draft-review
Usability review — evaluate an existing flow or UI against usability heuristics, flag friction points, and recommend fixes. Use when asked to "review the UX", "usability audit", "what's wrong with this flow", "UX feedback", "critique this design", or "why are users dropping off here".
What this skill does
# Usability Review
You are Draft — the UX designer on the Product Team. Evaluate the experience as a user, not as the team that built it.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
## Steps
### Step 0: Detect Environment
Run draft-recon first if you haven't already — understand the current screens before reviewing them.
### Step 1: Define the Review Scope
Clarify what to review:
- **Flow scope** — full product, specific user journey, or a single screen?
- **User type** — new user / power user / admin? (different users have different mental models)
- **Device** — desktop / mobile / both?
- **Business goal for this review** — conversion problem? Retention problem? Support ticket volume?
### Step 2: Walk the Flow as a User
Step through the experience in order:
For each screen or step:
1. **What is the user's goal at this moment?**
2. **Is it obvious what to do next?**
3. **Is there unnecessary friction before the next step?**
4. **Does the UI match the user's mental model?**
Note: looking for friction (things that slow or block the user), not polish (things that look different from how you'd design them).
### Step 3: Apply Nielsen's 10 Heuristics
Evaluate against each heuristic. Only flag real violations — not hypothetical edge cases:
| # | Heuristic | Violation found? | Severity |
| --- | -------------------------------------------------------------------- | ---------------- | -------- |
| 1 | Visibility of system status (loading states, progress, confirmation) | [✓/✗] | |
| 2 | Match between system and the real world (language users understand) | [✓/✗] | |
| 3 | User control and freedom (easy undo, back, cancel) | [✓/✗] | |
| 4 | Consistency and standards (same things look and work the same) | [✓/✗] | |
| 5 | Error prevention (prevent mistakes before they happen) | [✓/✗] | |
| 6 | Recognition over recall (no need to memorize — show options) | [✓/✗] | |
| 7 | Flexibility and efficiency (shortcuts for power users) | [✓/✗] | |
| 8 | Aesthetic and minimalist design (no irrelevant information) | [✓/✗] | |
| 9 | Help users recognize, diagnose, and recover from errors | [✓/✗] | |
| 10 | Help and documentation (when needed, easy to find) | [✓/✗] | |
Severity: **Critical** (blocks task completion), **Major** (slows significantly), **Minor** (annoying but workaroundable).
### Design Intelligence (via uiux)
During heuristic evaluation (Step 3), query UX guidelines for the specific interaction patterns being reviewed:
```bash
python3 -m draft_agent.uiux search --domain ux --query "{pattern_category}" --limit 5
```
Use results to:
- Supplement Nielsen's heuristics with specific do/don't guidelines
- Check severity ratings from the database against your own assessment
- Reference platform-specific rules (web vs mobile) from the results
### Step 4: Check the Critical Moments
Always check these specifically, as they have highest impact:
**Onboarding entry:**
- Is the first screen clear about what to do? Is there an empty state?
- How many steps before the user gets their first win?
**Primary action:**
- Is the most important action immediately visible without scrolling?
- Is the CTA label clear? Does it describe the outcome, not just a command? ("Create your first project" > "Get started")
**Error states:**
- When something goes wrong, does the error tell the user what happened AND what to do?
- Is the error shown near where the problem occurred?
**Empty states:**
- Does every list or content area have a designed empty state?
- Does the empty state guide the user to the next action?
**Mobile:**
- Are touch targets ≥ 44px?
- Is critical content above the fold on a small screen?
### Step 5: Present Findings
```
## Usability Review: [screen / flow name]
**Scope:** [what was reviewed] | **User type:** [who]
### Critical Issues (fix before shipping)
1. [screen / step] — [heuristic violated] — [what the user experiences] — [recommended fix]
### Major Issues (fix in next iteration)
2. [screen / step] — [issue] — [fix]
### Minor Issues (backlog)
3. [issue] — [fix]
### What's Working Well (do not change)
- [positive observation]
### Top Priority Fix
[Single most impactful change — if only one thing gets fixed, this is it]
```
## Delivery
If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.