Skip to content
Back to skills

Ux Heuristic Evaluation

ASecurity

Evaluate UI behavior against usability heuristics.

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agentsgodocumentation

Security analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned September 2, 2026

npx -y skills add Eliyce/paqad-ai --skill ux-heuristic-evaluation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ux Heuristic Evaluation?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ux Heuristic Evaluation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/eliyce-ux-heuristic-evaluation/badge)](https://www.skillsdirectory.com/skills/eliyce-ux-heuristic-evaluation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ux-heuristic-evaluation
description: Evaluate UI behavior against usability heuristics.
model_tier: medium
triggers:
  - ui_impact:
      - new-component
      - new-screen
      - redesign
cacheable: true
cache_key_inputs:
  - docs/modules/*/ui/components.md
  - docs/modules/*/ui/screens.md
output_format: markdown
input_schema:
  ui_surface_paths:
    type: path[]
    required: true
    description: UI surfaces or docs to evaluate.
  request_text:
    type: string
    required: false
    description: Optional evaluation scope.
---

## What It Does

Evaluates changed UI behavior against a defined heuristic rubric so usability issues are reported as concrete user-impact findings instead of subjective design opinions.

## Use This When

Use this for any meaningful UI change once the target flow and states are known, especially before final review or documentation handoff.

## Inputs

- Read the affected UI docs, flow notes, and current state inventory first.
- Read `references/heuristic-rubric.md` before evaluating the interface.
- Read the relevant stack-specific browser validation guide if behavior needs interactive confirmation.

## Procedure

1. Walk every heuristic in `assets/heuristics.txt` against the changed interface; never skip a category silently.
2. Tie each issue to a user task, state, or observed confusion point — never style preference.
3. Bucket findings into Blocking Issues vs Improvement Opportunities per `assets/output.template.md`.
4. Note any UI doc that must update because the heuristic reveals missing state documentation.
5. Validate with `scripts/lint-output.sh`.

## Output Contract

- Return sections named `Blocking Issues` and `Improvement Opportunities`.
- Each finding must state the affected screen or component, the heuristic violated, and the user impact.
- If no issues are found, write `Blocking Issues: none` and `Improvement Opportunities: none`.

## Escalate / Stop Conditions

- Ask when the expected user goal or task completion path is unclear.
- Warn when the interface appears to conflict with accessibility or recovery expectations.
- Do not file purely stylistic preferences as heuristic issues.

## Resources

- `references/heuristic-rubric.md`
- `scripts/lint-output.sh`
- `assets/output.template.md`
- `assets/heuristics.txt`
- `runtime/capabilities/coding/stacks/flutter/references/tools/playwright.md`
- `agents/openai.yaml`

Files in this skill

  • SKILL.md2.4 KB
  • agents/openai.yaml123 B
  • assets/heuristics.txt874 B
  • assets/output.template.md375 B
  • references/heuristic-rubric.md231 B
  • scripts/lint-output.sh849 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.