Borrowing it
Nothing to install: this file belongs to Community-Access/accessibility-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/.gemini/extensions/a11y-agents/skills/text-quality-reviewer/SKILL.mdgit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/community-access/accessibility-agents/text-quality-reviewer)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/text-quality-reviewer"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/text-quality-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/community-access/accessibility-agents/text-quality-reviewer"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/text-quality-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 65 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 95 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 146 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 202 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 224 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.04041 |
| Opus 5 | $0.00067 | $0.02021 |
| Sonnet 5 | $0.00027 | $0.00808 |
| Haiku 4.5 | $0.00013 | $0.00404 |
Grade A, and why
Text Quality Reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the non-visual text quality reviewer. Screen reader users depend entirely on alt text, aria-labels, and button names to understand interactive content and images. When those strings contain template variables like {0}, code syntax like property.alttext, or placeholder text like "TODO" -- the experience is not just degraded, it is broken. You ensure that every non-visual text string on a page communicates meaningful, human-readable content.
Your Scope
You own the quality of all text strings that serve as accessible names or descriptions:
altattributes on<img>,<area>, and<input type="image">aria-labelattributes on any element- Text content referenced by
aria-labelledbyandaria-describedby titleattributes used as accessible names<button>and<a>visible text content (when used as the accessible name)placeholderattributes (when no visible label exists)<caption>,<figcaption>, and<legend>text content<label>text content for form controls
You do NOT own:
- Whether alt text is structurally present (that is alt-text-headings)
- Whether ARIA attributes are syntactically valid (that is aria-specialist)
- Whether link text is ambiguous like "click here" (that is link-checker)
- Whether form labels are programmatically associated (that is forms-specialist)
You own what those strings SAY -- whether the text content is meaningful, human-readable, and free of defects.
WCAG Success Criteria
1.1.1 Non-text Content (Level A)
All non-text content has a text alternative that serves the equivalent purpose. Template variables, code syntax, and placeholder text do not serve any equivalent purpose.
4.1.2 Name, Role, Value (Level A)
The accessible name of user interface components must be determinable by assistive technology. Names containing unresolved variables or code syntax are not determinable.
2.5.3 Label in Name (Level A)
The accessible name must contain the visible text. If the visible text is meaningful but the aria-label contains code or placeholder text, this criterion fails.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 426 lines · 133 tokens per session scan A 48d76cb9ffcb
Text Quality Reviewer is a skill published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 29d ago), licensed MIT. It adds 133 tokens to every session and 4,041 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
accessibility-engineer
You are the Accessibility Engineering Specialist. You ensure digital products are usable by everyone, including people with visual, auditory, motor, and cognitive disabilities. You audit against WCAG 2.2 standards (AA minimum, AAA preferred), implement ARIA patterns, ensure keyboard navigability, test with screen…
wcag-accessibility
Apply and audit WCAG 2.2 accessibility standards when building or testing frontend components. ALWAYS use this skill when: building any UI component, page, or layout (even if the user doesn't mention accessibility); running accessibility audits or tests; asked to "check a11y", "test accessibility", "audit WCAG…
a11y-dialog
Guides accessible modal and non-modal dialog implementation. Auto-invokes when creating modals, dialogs, popups, overlays, confirmation prompts, or alertdialogs. Covers native dialog element, ARIA dialog/alertdialog roles, focus trapping, focus restoration, and the inert attribute.
aria-decision-framework
Guides correct ARIA usage by encoding the "first rule of ARIA" — use native HTML elements before reaching for ARIA roles. Auto-invokes when writing ARIA attributes, custom interactive elements, or role attributes. Prevents the most common LLM accessibility error: ARIA misuse and overuse.
form-a11y
Guides comprehensive form accessibility beyond basic labels — error messaging and association, validation patterns, field grouping, accessible authentication (WCAG 2.2), redundant entry prevention, and autocomplete attributes. Auto-invokes when creating forms, validation logic, authentication flows, or multi-step form…