ui-pattern-library
Skill13 starsChanged 5 months agoMITView on GitHub
Picks UI patterns that address the mechanism of a solution hypothesis — for wireframing in /sketch. Use when sketching a solution, choosing between interface approaches, or when the user says "какой паттерн использовать", "what component to use", "UI pattern", "how should this screen work", "нарисуй экраны".
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ambiguity-resolverSkill
- challengeSkill
- deep-thinkSkill
- design-critique-templateSkill
- experiment-designSkill
- ingestSkill
- interview-analysisSkill
- multi-source-signal-synthesiserSkill
- next-advisorSkill
- pipeline-stepsSkill
- post-launch-reviewSkill
- problem-structuringSkill
- product-requirements-docSkill
- setup-initiativeSkill
- solution-scoringSkill
- strategic-narrative-generatorSkill
- system-design-docSkill
- technical-spec-documentSkill
- tracking-and-funnelsSkill
- user-persona-builderSkill
- user-story-generatorSkill
- user-testingSkill
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 14
Start from the hypothesis mechanism: Read the solution hypothesis (output/solution-hypotheses.md, linked ids in the registry): the …
- Distinctive: line 23
create/capture intent → save-for-later, wishlists, follow/subscribe, re-engagement entry points
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 Patterns for Solution Sketches
Serves the /sketch job: turn a solution hypothesis into concrete screens.
The question is never "which component is prettiest" — it's "which
pattern delivers the mechanism this hypothesis promises".
Method
- Start from the hypothesis mechanism. Read the solution hypothesis
(
output/solution-hypotheses.md, linked ids in the registry): the "Formula: if X then Y because Z" line names the mechanism. The pattern must implement Z — everything else is decoration. - Pick a pattern per mechanism, e.g.:
- reduce effort at a step → inline editing, smart defaults, one-tap confirm, progressive disclosure
- build trust → social proof blocks, transparent pricing breakdown, recognizable payment affordances
- create/capture intent → save-for-later, wishlists, follow/subscribe, re-engagement entry points
- explain something new → empty states that teach, contextual tooltips, first-run checklists (NOT tours nobody reads)
- surface at the right moment → contextual banners/sheets anchored to the user's current task, not global modals
- Respect platform conventions the segment already knows (CONTEXT.md: platform). A familiar mediocre pattern usually beats a novel one — the novelty tax is real and shows up in concept tests.
- Name the risk per screen — what the concept test (step 8.5) should probe: discoverability? comprehension? trust?
Output — into output/solution-sketch.md
Per screen: purpose (which hypothesis/mechanism) → chosen pattern + why → elements list top-to-bottom → user flow in/out → open risk for testing. Text wireframes are fine; Figma via MCP when connected.
Anti-patterns
- Design-system lectures (tokens, atomic design, component APIs) — that's the design team's domain, not a PM sketch.
- Patterns chosen by taste with no link to the hypothesis mechanism.
- Novel interactions where a platform convention exists — unless novelty IS the hypothesis.
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.

