Skill: Prototype & Research
Requirements
This skill needs the full UX/UI Agent Skills kit: the gates, the references and
the design-system library. Install it with npx ux-ui-agent-skills@3.1.0 init
or as the Claude Code plugin. npx skills@1.7.6 add copies the skill folder and
nothing else. Installed that way, this skill runs in guidance-only mode: no gate
runs, so it gives no verdict.
Step 0: is the kit here? Check once:
ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSING
On KIT_MISSING, open your reply with: "Guidance-only mode: the UX/UI Agent
Skills kit is not installed here, so no gate ran and nothing below is
measured." Then work from this file and general practice, under three rules.
Do not guess or cite the contents of a kit file you could not open. State no
measured number (no contrast ratio, no N/N, no "passes WCAG"): write "not
verified" where one would go. End with a line Skipped (kit not installed):
that names every gate script this file tells you to run, then the install
command above.
Guide work through the right fidelity level with validation.
Steps
- Read
${CLAUDE_SKILL_DIR}/../../../workflows/prototyping.md (5-level fidelity ladder, journey mapping template, usability-testing script, sample data).
- 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).
- For flows: produce a user-journey map with decision points, error paths, and edge cases.
- For validation: define the usability test (tasks, success criteria, 5-user rule) using the script.
- High-fi/code steps pull tokens (
${CLAUDE_SKILL_DIR}/../../../tokens/*), components (${CLAUDE_SKILL_DIR}/../../../components/*), taste (${CLAUDE_SKILL_DIR}/../../../taste/*), and a11y (${CLAUDE_SKILL_DIR}/../../../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).
1---2name: prototype3description: Move an idea up the fidelity ladder (content-first → wireframe → low-fi → high-fi → code) with a validation plan at each level, plus user-journey mapping and usability-testing scripts. Use when the user wants to prototype, wireframe, map a user flow, or plan/run usability testing.4# `invocation:` was not a field Claude Code reads - unknown frontmatter keys are5# ignored without an error, so these six were auto-invocable the whole time they6# were marked user-only. This is the field that actually does it.7disable-model-invocation: true8metadata:9 source: https://skillmd.com/skills/tuyv/prototype10---1112# Skill: Prototype & Research1314## Requirements1516This skill needs the full UX/UI Agent Skills kit: the gates, the references and17the design-system library. Install it with `npx ux-ui-agent-skills@3.1.0 init`18or as the Claude Code plugin. `npx skills@1.7.6 add` copies the skill folder and19nothing else. Installed that way, this skill runs in **guidance-only mode**: no gate20runs, so it gives no verdict.2122> **Step 0: is the kit here?** Check once:23> `ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSING`24> On `KIT_MISSING`, open your reply with: "Guidance-only mode: the UX/UI Agent25> Skills kit is not installed here, so no gate ran and nothing below is26> measured." Then work from this file and general practice, under three rules.27> Do not guess or cite the contents of a kit file you could not open. State no28> measured number (no contrast ratio, no N/N, no "passes WCAG"): write "not29> verified" where one would go. End with a line `Skipped (kit not installed):`30> that names every gate script this file tells you to run, then the install31> command above.3233Guide work through the right fidelity level with validation.3435## Steps361. Read `${CLAUDE_SKILL_DIR}/../../../workflows/prototyping.md` (5-level fidelity ladder, journey mapping template, usability-testing script, sample data).372. Identify the current need and pick the **lowest** fidelity that answers it. Never skip levels:38 - Content-first (info needs) → Wireframe (layout/nav) → Low-fi (task completion) → High-fi (visual/a11y) → Code (feasibility/perf).393. For flows: produce a user-journey map with decision points, error paths, and edge cases.404. For validation: define the usability test (tasks, success criteria, 5-user rule) using the script.415. High-fi/code steps pull tokens (`${CLAUDE_SKILL_DIR}/../../../tokens/*`), components (`${CLAUDE_SKILL_DIR}/../../../components/*`), taste (`${CLAUDE_SKILL_DIR}/../../../taste/*`), and a11y (`${CLAUDE_SKILL_DIR}/../../../accessibility/*`).4243## Output44The artifact at the chosen fidelity + an explicit "what we validate next" plan.4546## Verification (before declaring done)47- The fidelity matches the question being answered; no level skipped.48- Flows include decision points, **error paths, and edge cases** (empty/loading/overflow), not just the happy path.49- A concrete validation step is named (tasks + success criteria), not "test later".50- High-fi/code artifacts pass the same token + a11y bar as `design-code` (no hardcoded values, contrast, states).