agentleFS
Sign inStart free
adityareddy-devadityareddy-dev/deskstudio/skills/accessibility-audit/SKILL.md

accessibility-audit

Skill43 starsChanged 23 days agoMITView on GitHub

A WCAG 2.2 AA audit of a file or URL with a code fix for every finding, and --fix to apply them. Use when a page or component needs to be checked for everyone, beyond what the contrast check sees.

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use design-system-audit, flaky-test-triage and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jpoindexterSkill

    design-system-audit

    Audit code for design system violations - grid spacing, tokens, existing components

    Also in 4 projects that use this

  • SUDARSHANCHAUDHARISkill

    flaky-test-triage

    Diagnoses inconsistent test results by separating product nondeterminism, automation defects, shared data, timing, infrastructure, environment, order, and concurrency effects.

    Also in 3 projects that use this

  • tekumaraSkill

    api-design-review

    Reviews REST API design by inventorying routes, finding overlapping functionality, comparing payloads and pagination, and checking resource naming, URL structure, identifiers, errors, idempotency, and timestamps. Use when asked to review API routes, compare endpoints, find redundant or superseding operations, assess contract consistency, or run a REST API design review.

    Also in 3 projects that use this

  • BufferoverflovvSkill

    observability-setup

    Add production observability to a FastMCP server: request IDs, slow-request logging, structured log fields, and optional Prometheus metrics. Use when: hardening logging for production, adding request tracing or correlation IDs, setting up slow-request alerts, adding a /metrics endpoint, or improving structured log output beyond the base middleware.

    Also in 3 projects that use this

  • mmondoraSkill

    infrastructure-as-code

    Infrastructure as Code with Terraform and Pulumi. State management, modularity, drift detection, secrets handling. Use when provisioning cloud resources, writing Terraform/Pulumi modules, or managing infrastructure configuration.

    Also in 3 projects that use this

  • Sagargupta16Skill

    upgrade-dependencies

    Upgrade a project's dependencies one at a time, running the test suite after each bump and reverting the ones that break it. Use it during routine dependency maintenance, when a batch of updates has accumulated; before a major release, to go into it on current and patched dependencies; when Renovate or Dependabot PRs have piled up and you want them resolved locally in one sitting; when a security advisory means you need the patched version in, and you need to know what it breaks.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 46 edited versions we read keep these.

  • 0

    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
  1. Very specific:

    Run: Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 46 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Audit for accessibility as the Design Manager. The Accessibility Specialist leads.

Deliverable and standard. An audit report with a fix per finding, to WCAG 2.2 AA (AAA with --level AAA), using the Accessibility Specialist's brief as the standard and the deliverable's own standard for anything visual. With --fix, the fixes applied to a copy of the file.

Desks.

DeskAgentTierDoes
Accessibility Specialistdesk:accessibility-specialistseniorleads: structure, names, keyboard, focus, colour, motion, text, media, each finding with a criterion and a fix
Content Designerdesk:content-designerbuilderalt text, link text, labels, error messages that say what to do
Design Engineerdesk:design-engineerbuilderwith --fix: applies every fix in the copy, keeps the design
Art Directordesk:art-directordirectorwith --fix: confirms the fixed render still matches the original's design intent

Inputs. A path to an HTML file, or a URL saved first to .desk/jobs/<id>/source.html. A screenshot is not enough for this command: say so and stop.

Proof sizes. --sizes, else phone,desktop. Proof's contrast, overflow and type checks run first so the Specialist does not repeat them.

Output under .desk/out/<id>/:

  • audit.md: result line, then findings as severity, criterion, element, what is wrong, the fix, grouped blocker, major, minor, then what proof already caught, then what needs a manual check (a screen reader pass, a real keyboard).
  • with --fix: final.html (the fixed copy, original untouched), applied.md (each fix and where), and renders/ before and after.

Run. Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above. Command name for state and events: accessibility-audit. Changes to the loop for this command:

  • Skip roughs and the pick. Phase order: intake, proof (checks and screenshots), audit (Specialist and Content Designer in parallel), report, and with --fix: fix rounds.
  • The gate is not the rubric. A round passes when the Specialist's return is pass with zero blockers and zero majors and proof passes. The Creative Director is not spawned, and scores in state holds { "by": "accessibility-specialist", "blockers": n, "majors": n, "minors": n, "pass": bool } per round instead of axes.
  • With --fix, the Design Engineer applies the fixes, proof reruns, the Specialist re-audits, up to --rounds (default 4). The Art Director looks once at the final render against the original and may add design notes for one more round.
  • The handback's Scores line reads the findings counts before and after.

The ask: $ARGUMENTS

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free