accessibility-research
Skill1 starsChanged 38 days agoMITView on GitHub
Plan research with disabled people and people who use assistive technology: recruiting, accommodations, consent, session setup and analysis. Use when someone wants to include people with disabilities in research, test with screen reader users, or go beyond automated accessibility checks.
In this repository17 other files it gives its agents.
- 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-analysisSkill
- usability-test-planSkill
- user-personasSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 13
Accommodations: ask each person what they need.
- Distinctive: line 15
Remote setup: test the video call tool with their assistive technology before the session.
- Distinctive: line 31
Don't use simulations (like blindfolding staff) as a substitute.
≈ “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
Accessibility research
Automated checks only catch part of the problem. The rest shows up when people who use assistive technology try the real thing.
Plan
- Who: people who use screen readers, screen magnification, voice control, switch devices or keyboard only, people with cognitive or learning disabilities, and people who are hard of hearing. Recruit through disability organisations and specialist panels, and pay fairly.
- Accommodations: ask each person what they need. Sessions may run longer; let people use their own device and setup; send materials in advance in accessible formats; offer captions or an interpreter.
- Consent in plain language, in a format they can use, with time to ask questions.
- Remote setup: test the video call tool with their assistive technology before the session.
Running sessions
Let people use their own settings and speed. Ask them to describe what their technology is announcing or doing. Don't take over their device. Note where they get stuck and the workaround they use.
Analysis
For each issue: the assistive technology and browser, the task, what happened, severity, and the WCAG success criterion it relates to. Separate barriers (can't complete) from friction (completes with effort).
Output
The plan, recruiting criteria, accommodation checklist, session guide, and after: findings by severity with assistive technology details and fixes.
Don't
- Don't use simulations (like blindfolding staff) as a substitute. Don't recruit only one kind of disability and call it accessible.
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.