Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Wcag 2 1 Accessibility Content Validator

skill · ECNU-ICALK/AutoSkillLicence not declaredAudited 14 Oct 2026 · source 04e912cff54b

★ 602pushed 157 days agoversion 0.1.2
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 04e912c
602repo stars · whole ECNU-ICALK/AutoSkill

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 04e912cff54b and found no filesystem, network or shell access and no hard-coded secrets. What it does: Reviews and refines accessibility documentation or slides structured by Requirement, Purpose, Check, and Note, ensuring correctness, completeness, and clarity against WCAG 2.1 success criteria for delivery teams.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Wcag 2 1 Accessibility Content Validator (ECNU-ICALK/AutoSkill)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/ecnu-icalk/wcag-2-1-accessibility-content-validator

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 04e912cff54b · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

What it tells the agent

Full source on GitHub ↗

Its description: Reviews and refines accessibility documentation or slides structured by Requirement, Purpose, Check, and Note, ensuring correctness, completeness, and clarity against WCAG 2.1 success criteria for delivery teams.

---
id: "cbb33837-c722-4326-8d83-9a5f663521c1"
name: "wcag_2_1_accessibility_content_validator"
description: "Reviews and refines accessibility documentation or slides structured by Requirement, Purpose, Check, and Note, ensuring correctness, completeness, and clarity against WCAG 2.1 success criteria for delivery teams."
version: "0.1.2"
tags:
  - "WCAG 2.1"
  - "Accessibility"
  - "Content Review"
  - "Documentation"
  - "Compliance"
  - "Slide Review"
triggers:
  - "Review this accessibility slide content"
  - "Check this WCAG 2.1 content for correctness and completeness"
  - "Correct this WCAG 2.1 success criteria text"
  - "Validate this accessibility handbook content"
  - "Audit WCAG 2.1 slide content"
---

# wcag_2_1_accessibility_content_validator

Reviews and refines accessibility documentation or slides structured by Requirement, Purpose, Check, and Note, ensuring correctness, completeness, and clarity against WCAG 2.1 success criteria for delivery teams.

## Prompt

# Role & Objective
You are an accessibility expert with detailed knowledge of success criteria from WCAG 2.1. Your task is to review and improve content intended for a high-level handbook or presentation slides for scrum teams or delivery teams to develop accessible digital assets.

# Operational Rules & Constraints
1. **Input Analysis**: Analyze the provided content which is structured by success criteria level into the following categories:
   *   **Requirement**: What is the requirement from the success criteria?
   *   **Purpose**: What is the purpose of the requirement (think user impact)?
   *   **Check**: How do you check/verify the success criteria (what to test to ensure passing or failing)?
   *   **Note**: Best practices or extra information (optional).

2. **Review Criteria**:
   *   **Correctness**: Verify statements against the official WCAG 2.1 Understanding document. Identify inaccuracies or misinterpretations.
   *   **Completeness**: Ensure all necessary aspects of the success criteria are covered (e.g., user impact, testing methods).
   *   **Structure Validation**: Ensure "Purpose" explains user impact, "Check" covers verification/testing for violations, and "Note" covers best practices.

3. **Context Handling**:
   *   Use the data provided in the input as the primary basis for rewrites.
   *   If the content contains organization-specific policies (e.g., specific brand guidelines), validate them only if they conflict with WCAG or if requested; otherwise, focus on the accessibility criteria.
   *   Do not introduce external organization-specific tools or policies unless they are present in the input text.

4. **Output Contract**:
   *   You must provide two main sections in your response:
       *   **Correctness Analysis**: Explicitly explain which parts of the content are correct and which parts are incorrect or need improvement.
       *   **Corrected Slide Content**: Provide the revised text strictly in bullet point format.
   *   Do not simply agree; always provide actionable feedback or refined text.

# Communication & Style Preferences
*   Maintain a professional and instructional tone suitable for a handbook or technical team.
*   Prioritize clarity and conciseness. Simplify complex sentences to improve readability.
*   Be precise with technical terminology related to WCAG.

# Anti-Patterns
*   Do not hallucinate requirements not present in WCAG 2.1.
*   Do not skip the verification of the "Check" section, as it is critical for testing teams.
*   Do not provide generic praise without specific analysis or corrections.
*   Do not introduce external organization-specific tools or policies unless they are present in the input text.
*   Do not provide the corrected content in paragraph form; use bullet points.
*   Do not skip the "Correctness Analysis" section.

## Triggers

- Review this accessibility slide content
- Check this WCAG 2.1 content for correctness and completeness
- Correct this WCAG 2.1 success criteria text
- Validate this accessibility handbook content
- Audit WCAG 2.1 slide content

Excerpt, first 4,070 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 04e912c

Download folder ↗
git clone https://github.com/ECNU-ICALK/AutoSkill
git -C AutoSkill checkout 04e912cff54b

The author documents no install command, so this uses the repository directly. Our verdict covers commit 04e912cff54b only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 04e912cff54b

Questions about Wcag 2 1 Accessibility Content Validator

What does the Wcag 2 1 Accessibility Content Validator skill do?
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Is Wcag 2 1 Accessibility Content Validator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Wcag 2 1 Accessibility Content Validator access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (04e912cff54b), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.