CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

67

1.34x
Quality

62%

Does it follow best practices?

Impact

89%

1.34x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/accessibility-compliance-accessibility-audit/SKILL.md

The canonical home for this skill is accessibility-compliance-accessibility-audit in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

42%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 lean, well-organized body with a sensible audit workflow and re-test loop, but it is undermined by a referenced playbook file that is missing from the bundle, a complete absence of concrete tools/commands, and redundant framing sections that restate the description.

Suggestions

Add the missing `resources/implementation-playbook.md` to the bundle (or remove both references to it) so the one-level-deep reference actually resolves.

Make the instructions executable: name specific tools and commands (e.g., `npx axe-cli <url>`, Lighthouse accessibility audit, WAVE) instead of "Run automated scans".

Trim redundancy: remove or merge the opening role paragraph and "Context" section, which restate the description and the "Use this skill when" bullets; move trigger guidance into the description.

Add explicit validation checkpoints between phases (e.g., how to verify a fix passed before re-closing a finding) to strengthen the re-test loop.

DimensionReasoningScore

Conciseness

The body re-states the same purpose three times: the opening paragraph ("You are an accessibility expert specializing in WCAG compliance..."), the "Context" section ("The user needs to audit and improve accessibility..."), and the "Use this skill when" bullets all restate scope already carried by the description. This is unnecessary explanation that could be tightened, matching the 3 anchor; it is not 4 because the redundancy is more than minor, and not 2 because the Instructions and Resources sections are lean.

3 / 5

Actionability

The instructions are high-level hints — "Run automated scans to collect baseline violations", "Perform manual checks (keyboard, screen reader, focus order, contrast)" — with no tool names (e.g., axe, Lighthouse, WAVE), commands, or concrete examples, and the detailed procedures are deferred to `resources/implementation-playbook.md`, which does not exist in the bundle. This matches the 2 anchor (minimal concrete guidance, missing the specific steps to execute); it is not 3 because the enumerated check categories, while named, leave no executable path to actually performing any step.

2 / 5

Workflow Clarity

A sensible sequence is present (confirm scope → automated scans → manual checks → map findings → remediate → "re-test after fixes", an explicit feedback loop), but the detailed procedure behind each step lives in the missing playbook file, so checkpoints are implicit and gaps are not minor. This matches the 3 anchor (steps listed, validation gaps); it is not 4 because the detailed procedure content is unavailable, and not 2 because the sequence is coherent and includes a re-test loop.

3 / 5

Progressive Disclosure

The structure is good in principle — a short overview with the detail split out to a single clearly-signaled reference (dedicated Resources section plus an inline pointer in Instructions) — but `resources/implementation-playbook.md` does not exist in the bundle (no resources/ or references/ directory is present), so the one-level-deep reference is broken. This fits the 3 anchor (some structure, references present but undermined); it is not 4 because a dangling reference is a significant navigation defect, and not 2 because nothing that belongs in a separate file is inlined and the reference is clearly signaled, not buried.

3 / 5

Total

11

/

20

Passed

Description

65%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 focused, well-scoped description with strong natural keywords and clear distinctiveness, but it lacks any "Use when..." trigger clause and is written in second person, which together cost it completeness and specificity points.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for an accessibility audit, WCAG compliance check, or remediation of accessibility barriers (a11y, screen reader, Section 508, ADA)."

Rewrite in third person voice ("Conducts accessibility audits..." instead of "You are an accessibility expert...") to avoid the specificity penalty and match the good-example style.

Add common synonyms users say — "a11y", "screen reader testing", "Section 508/ADA compliance" — to round out trigger term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("Conduct audits, identify barriers, and provide remediation guidance") in a named domain (WCAG, inclusive design, assistive technology), which matches the 4 anchor — but it is written in second person ("You are an accessibility expert"), which per judging guidelines reduces the specificity score by 1 to 3. It is not a 2 because it goes well beyond naming the domain: three distinct actions plus sub-domains are stated.

3 / 5

Completeness

The "what" is clear (conduct audits, identify barriers, provide remediation guidance), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description, which per judging guidelines caps completeness at 3. It is not 4/5 because "when" is entirely absent rather than merely implicit; not 2 because the "what" is concrete and specific.

3 / 5

Trigger Term Quality

Good natural keyword coverage — "accessibility", "WCAG compliance", "audit", "inclusive design", "assistive technology", "remediation" — terms a user would naturally say. It is not 5 because common synonyms and variations users actually use ("a11y", "screen reader", "Section 508", "ADA") are missing; not 3 because the terms present are varied and natural rather than generic.

4 / 5

Distinctiveness Conflict Risk

"WCAG compliance", "inclusive design", "assistive technology compatibility", and "remediation guidance" define a clear accessibility-audit niche with distinct triggers and minimal overlap risk with other skills. It fits the 5 anchor; no neighboring anchor fits better since the domain vocabulary is highly specific.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/accessibility-compliance-accessibility-audit/SKILL.md

Reviewed

Table of Contents

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.