test-scenario — Claude Code skill: usability test tasks
Writes usability test scenarios with realistic context, success criteria and facilitation notes. Useful once the study is planned and the tasks are still missing.
npx skills add Owl-Listener/designer-skills --skill test-scenario -a claude-codeWhat test-scenario does
The skill covers one slice of study prep: the tasks themselves. Each scenario gets a context, a task, success criteria and an observation guide. The context is a short backstory that gives the participant a reason to act without pointing at the answer. The task states a goal rather than a question, and avoids interface wording that gives the path away.
Success criteria cover completion, time on task, error and wrong-path counts, assistance requests, and a 1–5 difficulty rating. The observation guide lists what to watch: hesitations, facial expressions, think-aloud comments, navigation choices, and how someone recovers from an error. Task types are exploratory, specific, comparative and open-ended.
The writing rules are plain: the participant's language instead of product jargon, motivation instead of instructions, one goal per task. The skill suggests starting with a warm-up task, ordering from easy to hard, and writing more scenarios than you need. Pilot them before real sessions. For the study design around the tasks, see usability-test-plan in the design-research set.
What it helps with
- write usability tasks that do not leak the UI path
- attach success criteria to every task
- build an observation guide for the facilitator
- pick a warm-up task and order the rest easy to hard
- pilot scenarios before running real sessions
Example prompts for the agent
- Write usability test scenarios for the new onboarding: context, task, success criteria and an observation guide.
- Draft five cart test tasks, from a warm-up to a hard one, with a 1–5 difficulty rating.
- Rewrite these tasks so no interface wording appears in the prompts.
How to install test-scenario
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill test-scenario -a claude-code2Manually: put the files in place
~/.claude/skills/test-scenario/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/test-scenario/
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill test-scenario -a codex2Manually: put the files in place
.agents/skills/test-scenario/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill test-scenario -a cursor2Manually: put the files in place
.cursor/skills/test-scenario/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Owl-Listener/designer-skills test-scenario2Manually: put the files in place
.github/skills/test-scenario/SKILL.md1Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill test-scenario -a gemini-cli2Platform CLI
gemini skills install https://github.com/Owl-Listener/designer-skills --path prototyping-testing/skills/test-scenarioManually: put the files in place
.devin/skills/test-scenario/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Owl-Listener/designer-skills --skill test-scenario -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about test-scenario
How do I install test-scenario in Claude?
Run npx skills add Owl-Listener/designer-skills --skill test-scenario -a claude-code. The skill file then sits at ~/.claude/skills/test-scenario/SKILL.md.
What does test-scenario do?
It writes usability test scenarios: context, task, success criteria and an observation guide. Tasks can be exploratory, specific, comparative or open-ended.
How is test-scenario different from usability-test-plan?
test-scenario only produces the participant tasks. The full study design is usability-test-plan from the design-research set.
Source text
SKILL.md · MIT
--- name: test-scenario description: Write realistic usability task scenarios with success criteria and facilitation notes. Use when you have a study and need the tasks. For the surrounding study design, use `usability-test-plan` (design-research). --- # Test Scenario You are an expert in writing usability test scenarios that reveal genuine user behavior. ## What You Do You write test scenarios with realistic tasks, clear success criteria, and structured observation guides. ## Scenario Structure ### Context Setting Brief, realistic backstory that gives the participant a reason to act without leading them. ### Task Specific goal to accomplish. Action-oriented, not question-based. Avoids UI terminology that hints at the answer. ### Success Criteria - Task completion (yes/no) - Time to complete - Number of errors or wrong paths - Assistance requests - Self-reported difficulty (1-5 scale) ### Observation Guide What to watch for: hesitations, facial expressions, verbal comments, navigation choices, error recovery behavior. ## Task Types - **Exploratory**: Find information (e.g., 'Find the return policy') - **Specific**: Complete a goal (e.g., 'Add a blue shirt size M to your cart') - **Comparative**: Choose between options - **Open-ended**: Achieve a goal with multiple valid paths ## Scenario Writing Rules - Use participant's language, not product jargon - Give motivation, not instructions - One goal per task - Don't reveal the UI path in the task wording - Include both simple and complex tasks ## Best Practices - Pilot test your scenarios before real sessions - Order tasks from easy to hard - Include a warm-up task - Prepare follow-up questions per task - Write more scenarios than you need (allow flexibility)
© Owl-Listener · MIT · Owl-Listener/designer-skills
