.

Enforce the output contract

Include, in order:

  1. Brief summary and confidence.
  2. Source ledger and assumptions.
  3. Problem, audience, and jobs.
  4. Value proposition and principles.
  5. Activation, core loop, MVP scope, and non-goals.
  6. Constraints and trust boundaries.
  7. Risks, hypotheses, and validation plan.
  8. Success signals and guardrails.
  9. UX handoff and open decisions.

Run the quality gate

Read references/product-brief-rubric.md and revise any blocking failure before completing.

Do not finish until:

  • Facts, assumptions, hypotheses, and decisions remain distinct.
  • The audience and situation are specific enough to design for.
  • Activation and the core loop are observable.
  • MVP scope contains a coherent value loop and explicit non-goals.
  • Sensitive data, permissions, failure, and platform constraints are addressed when relevant.
  • Success signals measure user progress and include applicable guardrails.
  • The UX handoff names required states without prematurely drawing screens.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mobile Product Brief AI skill do?

Turn an early mobile app idea, feature request, or product concept into an actionable, assumption-aware product brief for UX and UI design. Use when Codex needs to clarify target users, problem, jobs, value proposition, activation, core loop, MVP scope, constraints, risks, success signals, or handoff requirements before mobile flows, wireframes, UI, prototyping, or implementation.

Why use Mobile Product Brief on TypingMind?

Because you install it once and use it with any model. Mobile Product Brief is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mobile Product Brief in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Xinvtech/mobile-design-os/tree/main/skills/mobile-product-brief. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mobile Product Brief?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mobile Product Brief?

As many as you like. As long as a model supports skills, you can use Mobile Product Brief with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mobile Product Brief AI skill free?

Yes. It is published on GitHub by Xinvtech under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇