---
name: Prototype & Research
slug: prototype-research
category: Frontend
description: Prototype & Research moves an idea through the right fidelity level, from content-first to wireframe to code, with validation at each step. It also supports user-journey mapping and usability testing when you need to evaluate a flow or interface.
github: "https://github.com/plugin87/ux-ui-agent-skills/tree/main/.claude/skills/prototype"
language: JavaScript
stars: 639
forks: 64
install: "npx degit https://github.com/plugin87/ux-ui-agent-skills/tree/main/.claude/skills/prototype ~/.claude/skills/prototype"
installs_to: ~/.claude/skills/prototype
source_path: .claude/skills/prototype/SKILL.md
collection_size: 17
category_size: 567
collection_url: "https://dirskills.com/collections/plugin87/ux-ui-agent-skills"
added: 2026-08-24T05:18:10.811Z
last_synced: 2026-08-24T05:18:10.811Z
canonical_url: "https://dirskills.com/skills/prototype-research"
---

# Prototype & Research

Prototype & Research moves an idea through the right fidelity level, from content-first to wireframe to code, with validation at each step. It also supports user-journey mapping and usability testing when you need to evaluate a flow or interface.

**Install:**

```bash
npx degit https://github.com/plugin87/ux-ui-agent-skills/tree/main/.claude/skills/prototype ~/.claude/skills/prototype
```

## README

# Skill: Prototype & Research

Guide work through the right fidelity level with validation.

## Steps
1. Read `workflows/prototyping.md` (5-level fidelity ladder, journey mapping template, usability-testing script, sample data).
2. Identify the current need and pick the **lowest** fidelity that answers it — never skip levels:
   - Content-first (info needs) → Wireframe (layout/nav) → Low-fi (task completion) → High-fi (visual/a11y) → Code (feasibility/perf).
3. For flows: produce a user-journey map with decision points, error paths, and edge cases.
4. For validation: define the usability test (tasks, success criteria, 5-user rule) using the script.
5. High-fi/code steps pull tokens (`tokens/*`), components (`components/*`), taste (`taste/*`), and a11y (`accessibility/*`).

## Output
The artifact at the chosen fidelity + an explicit "what we validate next" plan.

## Verification (before declaring done)
- The fidelity matches the question being answered — no level skipped.
- Flows include decision points, **error paths, and edge cases** (empty/loading/overflow), not just the happy path.
- A concrete validation step is named (tasks + success criteria), not "test later".
- High-fi/code artifacts pass the same token + a11y bar as `design-code` (no hardcoded values, contrast, states).