ux-ui-design-assessment
Skill4 starsChanged 2 months agoMITView on GitHub
Analyze and document the UX/UI of a project against the full UX/UI body of knowledge, or design the UX/UI for a new project from scratch. Use when the user wants to know "how is this project's UX/UI", to audit/review/evaluate an existing interface, to produce a UX/UI assessment report, or to design UX/UI for a new product (personas, empathy maps, information architecture, wireframe/prototype plan, color and typography, responsive strategy, moodboard, usability test plan). Triggers include "วิเคราะห์ UX/UI", "สแกน UI ของโปรเจกต์", "ออกแบบ UX/UI", "เขียนเอกสาร UX/UI", "audit the UI", "evaluate UX", "UX/UI ของโปรเจกต์นี้เป็นอย่างไร", "design the UX for a new app". Produces a written file (UX-UI-ASSESSMENT.md or UX-UI-DESIGN-DOC.md). This skill documents and plans; it hands code implementation to the companion `ui-design-engineering` skill.
In this repository58 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/project-docs-prep/templates/AGENTS.mdAGENTS.md
- skills/project-docs-prep/templates/CLAUDE.mdCLAUDE.md
- deep-planningSkill
- deep-planningSkill
- deprecatedSkill
- architecture-reviewSkill
- code-reviewSkill
- diagnoseSkill
- tddSkill
- ui-design-engineeringSkill
- in-progressSkill
- mcp-tool-managementSkill
- skill-managementSkill
- obsidian-canvasSkill
- obsidian-markdownSkill
- obsidian-notion-bridgeSkill
- obsidian-vault-workflowSkill
- boomz-preferencesSkill
- personal-agent-workflowSkill
- personalSkill
- automation-designSkill
- grill-with-docsSkill
- handoffSkill
- inbox-meeting-triageSkill
- markdown-reportSkill
- prompt-improvementSkill
- project-docs-prepSkill
- claim-citation-checkSkill
- daily-news-reportSkill
- github-skill-researchSkill
- project-discoverySkill
- repo-tourSkill
- research-methodologySkill
- seo-website-evaluatorSkill
- thaiSkill
- thai-addressSkill
- thai-customer-serviceSkill
- thai-date-formatSkill
- thai-festival-cardSkill
- thai-government-formSkill
- thai-id-validateSkill
- thai-invoiceSkill
- thai-pdpaSkill
- thai-resumeSkill
- thai-social-captionSkill
- thai-text-processingSkill
- thai-translateSkill
- backtest-expertSkill
- dividend-value-screenerSkill
- drawdown-circuit-breakerSkill
- exposure-coachSkill
- market-breadth-analyzerSkill
- portfolio-managerSkill
- position-sizerSkill
- tradingSkill
- trader-memory-coreSkill
- uptrend-analyzerSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
If unsure, ask the user one question: "Is there an existing interface to evaluate (Audit), or are we designing UX/UI for something new …
- Distinctive: line 36
Follow references/design-workflow.md for the full loop.
- Very specific: line 53
After Audit mode, the prioritized fix list is handed to ui-design-engineering, which implements and browser-validates the changes.
- Very specific: line 57
Evidence, not opinion: Every finding cites a file:line reference or an observed browser behavior on the real route.
- Distinctive: line 59
No emoji in output files: Use named icons (e.g., Lucide) or named SVGs for any visual indicator.
- Distinctive: line 62
Honesty: If a dimension has no supported findings after falsification, say so.
≈ “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
UX/UI Design Assessment
Produce an evidence-based UX/UI document for a project — either by auditing an existing interface or by designing the UX/UI for a new one. The methodology is the ten-topic UX/UI body of knowledge in references/ux-ui-knowledge.md.
This skill documents and plans. It does not implement UI code — that is the job of the companion ui-design-engineering skill.
Choose The Mode
- Audit mode — evaluate an existing project's interface against the ten UX/UI dimensions; produce a report file describing how the project's UX/UI currently is.
- Design mode — design the UX/UI for a new (or redesigned) product; produce a design document.
If unsure, ask the user one question: "Is there an existing interface to evaluate (Audit), or are we designing UX/UI for something new (Design)?"
Knowledge Base (read on demand)
- references/ux-ui-knowledge.md — the ten topics: UX/UI foundations, Design Thinking, user research (persona/empathy map/affinity), information architecture, wireframe/mockup/prototype, visual hierarchy, color and typography, responsive design, moodboard, usability testing.
- references/audit-rubric.md — Audit mode: ten-dimension rubric, severity scale, evidence rules.
- references/design-workflow.md — Design mode: the 7-step loop and sub-templates (persona card, empathy map, problem statement, user flow, wireframe checklist, moodboard).
- references/external-techniques.md and references/credits.md — what was adapted from external skills (design-lab, ui-ux-pro-max, improve-ui, rams, web-design-guidelines).
Audit Mode Workflow
- Inspect the project — read the framework, routes, components, design tokens, and any
DESIGN.md. Open the real pages in a browser when possible. - Identify user and task — name the primary user, their immediate goal, the environment, and how often the workflow runs.
- Evaluate against the ten dimensions — for each, find evidence and apply the rubric. Never guess; every candidate must pass the three-part proof gate (contract + runtime + correction) and survive falsification.
- Rate and prioritize — assign a rating (Strong/Adequate/Weak/Missing/N/A) and a severity (P0-P3) to each finding. If nothing survives falsification for a dimension, write "No supported findings".
- Write the report — fill templates/UX-UI-ASSESSMENT.md: overall summary, dimension table, findings by severity, responsive/accessibility/usability sections, prioritized fix list.
Design Mode Workflow
Follow references/design-workflow.md for the full loop. Summary:
- Empathize — interview with open-ended questions (never leading).
- Define — write a problem statement and top pain points.
- Ideate — generate meaningfully distinct variants.
- Information architecture + wireframe plan — sitemap, user flow, taxonomy, wireframe structure before any styling.
- Visual design — color, typography (max 2 fonts), hierarchy, moodboard.
- Prototype + usability test plan — clickable flow, full component states, open-ended test tasks.
- Finalize — write templates/UX-UI-DESIGN-DOC.md.
Output Files
- Audit mode ->
UX-UI-ASSESSMENT.md(place at repo root or underdocs/; do not overwrite existing project files unless asked). - Design mode ->
UX-UI-DESIGN-DOC.md.
Companion Skill
After Audit mode, the prioritized fix list is handed to ui-design-engineering, which implements and browser-validates the changes. This keeps assessment and implementation separate: this skill stays evidence-based and read-only toward code.
Guardrails
- Evidence, not opinion. Every finding cites a
file:linereference or an observed browser behavior on the real route. If you cannot prove it, do not report it. - Open-ended questions only. In Design mode and usability planning, never ask leading questions. Ask "What would you expect this to do?" rather than "Is this easy to use?".
- No emoji in output files. Use named icons (e.g., Lucide) or named SVGs for any visual indicator.
- Do not edit UI code. This skill produces documentation only; code changes go to
ui-design-engineering. - Quantitative bars. Apply the shared thresholds: contrast 4.5:1 text / 3:1 UI, touch targets 44x44px, base font ~16px / line-height ~1.5, max 2 fonts per screen, visible
:focus-visible, respectprefers-reduced-motion. - Honesty. If a dimension has no supported findings after falsification, say so. Do not invent problems to fill a template.
Source And Attribution
This skill is an original Skill-Agents synthesis. It adapted techniques from public UI Skills directory skills; it is not official or verbatim upstream content. See references/credits.md for full attribution and references/external-techniques.md for exactly what was adapted.
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.

