More room for your next idea. Membership from $9.99/month.Take a look

Accessibility Review Studiov1.0.0

Turn authorized HTML into a traceable accessibility worklist. Inspect source lines and bounded naming/structure checks, compare actual remediation with a baseline, keep removed pages separate and collect manual browser observations tied to exact source hashes.

No reviews yetFeatured

See what you can make

Jump to a momentExplore the workflow
Made with this SkillA source finding ledger and remediation comparison

Actual 20 → 2 source review · eight manual checkpoints

Open full example

What you get

A source finding ledger and remediation comparison

What you can make

  • Locate bounded HTML naming and structural findings with actual source lines and hashes.
  • Compare new, persisting and resolved defects while keeping removed pages separate.
  • Collect manual browser observations and export a source-bound remediation handoff.
Explore delivered files6 groups
  • index.html + report.json
  • findings.csv + remediation.md
  • review-input.json + sources/*.html.txt
  • baseline.json (when supplied)
  • manual-review.json (browser export)
  • delivery-manifest.json

Good fit

Developers and designers reviewing authorized source pages before and after a concrete correction.

DeveloperDesigner

Know the limits

Static HTML checks do not execute CSS or JavaScript and do not certify WCAG conformance.

About this skill

Capabilities: thirteen bounded static-source rule categories, relative file and line references, exact source excerpts/hashes, severity and text filters, new/persisting/resolved/out-of-scope comparisons, eight manual checkpoints, source-bound review imports and optional CI failure thresholds.

Deliverables: an original two-page Wayfinder source review from twenty initial findings to two remaining findings, interactive index.html, report JSON, findings CSV, remediation Markdown, inert source copies, editable input, optional baseline and SHA-256 manifest.

Read the full workflow

First run: Python 3.10+ standard library, offline. Run scripts/build-review.py against examples/site-before, then examples/site-after with the generated baseline report. Open the second report and inspect current and resolved source evidence.

Validation: actual before/after scans, eighteen verified source resolutions and two persisting findings, wrapper-stable matching, baseline/current hash separation, real browser filters and review downloads, stale-evidence rejection, traversal/symlink rejection, desktop/mobile layout and exact archive re-execution.

Version 1.0.0: original MIT workflow, scanner and review interface. This bounded HTML parser does not execute CSS or JavaScript and is not a live DOM scanner or WCAG certification. Anonymous element reordering needs manual reconciliation. Unperformed browser and assistive-technology checks remain not-run. $4.99 one-time; eligible active Premium membership includes this package.

Read skill facts →Choose a skill by task →
Accessibility review

FROM PACKAGE TO FIRST RESULT

Your first traceable accessibility review.

Generate a baseline from the fictional Wayfinder HTML, then compare the authored repair. The resulting room keeps eighteen resolved defects, two remaining findings and eight explicitly unperformed manual checks.

View example result
US$4.99 · MIT licensePython 3.10+ · offlineNo API key or paid provider
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/accessibility-review-studio

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.

  3. 03

    Run the included sample

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/accessibility-review-studio
python3 scripts/build-review.py --input examples/review.json --root examples/site-before --output ./review-before
python3 scripts/build-review.py --input examples/review.json --root examples/site-after --baseline review-before/report.json --output ./review-after
    Your first result

    Switch Current, Resolved and Removed from scope; filter rules/severity, inspect each actual source line and its own source hash. Download a manual-review template, record observations only after actual live checks, then rebuild with matching source hashes.

    Python 3.10+ standard library, offline. Bounded static HTML checks do not verify CSS, runtime DOM, contrast, screen readers or full WCAG conformance. Unique IDs or per-tag source order match findings; reordered anonymous elements need manual review. Pass/fail notes require actual observations and exact matching source hashes.

    If review-after already exists, change the output to ./review-after-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use Accessibility Review Studio at .agents/skills/accessibility-review-studio. Read SKILL.md and review scripts/build-review.py. Run examples/review.json into a new output folder and show me all generated files. Keep fictional sample content clearly labeled.

Ready to use your own facts?

Copy examples/review.json to a new input file, replace all fictional facts, and generate into a new folder. Review the content before using or publishing it; the generator does not independently verify claims.

Reviews0

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get Accessibility Review Studio?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

Compare access and pricing
Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

Codex setupClaude Code setupCursor setup
What files can this workflow generate?

The documented 1.0.0 workflow lists: index.html + report.json; findings.csv + remediation.md; review-input.json + sources/*.html.txt; baseline.json (when supplied); manual-review.json (browser export); delivery-manifest.json. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

Review all deliverablesInspect the working example
What should I check before using the result?

Python 3.10+ standard library, offline. Bounded static HTML checks do not verify CSS, runtime DOM, contrast, screen readers or full WCAG conformance. Unique IDs or per-tag source order match findings; reordered anonymous elements need manual review. Pass/fail notes require actual observations and exact matching source hashes.

Read the installation guideReview third-party notices

More skills to explore

View all skills
$4.99One-time purchase