Skip to main content
skill CX Codex

usability-tester · oakoss — Claude Code skill: what it does, how to install

usability-tester plans usability test sessions, evaluates interfaces against heuristic standards, and scores UX friction points using severity formulas.

MIT 122 installs ★ 29 updated 2026-08-17

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add oakoss/agent-skills --skill usability-tester -a claude-code
Open on GitHub

What usability-tester does

The skill outlines UX evaluation workflows. It supplies structure for moderated sessions, think-aloud studies, accessibility checks, and cognitive walkthroughs. Instead of tracking click counts like analytics tools, it focuses on diagnosing why users get stuck on specific flows.

It relies on concrete target numbers: 80% or higher task completion rate and SUS scores starting at 68. Defect priority uses a direct formula: impact (1-3) multiplied by frequency (1-3). Any finding scoring 6 or higher gets marked as a blocker before launch.

This skill does not write automated UI assertions or measure page performance. You still need regular testing frameworks for code regression suites.

What it helps with

  • structure realistic task scenarios without leading instructions
  • run heuristic evaluations based on Nielsen's principles
  • calculate SUS scores and task completion rates from test notes
  • rank UX issues using impact-by-frequency severity scores
  • plan participant recruitment across test waves

Example prompts for the agent

  • Draft a moderated usability test plan for the checkout flow with three task scenarios
  • Run a heuristic evaluation on this settings view and score every violation by severity
  • Calculate the SUS score and task success rate from these user testing session notes

How to install usability-tester

1Skills CLI (Vercel)

npx skills add oakoss/agent-skills --skill usability-tester -a claude-code

2Manually: put the files in place

~/.claude/skills/usability-tester/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/usability-tester/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about usability-tester

How to install usability-tester in Claude Code?

Run npx skills add oakoss/agent-skills --skill usability-tester -a claude-code in your terminal.

When should you avoid using this skill?

Skip it for analytics setup, A/B test experiments, and automated end-to-end test code, because it is built for observational UX research.

How does the skill determine issue priority?

It multiplies impact (rated 1 to 3) by frequency (rated 1 to 3). Scores of 6 and above require fixes before deployment.

Source text

SKILL.md · MIT
---
name: usability-tester
description: 'Conduct usability tests and identify UX issues through systematic observation. Use when testing user flows, validating designs, identifying friction points, running heuristic evaluations, or ensuring users can complete core tasks. Use for test planning, think-aloud protocol, task scenarios, severity rating, accessibility evaluation.'
license: MIT
metadata:
  author: oakoss
  version: '1.0'
---

# Usability Tester

## Overview

Validates that users can successfully complete core tasks through systematic observation and expert evaluation. Covers moderated and unmoderated testing, heuristic evaluation, accessibility checks, and issue severity scoring. Not a substitute for analytics or A/B testing -- those measure what happens, usability testing reveals why.

**When to use:** Testing user flows, validating designs, identifying friction points, running heuristic evaluations, ensuring users can complete core tasks, planning and executing usability test sessions.

**When NOT to use:** Analytics or A/B test setup, visual design critique without task-based evaluation, automated UI testing (use a testing framework), performance benchmarking.

## Quick Reference

| Method                 | Best For                                | Participants                | When to Use                            |
| ---------------------- | --------------------------------------- | --------------------------- | -------------------------------------- |
| Moderated testing      | Deep insights, complex flows            | 5-8 per persona             | Design and prototyping stage           |
| Unmoderated testing    | Scale, quantitative data                | 20-50+                      | Pre-launch and post-launch             |
| Guerrilla testing      | Quick validation, early concepts        | 5-10 random                 | Early concept stage                    |
| First-click testing    | Navigation, information architecture    | 20-50                       | Any stage, especially IA redesigns     |
| Heuristic evaluation   | Expert review against principles        | 3-5 evaluators              | Before user testing, design audits     |
| Cognitive walkthrough  | Task flow analysis                      | 2-3 evaluators              | Early design, new feature review       |
| Accessibility audit    | Inclusive design validation             | 3-5 users with disabilities | Pre-launch, compliance reviews         |
| Synthetic user testing | Scalable task validation with AI agents | N/A (automated)             | Continuous, regression testing         |
| AI-moderated sessions  | Async moderated testing at scale        | 10-50+                      | When moderator availability is limited |

## Core Metrics

| Metric                 | Target                                      | What It Measures            |
| ---------------------- | ------------------------------------------- | --------------------------- |
| Task success rate      | 80% or higher for core tasks                | Can users complete the task |
| Time on task           | Simple under 30s, medium 1-2m, complex 3-5m | Efficiency                  |
| Error rate             | Fewer than 2 per task                       | Learnability and clarity    |
| Post-task satisfaction | 4.0 or higher on 5-point scale              | Subjective ease             |
| SUS score              | 68+ (industry average), 80+ (excellent)     | Overall usability           |

## Issue Severity

Severity equals Impact (1-3) multiplied by Frequency (1-3). Critical (8-9): fix before release. High (6-7): fix before release. Medium (4-5): next release. Low (1-3): backlog.

## Common Mistakes

| Mistake                                                                 | Correct Pattern                                                                        |
| ----------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
| Writing task scenarios with product jargon or step-by-step instructions | Use natural language with realistic context and clear goals to test discoverability    |
| Helping users or explaining the UI during test sessions                 | Observe silently and let users struggle; confusion reveals real issues                 |
| Testing only the happy path with ideal inputs                           | Include error states, edge cases, and recovery scenarios in test plans                 |
| Using fewer than 5 participants per persona                             | Recruit 5-8 users per persona; after 5, diminishing returns per Nielsen research       |
| Collecting findings without severity scoring or follow-up actions       | Score every issue by impact times frequency and assign fix priority                    |
| Skipping heuristic evaluation before user testing                       | Run expert review first to catch obvious issues cheaply before spending on recruitment |
| Ignoring accessibility in test planning                                 | Include participants with disabilities and test with assistive technologies            |
| Running only one round of testing                                       | Test in waves: 5 users, fix issues, test 5 more until success rate meets targets       |

## Delegation

- **Test plan and scenario creation**: Use `Task` agent to draft objectives, research questions, and realistic task scenarios for each persona
- **Heuristic evaluation**: Use `Task` agent to walk through interfaces against Nielsen's 10 heuristics and document violations with severity ratings
- **Metrics analysis and severity scoring**: Use `Task` agent to calculate SUS scores, task success rates, and severity ratings from raw test data
- **Test report generation**: Use `Task` agent to compile findings into structured reports with prioritized recommendations
- **Test infrastructure planning**: Use `Plan` agent to select testing methods, define recruitment criteria, and schedule test waves

> If the `quality-auditor` skill is available, delegate full codebase quality audits and scoring to it.
> Otherwise, recommend: `pnpm dlx skills add oakoss/agent-skills -s quality-auditor -a claude-code -y`

## References

- [Test Planning](references/test-planning.md) -- objectives, research questions, recruitment, task scenario templates, screening criteria
- [Conducting Tests](references/conducting-tests.md) -- think-aloud protocol, facilitation rules, post-task questions, session structure
- [Testing Methods](references/testing-methods.md) -- unmoderated, guerrilla, first-click, cognitive walkthrough, method selection by lifecycle stage
- [Heuristic Evaluation](references/heuristic-evaluation.md) -- Nielsen's 10 heuristics, evaluation process, severity rating, combining with user testing
- [Metrics and Severity](references/metrics-severity.md) -- success rate, time on task, errors, satisfaction, SUS scoring, severity formula
- [Reporting](references/reporting.md) -- test report template, key insights format, stakeholder presentation, recommended actions
- [Accessibility Testing](references/accessibility-testing.md) -- inclusive recruitment, assistive technology testing, WCAG alignment, accessibility heuristics
- [Remote and Tools](references/remote-and-tools.md) -- remote vs in-person comparison, testing tools, test frequency, checklists

© oakoss · MIT · oakoss/agent-skills

Similar skills

All skills for Testing and QA →

usability-tester by other authors comes first.

usability-tester daffy0208 usability-tester designs observational usability studies, crafts task scenarios without leading instructions, and scores UX issue severity. CX Codex +1 188installs ux-usability-foundations hueyexe ux-usability-foundations guides an AI agent to design, review, and refine interfaces around usability principles, error prevention, and user mental models. CX Codex +1 667installs usability-testing rampstackco The usability-testing skill helps plan and run usability tests on prototypes and live designs to find problems before launch. Covers moderated tests, task scripts, observation, and findings reports. CX Codex +1 319installs usability-check haabe usability-check runs a screen-level usability review against Nielsen's 10 heuristics and returns a pass/partial/fail table, useful before calling UI work done. CX Codex +1 ★ 54repo stars nielsen-usability-heuristics dembrandt nielsen-usability-heuristics audits UI components and interaction flows using Nielsen's usability heuristics. Helps spot missing feedback, confusing copy, and poor error handling. CX Codex +1 1,200installs ux-review NickCrew ux-review reviews a component or flow from three angles: usability heuristics, WCAG 2.1 AA accessibility and interaction design. Comes back with a prioritized report. CX Codex +1 119installs ux-heuristics wondelai ux-heuristics — a skill for assessing and improving interface usability using Nielsen's heuristics and Krug's principles. Triggers when users describe navigation complexity, form confusion, or unclear design patterns. CX Codex +1 10,800installs

From the same set106

The whole set →
seo-optimizer seo-optimizer — an SEO architecture skill: JSON-LD entities, E-E-A-T signals, topic clusters and a 30-point content audit. Runs in Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. CX Codex +1 125installs performance-optimizer performance-optimizer provides structured workflows for profiling, caching, and full-stack performance tuning. Helps eliminate slow database queries, optimize bundles, and reduce API latency. CX Codex +1 124installs storybook-stories Writes Storybook stories and interaction tests in CSF3 format. Handles component examples, Chromatic visual snapshot setup, and accessibility checks. CX Codex +1 124installs shell-integration The shell-integration Claude Code skill provides terminal integration guides and Bash, Zsh, and Fish patterns for completions, prompt hooks, and portable POSIX wrappers. CX Codex +1 123installs react-email Build responsive HTML emails from React Email components and render them as HTML or plain text. Useful for transactional messages and marketing templates. CX Codex +1 122installs rag-implementer rag-implementer guides an agent through a retrieval-augmented generation build, from chunking and embeddings to hybrid retrieval and quality metrics. CX Codex +1 121installs service-worker service-worker guides the coding assistant in configuring Workbox v7.4 caching, offline app shells, background sync, and push notifications. CX Codex +1 121installs cli-power-tools cli-power-tools guides coding agents to use fast Rust-based command-line utilities and structured parsers instead of legacy shell pipelines. CX Codex +1 121installs

Project sponsors

Companies that keep this analytics open