Skip to content
Design
Command

/evaluate

Run a heuristic evaluation end to end — expert review against heuristics with severity ratings and recommended fixes.

BOOST
From plugin
designer-skills
2.9k33 skills33 commands
Install
> /plugin marketplace add Owl-Listener/designer-skills

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/evaluate

Context preview

What this command does when you run it.

Run a heuristic evaluation end to end — expert review against heuristics with severity ratings and recommended fixes.

Command definition

evaluate.md
description: Run a heuristic evaluation end to end — expert review against heuristics with severity ratings and recommended fixes.
argument-hint: "[design, screen, or flow to evaluate]"

/evaluate

Run a heuristic evaluation of a design.

Steps

1. **Scope** — Define screens and flows to evaluate. 2. **Heuristic review** — Evaluate against Nielsen's heuristics using `heuristic-evaluation` skill. 3. **Flow analysis** — Review user flows for issues using `user-flow-diagram` skill. 4. **Accessibility check** — Evaluate accessibility using `accessibility-test-plan` skill. 5. **Severity rating** — Rate and prioritize all findings. 6. **Recommendations** — Provide specific improvement suggestions.

Output

Evaluation report with findings per heuristic, severity ratings, accessibility issues, and prioritized recommendations. Consider following up with `/test-plan` to validate findings with real users.

Ships withdesigner-skills

Design skills for the agent era, written so an AI agent can actually use them. 273 skills and 76 commands across 33 plugins, in five collections, for Claude Code and Gemini CLI. Not sure which skill you need?

Get the whole plugin

Other commands on designer-skills.