Index of every page on this site: llms.txt
All skills
Run it yourself

Audits HTML documents for accessibility tree integrity, semantic tag hygiene, and agent extractability affordances. Identifies structural bottlenecks that impair autonomous web agents and LLM scrapers. Use when diagnosing why a brand is missing from AI assistants or when evaluating agent actionability

  • 3 files
  • 10.7 KB
  • Apache-2
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/tejasshukla2007/brand-ai-readiness-audit/a11y-extractor-audit

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈81 tokens for metadata: the name and description. ≈531 when used: this file. ≈183 more on demand in 1 file.

Description uses 4.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈334 characters, or 4.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Semantic HTML & Accessibility Tree Audit

When to Use

Execute this skill during a brand discoverability and engagement audit to evaluate whether an AI assistant, business agent (UCP), or RAG crawler can parse text hierarchies and interact with page controls.

Inputs

  • html_content: The raw DOM string of the audited page.
  • url: Target webpage URL.

Procedure

  1. Read the provided raw HTML document strictly in-memory to minimize I/O overhead.
  2. Execute the bundled audit script by piping the HTML content into it via standard input. Run the exact following bash command: echo "$html_content" | python3 scripts/a11y_extractor_check.py
  3. The script will scan the document <head> for UCP/ACP agentic commerce feeds, compute static accessible names for interactive nodes, and verify structural landmarks (<main>, <article>, heading monotonicity).
  4. Do not alter or summarize the script's output.
  5. Output the exact findings mathematically as generated by the script.

Deterministic Grading Rubric

You must assign severities and generate findings strictly according to this matrix based on the JSON output from a11y_extractor_check.py.

Condition from Script Output Finding Title Severity Priority
Interactive controls (buttons, links, inputs) lack an accessible name (no aria-label, visible text, or alt) Nameless Interactive Controls (Agent Blockers) critical (if no commerce feed) / high critical / high
Document lacks <main> or <article> tags Missing Core Semantic Container (<main> or <article>) high high
Document has exactly 0 <h1> tags Missing Entity Anchor (<h1>) high high
Document has more than 1 <h1> tag Multiple Entity Anchors (Ambiguous <h1>) medium medium
Heading levels skip ranks (e.g., h2 followed directly by h4) Fragmented Heading Hierarchy medium medium

Allowed Tools

  • bash (executing bundled script scripts/a11y_extractor_check.py)

Output

Emit only a valid JSON array matching the exact structure dictated in references/finding_schema.json.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 1b012a3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 2 months ago

README badge

README badge for tejasshukla2007/brand-ai-readiness-audit/a11y-extractor-audit