a11y-pass
Skill0 starsChanged 18 days agoMITView on GitHub
Check keyboard access, accessible names, and contrast on the current UI diff only. Use when the user asks for an accessibility pass, a11y review, or /a11y-pass. Do not score the whole app. Do not invent WCAG certificates.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- KyaniteLabs/tastechecktheir own version, first seen Nov 2, 2026
- Alfred-Lau/skillstheir own version, first seen Oct 20, 2026
- kitloomlk-stack/frontend-design-quality-kittheir own version, first seen Oct 15, 2026
- Zwin-ux/kittheir own version, first seen Oct 11, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- KyaniteLabs/tastecheck★ 12same name
- Alfred-Lau/skills★ 1same name
- kitloomlk-stack/frontend-design-quality-kit★ 0same name
- Zwin-ux/kit★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Do not edit the product to “fix while reviewing” unless the user asked to implement.
- Very specific: line 34
If the diff has no interactive UI, say n/a and stop.
- Distinctive: line 43
Read AGENTS.md if present.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
A11y pass
Judge the diff, not the product. This is not verify-ui (flow) and not write-ui-spec.
Do not edit the product to “fix while reviewing” unless the user asked to implement. Prefer findings.
Is this the right skill?
| Signal | Do this instead |
| Exercise the user flow | verify-ui |
| Spec states of a screen | write-ui-spec |
| Whole-site audit | stop — this skill is diff-only |
Required inputs
- The UI diff (git vs HEAD, or the files edited this session)
AGENTS.md
If the diff has no interactive UI, say n/a and stop.
Human decisions (do not invent)
- Waiver of a fail
- Target WCAG level if the repo does not already state one — default to the checks below only
Procedure
- Read
AGENTS.mdif present. Collect the UI diff. - For each new or changed control: can it be reached from the keyboard, does it have an accessible name, is text unreadable on its background (obvious fail only — do not invent a contrast ratio).
- Find the home:
docs/qa/a11y-<slug-or-id>.mdor put the table in the reply if the user asked for a pass in-session. - Open references/a11y-template.md. Copy every heading. Write
n/awhen unused. - Fail closed: if you did not exercise keyboard on a new control, mark that control
unverified, not pass.
Output
- Path:
docs/qa/a11y-<slug-or-id>.md - Template:
references/a11y-template.md
Quality bar
- Scope is the diff
- New controls are pass / fail / unverified (no silent pass)
- No invented audit score
- Unused headings are
n/a
Done
- Path or the table in the reply
- Fail + unverified counts
- Next skill:
implement-changeto fix, orready-to-merge
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.