ai-ui-anti-patterns
Skill4 starsChanged 3 months agoApache-2.0View on GitHub
The 10 most common AI UI failures, ranked by severity, with root cause analysis and concrete fixes. Covers the chatbot trap, dashboard fatigue, perpetual shimmer, hidden AI activity, read-only output, missing kill switches, and more. Use when debugging AI interface problems, reviewing an AI app for UX issues, or preventing common mistakes in AI-native design. Triggers on: "AI UI mistakes", "common AI UI failures", "anti-patterns", "what not to do", "AI UI pitfalls", "fix this AI interface".
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
- Distinctive: line 15
No way to stop AI
- Very specific: line 39
If removing chat still lets users finish ~80% of jobs via buttons and direct edit, chat must not be the primary UI.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
AI UI Anti-Patterns
The 10 most common AI-native UI failures, ranked by severity. Depth (symptoms, fixes, chatbot decision tree) lives in references/.
Top 10 (severity)
- User can't tell if AI is working
- AI output is read-only
- No way to stop AI
- Dashboard overwhelms the user
- AI failures are hidden
- Chat is the only interface
- No confidence indication
- Perpetual loading spinners
- Inconsistent AI behavior
- App breaks without AI
Ship checklist
- Ambient working indicator (not spinner-only)
- Inline edit of AI output
- Kill switch within 2 taps
- Output ≥80% of working canvas; one primary CTA
- Errors visible with recovery path
- Common actions are buttons; chat is overflow
- Confidence where decisions matter
- Stream / skeleton instead of long blank waits
- Consistent output shape or explained variation
- Manual fallback when AI is unavailable
Chatbot trap (one-liner)
If removing chat still lets users finish ~80% of jobs via buttons and direct edit, chat must not be the primary UI. Full tree: references/chatbot-trap-decision-tree.md.
Reference Map
references/top-failures.md— each failure with symptoms, fixes, related skillsreferences/chatbot-trap-decision-tree.md— when chat is wrong vs earned
Related Skills
- For calm technology principles → use
calm-technology-ui - For Nielsen/Norman audit → use
ai-ui-heuristics - For generative UI patterns → use
ai-native-ui-design - For multi-agent UI → use
agentic-ui-patterns - For failure/empty messaging → use
error-empty-states - For structured jobs → use
form-ux
In this repository80 other files it gives its agents.
- a11y-accessibility-designSkill
- agentic-ui-patternsSkill
- ai-native-ui-designSkill
- ai-ui-heuristicsSkill
- calm-technology-uiSkill
- conversion-growth-designSkill
- cross-platform-designSkill
- dark-mode-designSkill
- data-visualizationSkill
- design-systemsSkill
- design-thinking-processSkill
- error-empty-statesSkill
- ethical-design-patternsSkill
- form-uxSkill
- information-architectureSkill
- interaction-design-patternsSkill
- internationalization-uiSkill
- mobile-touch-designSkill
- modal-classes-lifecycleSkill
- modal-container-imagesSkill
- modal-dicts-queuesSkill
- modal-endpointsSkill
- modal-fundamentalsSkill
- modal-gpu-computeSkill
- modal-networkingSkill
- modal-observabilitySkill
- modal-parallel-executionSkill
- modal-sandboxesSkill
- modal-scaling-performanceSkill
- modal-schedulingSkill
- modal-secretsSkill
- modal-serversSkill
- modal-storageSkill
- modal-web-servingSkill
- modal-workspace-adminSkill
- motion-design-principlesSkill
- notifications-permissionsSkill
- onboarding-uxSkill
- rust-api-designSkill
- rust-async-programmingSkill
- rust-cargo-masterySkill
- rust-cli-applicationsSkill
- rust-clippy-lintsSkill
- rust-closures-iteratorsSkill
- rust-compiler-internalsSkill
- rust-concurrencySkill
- rust-design-patternsSkill
- rust-editionsSkill
- rust-embeddedSkill
- rust-error-handlingSkill
- rust-game-developmentSkill
- rust-lifetimes-borrowingSkill
- rust-macrosSkill
- rust-performanceSkill
- rust-rustdocSkill
- rust-rustup-toolchainSkill
- rust-smart-pointersSkill
- rust-testing-benchmarkingSkill
- rust-type-systemSkill
- rust-unsafe-ffiSkill
- The first 60 shown.
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.