usability-test-analysis
Skill1 starsChanged 36 days agoMITView on GitHub
Analyse usability test sessions into severity ranked findings with how many participants hit each issue, evidence, and specific fixes. Use when someone has test notes, recordings, transcripts or results from a usability study and wants findings, a report, or a prioritised list of issues.
In this repository17 other files it gives its agents.
- accessibility-researchSkill
- ai-browser-walkthroughSkill
- analytics-insightsSkill
- card-sort-tree-testSkill
- competitive-analysisSkill
- diary-studySkill
- interview-guideSkill
- jobs-to-be-doneSkill
- journey-mapSkill
- research-planSkill
- research-readoutSkill
- screener-surveySkill
- stakeholder-interviewsSkill
- survey-designSkill
- synthetic-usersSkill
- usability-test-planSkill
- user-personasSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Don't report a single participant's opinion as a pattern, but do report a single critical failure.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Usability test analysis
Turn sessions into a short list of problems the team will actually fix.
Steps
- Per task: success, partial or failure for each participant, time on task, and the ease score. Present as a small table.
- Log every observation with participant id, task, what happened, and a quote or timestamp.
- Group into issues. For each issue: how many participants hit it (for example 4 of 6), where in the flow, what they expected, what happened instead.
- Severity from impact and frequency:
- Critical: blocks the task, or causes a costly mistake
- Serious: major delay or frustration, many participants
- Minor: slows or annoys, recovers on their own
- Fix for each issue, specific enough to design from, plus what to re test.
- What worked: things to keep, with evidence.
Output
The task table, then issues ordered by severity, each with count, evidence, and fix; then what worked; then open questions for the next round.
Don't
- Don't report a single participant's opinion as a pattern, but do report a single critical failure. Don't mix in your own design preferences as findings. Don't name participants; use ids.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.