accessibility-compliance-accessibility-audit

You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/accessibility-compliance-accessibility-audit/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, token-efficient skill body with a sensible audit workflow, but it is thin on executable specifics and its single external reference is a broken path. Fixing the playbook reference and naming concrete tooling would lift both weak dimensions.

Suggestions

Ship the referenced playbook and fix its path — `resources/implementation-playbook.md` does not exist in the bundle; consider the conventional `references/` directory.

Name specific automated scanners (axe-core, Lighthouse, WAVE) and example WCAG criteria or a report format in the Instructions so guidance is executable rather than directional.

Trim the redundant opening paragraph and "Context" section, both of which restate the frontmatter description.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet points with no explanation of concepts Claude already knows, but the opening paragraph repeats the frontmatter description verbatim and the "Context" section restates the same purpose again — these could be trimmed. Not a 5 because of that redundant framing.	4 / 5
Actionability	Instructions name concrete check categories ("keyboard, screen reader, focus order, contrast") but give no specific tools (axe-core, Lighthouse, WAVE), commands, WCAG criterion examples, or report/deliverable format. Guidance is directional rather than executable, matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	A clear six-step sequence (scope → automated scans → manual checks → map findings → remediation → re-test) with a re-test checkpoint after fixes. It falls short of 5 because validation details are thin — no explicit feedback loop on what to do when re-tests fail or how to verify completeness.	4 / 5
Progressive Disclosure	Structure is good with a single one-level-deep reference clearly signaled in both Instructions and Resources, but the referenced file `resources/implementation-playbook.md` does not exist in the bundle (no `resources/` directory is present), so navigation to the detailed material fails. The broken reference prevents a 4 despite the otherwise clean organization.	3 / 5
	Total	14 / 20 Passed

Description

61%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A domain-focused description with decent keyword coverage, but it is written in second person, lacks any explicit "Use when..." trigger clause, and uses moderately generic action language. Converting to third person and adding an explicit trigger clause would move it into the good-example range.

Suggestions

Rewrite in third person (e.g., "Conducts accessibility audits against WCAG...") to avoid the second-person specificity penalty.

Add an explicit trigger clause such as "Use when the user mentions accessibility, WCAG, a11y, screen readers, Section 508, or inclusive design."

Include natural synonym terms users say — "a11y", "screen reader compatibility", "ADA/Section 508" — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description lists three concrete actions ("Conduct audits, identify barriers, and provide remediation guidance") which would anchor at 4, but it opens in second person ("You are an accessibility expert"), which the guidelines penalize by reducing specificity by 1. Actions are also somewhat generic ("identify barriers") rather than naming concrete deliverables.	3 / 5
Completeness	It clearly answers 'what' (audits, barrier identification, remediation guidance) but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3. When-to-use is only weakly implied by the domain specialization.	3 / 5
Trigger Term Quality	Good natural keyword coverage — "accessibility", "WCAG compliance", "audit", "inclusive design", "assistive technology" are phrases users would actually say. Common variations like "a11y", "screen reader", "Section 508", and "ADA" are missing, keeping it below a 5.	4 / 5
Distinctiveness Conflict Risk	The accessibility/WCAG compliance niche is clearly distinguishable with distinct triggers. There is minor overlap risk with general UX/UI design review skills, which keeps it below a 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/accessibility-compliance-accessibility-audit/SKILL.md
Commit: 7b534bc

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.