Mobile Reference Research

Community

Xinvtech

mobile-reference-research

Find, inspect, compare, and shortlist native mobile product references for a new app or feature. Use when Codex needs evidence-backed reference research, a source matrix, competitor or pattern comparison, style-family inputs, or a clear borrow/transform/reject boundary before UX or UI design.

Overview

Publisher	Xinvtech
Repository	`mobile-design-os`
Skill name	`mobile-reference-research`
Stars	4
Forks	0
Bundled files	6
License	MIT
Links	Skill source Repository Homepage

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.
6 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 Reference Research AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Xinvtech/mobile-design-os/tree/main/skills/mobile-reference-research
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.

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-reference-research .claude/skills/mobile-reference-research

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile Reference Research 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 Reference Research 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 Reference Research 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 Reference Research

Build a small, traceable reference field that informs product and interface decisions without turning the target into a clone.

Choose the research mode

Discover: find a focused set of current, first-party mobile references from a product brief and search terms.
Compare: compare supplied references across mechanics, task flow, platform behavior, visual grammar, and risks.
Shortlist: reduce a larger board or source set to the references that should influence the next design stage.

Use analyze-mobile-ui after this Skill when screenshots or source products need detailed Design DNA extraction. Use mobile-ui-design when the user wants visual directions or rendered screens.

Establish the research question

Record the target product, primary user/job, platform, core task, usage frequency, and what decision the references must inform. Do not search for “beautiful apps” without a decision to make.

Build the evidence set

Prefer official App Store/Google Play pages, first-party product pages, platform surfaces, and supplied screenshots.
Record a stable RF ID, source URL or local path, platform, product state, access date, and evidence limitations for every source.
Keep native-mobile and platform-surface references at or above 60% of the set, including at least one real native-mobile product.
Inspect screenshots and boards directly; treat store marketing frames as presentation evidence, not proof of runtime behavior.
Mark current, versioned, or time-sensitive claims with their date. Use unknown when a source does not establish behavior.

Compare reusable qualities

For each selected reference, record:

One concrete product or interaction quality to borrow.
One visual or behavioral boundary not to copy.
The target-product decision it may inform.
Whether the transfer is transfer, transform, or reject.
Confidence and the evidence IDs supporting the conclusion.

Compare the same task across references whenever possible: entry, action, feedback, durable result, and recovery. Separate product mechanics from visual decoration.

Produce the research package

Create:

reference-research.md using assets/reference-research-template.md.
reference-research.json using assets/reference-research-template.json and references/reference-research-schema.md.

Run python3 scripts/validate_reference_research.py <path-to-reference-research.json> and fix every error. Treat warnings or evidence gaps as inputs to the next Skill, not as permission to invent behavior.

Enforce the output order

Research question and target context.
Evidence inventory and coverage gaps.
Reference comparison matrix.
Transfer, transform, and reject decisions.
Shortlist for UX, platform, and visual work.
Open questions, freshness, and confidence.

Do not finish with a gallery of names only. Every shortlisted reference must change a concrete design decision or be removed.

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 Reference Research AI skill do?

Why use Mobile Reference Research on TypingMind?

Because you install it once and use it with any model. Mobile Reference Research 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 Reference Research in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Xinvtech/mobile-design-os/tree/main/skills/mobile-reference-research. 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 Reference Research?

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 Reference Research?

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

Is the Mobile Reference Research 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

Gitcrawl

openclaw

OrganizationPopular

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Mobile Reference Research

Choose the research mode

Establish the research question

Build the evidence set

Compare reusable qualities

Produce the research package

Enforce the output order

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now