ui-pro-max
Skill7 starsChanged 12 days agoMITView on GitHub
Refine complex product workflows with task-first states, platform conventions, accessible primitives, original mock UI examples and a controlled UI UX Pro Max handoff. Preserves an existing product's identity.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- claude-dashboardsSkill
- claude-motionSkill
- deep-researchSkill
- image-deep-researchSkill
- link-previewSkill
- remotion-videoSkill
- sound-designSkill
- terminal-uiSkill
- ultimate-frontend-skillsSkill
- visual-researchSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Use installed apple-design for platform conventions and the optional nextlevelbuilder/ui-ux-pro-max-skill pack for its domain.
- Distinctive: line 26
Ask about the user's role and primary task only if missing.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
UI Pro Max workflow layer
This is UFS's original workflow guide, not an Apple product or a fork of UI UX
Pro Max. Read the main UFS references/workflows.md. Existing product identity,
platform conventions and a supplied Claude Design canvas take precedence over
house defaults. Do not impose a universal premium template on every subject.
Use installed apple-design for platform conventions and the optional
nextlevelbuilder/ui-ux-pro-max-skill pack for its domain. Assign one owner to
each decision; do not load conflicting direction packs or change enabled
plugins automatically. packs --dry-run --only <id> previews the explicit
source install. Adding a catalog entry never installs a runtime or approves a
tool call.
Build the real happy path, then loading, empty, error, disabled, retry and
permission states. Mock data stays labeled mock; never invent social proof.
assets/workflow.html is an original local mock library for a searchable task
table, accessible native dialog and form validation. It makes no network calls
and does not implement a production backend. Serve it to inspect its behaviors.
Ask about the user's role and primary task only if missing. Present concrete working files, not design reasoning. Test the operation end to end, then hunt for keyboard traps, race conditions, long labels and clipped narrow screens.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

