Userflow logo

Userflow

Community
jpoindexter
userflow

Use when the user invokes /userflow, asks which UX flow or layout patterns apply to what they're building, or describes an app, feature, or screen to build or review and wants the right proven flow guidance pulled in automatically. Also use at the start of any UI build when it's unclear which flow-* skills are relevant.

Overview

Publisherjpoindexter
Repositoryux-flow-skills
Skill nameuserflow
Stars
5
Forks
0
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Userflow 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/jpoindexter/ux-flow-skills/tree/main/skills/userflow
  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/jpoindexter/ux-flow-skills.git /tmp/ux-flow-skills
mkdir -p .claude/skills
cp -r /tmp/ux-flow-skills/skills/userflow .claude/skills/userflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Userflow 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 Userflow 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 Userflow 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.

Userflow Dispatcher

Overview

Entry point for the flow-* skill set. Reads what the user is building (from their words or the project itself), selects the most relevant flow skills, loads them, and applies their combined guidance — so the user never has to know skill names.

When to Use

  • /userflow invoked, with or without arguments
  • User describes something to build/review ("add billing", "new mobile app", "our signup is leaking users") and flow guidance would help
  • Starting any app surface when the relevant flow-* skills aren't obvious
  • NOT for pure visual styling (color, type, spacing) — no flow skill covers that
  • NOT when the user already named a specific flow-* skill — just invoke it directly

The Dispatch Process

  1. Determine scope. Use the argument text if given. If none, infer from conversation; if still unclear, inspect the project (routes, screens, package manifest) — don't interrogate the user. Ask at most one question, only if the answer changes skill selection.
  2. Select skills from the routing table below. Pick 1–4. Prefer the fewest that cover the task; a whole-app request gets the App Bundle, a single screen gets 1–2.
  3. Load them. Invoke each selected skill (Skill tool in Claude Code; read skills/<name>/SKILL.md in other harnesses). Never work from memory of a skill — load it.
  4. State the selection in one line ("Applying flow-checkout + flow-forms") and do the work under their combined rules. On conflicts, the more specific skill wins (flow-checkout beats flow-forms inside a payment step).
  5. Check the output against each loaded skill's Anti-Patterns section before presenting it.
  6. Generate the flow report. For any request that designs or reviews one or more flows, emit a self-contained flow-report.html the user can open — see Flow Report below. Skip only for trivial single-question lookups.

Flow Report

Fill report-template.html (in this skill's directory) — a dependency-free HTML file, one copy per run, written to the project root (or a path the user names):

  • Header: project, date, one-line scope, chips for each skill applied.
  • Per flow: numbered step cards (screen title, what's on it, primary action → destination, branch conditions), a screen-inventory table (purpose / primary action / empty-loading-error states), and an anti-pattern audit table with PASS/WARN/FAIL verdicts taken from the loaded skills' Anti-Patterns sections.
  • Footer sections: open questions / parked items. Duplicate the marked repeat-block per flow; delete unused placeholders — never ship {{…}} in output. Tell the user the file path when done.

Routing Table

Signal in task / projectSkills
Signup, login, SSO, passkeys, 2FA, password reset, "locked out", session expiryflow-auth
First-run, welcome, activation, setup wizard, "users sign up but don't stick"flow-onboarding (+ flow-empty-states)
Blank screen, no data yet, loading, skeletons, spinners, "feels slow"flow-empty-states
Push/notification/location/camera permission, priming, "everyone denies the prompt"flow-permissions
Cart, checkout, payment, buy, donate, order confirmation, abandonmentflow-checkout (+ flow-forms)
Pricing page, trial, subscription, upgrade/downgrade, cancel, paywall, dunningflow-paywall
Settings, preferences, profile, account, delete account, change email/password, data exportflow-settings (+ flow-forms)
Share, invite, collaborators, permissions on objects, "who can see this", presenceflow-sharing
Nav structure, menus, tab bar vs sidebar, breadcrumbs, "users get lost", cmd+Kflow-navigation
Overall layout, shell, panels, sidebar widths, responsive collapse, "layout feels off"flow-app-shell (+ flow-navigation)
Table, list, feed, grid of records, sorting, bulk actions, pagination vs infinite scrollflow-tables
Search box, filters, facets, typeahead, zero results, "can't find things"flow-search
Any form, wizard, multi-step, field validation, "form abandonment"flow-forms
Errors, failures, offline, retries, undo, destructive actions, 404/500, lost workflow-errors
AI chat, assistant, copilot, agent UI, streaming, tool-use display, citationsflow-ai-chat

Bundles (multi-skill requests)

Request shapeBundle
"New app" / greenfield productflow-app-shell, flow-navigation, flow-onboarding, flow-auth
"Add billing/monetization"flow-paywall, flow-checkout, flow-settings
"Admin panel / dashboard / back office"flow-app-shell, flow-tables, flow-search
"Make it collaborative / add teams"flow-sharing, flow-permissions, flow-settings
"UX audit / review the whole app"Walk the routing table against each existing surface; report per-skill anti-pattern hits
"Add an AI feature"flow-ai-chat, flow-empty-states, flow-errors

Quick Reference

SituationAction
/userflow build a pricing pageLoad flow-paywall, build under it
/userflow with no args, mid-projectInfer surface from recent work; inspect repo if needed
Task matches nothing in the tableSay so — don't force-fit a skill
More than 4 skills matchIt's a bundle request — use a bundle row or split the work

Anti-Patterns

MistakeFix
Summarizing skills from memory instead of loading themAlways load the selected SKILL.md — the value is in the specifics
Loading all 15 "to be safe"Max 4; selection is the job
Asking the user which skills they wantThey invoked the dispatcher precisely to avoid that — route, then state the pick
Applying flow guidance to a styling-only requestRedirect to design/styling skills; flows ≠ visuals

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 Userflow AI skill do?

Use when the user invokes /userflow, asks which UX flow or layout patterns apply to what they're building, or describes an app, feature, or screen to build or review and wants the right proven flow guidance pulled in automatically. Also use at the start of any UI build when it's unclear which flow-* skills are relevant.

Why use Userflow on TypingMind?

Because you install it once and use it with any model. Userflow 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 Userflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jpoindexter/ux-flow-skills/tree/main/skills/userflow. 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 Userflow?

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 Userflow?

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

Is the Userflow AI skill free?

Yes. It is published on GitHub by jpoindexter 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 👇