skills/product/ux-flow/SKILL.md
UX flow design and analysis. Creates user flow diagrams, interaction patterns, and information architecture. Generative — creates and maps flows rather than evaluating existing ones (see product/ux-review for evaluation). Use when: "user flow", "flow diagram", "interaction design", "information architecture", "IA mapping", "user journey map", "navigation design", "flow analysis"
npx skillsauth add mikeparcewski/wicked-garden ux-flowInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Design and map user flows, interaction patterns, and information architecture. This skill is generative — it creates flows and IA structures from requirements or existing code, rather than evaluating whether a flow is good.
| Type | Purpose | Output | |------|---------|--------| | Task flow | Single task, one path | Linear diagram | | User flow | Multiple paths, decision points | Branching diagram | | Screen flow | UI states per step | Annotated screens | | System flow | Front-end + back-end | Swimlane diagram |
[Start] → [Login Page]
↓
{Credentials valid?}
/ \
Yes No
↓ ↓
[Dashboard] [Error Msg] → [Retry]
↓
{Has onboarding?}
/ \
Yes No
↓ ↓
[Setup Flow] [Home]
flowchart TD
A[Start] --> B[Login Page]
B --> C{Valid?}
C -->|Yes| D[Dashboard]
C -->|No| E[Error State]
E --> B
D --> F{New user?}
F -->|Yes| G[Onboarding]
F -->|No| H[Home]
When analyzing an existing flow:
From requirements or code, extract:
App Root
├── Auth
│ ├── Login
│ ├── Register
│ └── Password Reset
├── Dashboard (requires auth)
│ ├── Overview
│ └── Widgets
└── Settings (requires auth)
├── Profile
├── Notifications
└── Security
Common patterns and when to use them:
| Pattern | Use Case | |---------|----------| | Modal dialog | Focused action, doesn't lose context | | Slide-over panel | Editing without navigation | | Inline edit | Simple field edits | | Full-page form | Complex data entry | | Wizard | Multi-step, sequential | | Accordion | Progressive disclosure | | Tab set | Peer-level content switching |
## UX Flow: {feature or page}
### Overview
{1–2 sentences: what the flow accomplishes}
### Information Architecture
{IA tree or description}
### User Flow
{ASCII or Mermaid diagram}
### Step-by-Step
1. User arrives at {entry point}
2. {action} → {system response}
3. {decision} → {branch A / branch B}
...
### Edge Cases
- **Empty state**: {what shows when no data}
- **Error state**: {what shows on failure, recovery path}
- **Loading state**: {feedback during async ops}
### Open Questions
- {question requiring product/stakeholder input}
development
--- name: large-scale-migration description: How to execute a LARGE MECHANICAL change across any codebase with LEVERAGE instead of an agent-grind or hand-edits — a cross-cutting migration, refactor, rename, dialect/framework/DB port, library adoption, or bulk transform. The map→transform→gate pattern: a deterministic transform driven by a source-of-truth map, proven by a differential-equivalence gate. Use when the work is "migrate all X to Y", "rename Z everywhere", "port to a new DB/dialect/fra
testing
v11 LLM-based work-shape classifier. Replaces the regex archetype detector with the model's own reasoning. Reads the user's prompt, picks the right archetype(s) from the catalog, identifies signals (blast_radius, novelty, reversibility, etc.), and persists to SessionState so subsequent turns steer correctly. Use when: the prompt_submit hook emitted a `<wg classify-due />` directive, OR explicitly invoked at session start, OR when re-classifying after the user changes scope mid-session.
tools
v11 work-shape archetype runner. When a prompt has been routed to one of the 9 archetypes (triage, explore, specify, decide, ship, review, incident, build, migrate), this skill is the entry point. It picks the right per-archetype playbook from refs/ and executes the phase shape declared in `.claude-plugin/archetypes.json`. Use when: a `<wg archetype="X">` or `<wg archetypes>` system-reminder tag appears, an explicit "let's run the X archetype" request, or when one of the per-archetype slash commands resolves to this skill.
development
Show or set the session intent variable. Intent gates how loud the framework is — simple-edit (silent), feature/research (synthesis directive), rigor (full crew context). Auto-detected on turn 1; this skill overrides explicitly. Sticky for the session. Use when: "set intent", "intent override", "/wicked-garden:intent", "make the framework quiet", "force rigor", "what's my intent".