Ext Ops Panel
Open dashboard
Comparison

ai-instruct vs A11Y Toolkit

ai-instruct is a plugin bundle for AI coding tools published by ziniman. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). A11Y Toolkit is an MCP server published by kinti. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-17. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplaceai-instructA11Y Toolkit
Claude Code: claude-plugins-community Listed
Version: 2.0.6
Forks (GitHub): 1
Stars (GitHub): 29
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 5.8.0
Downloads/month (PyPI): 5 352
Downloads/week (PyPI): 672
Forks (GitHub): 0
Stars (GitHub): 2
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

ai-instruct vs A11Y Toolkit
Factai-instructA11Y Toolkit
Marketplaces that list it11
Stars (GitHub) (differs)29 (better)2 (worse)
Forks (GitHub) (differs)1 (better)0 (worse)
Last release (differs)Not published2026-10-17
Where it runs (differs)Installs as a plugin bundleOn your machine (a11y-toolkit)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)5Not a bundle
Licence (differs)Apache-2.0Not stated
Repository (differs)github.com/ziniman/ai-instructgithub.com/kinti/a11y-toolkit
Changes in the last 7 days (differs)02
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

ai-instruct

In its own words, on Claude Code: claude-plugins-community:

Five practical skills covering the domains developers most often Google when shipping a website. Each skill auto-loads only when relevant to the task: Web Accessibility on UI work, SEO/LLMO before launch, Core Web Vitals on performance issues, AWS SPA deploy on Amplify/CDK work, and Google Analytics 4 on tracking setup. Originally distributed as standalone markdown guides for any AI tool (also available via npx ai-instruct init); now packaged as a single Claude Code plugin for one-command install.

A11Y Toolkit

In its own words, on Official MCP Registry:

The accessibility layer for AI coding agents: audit, fix, document and watch - WCAG 2.2.

How to run each

ai-instruct As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install ai-instruct@claude-community

A11Y Toolkit As a local MCP server: PyPI package

Claude Code
claude mcp add --transport stdio a11y-toolkit -- uvx a11y-toolkit --from a11y-toolkit a11y-toolkit-mcp

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: ai-instruct · What it can do: A11Y Toolkit · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built