By a8cteam51
Run automated functional, accessibility, and performance QA tests on WordPress sites using Playwright-powered browser automation, including WCAG 2.2 AA checks, multi-viewport design validation, and AI discovery evaluation.
Parse $ARGUMENTS into a URL and an optional environment type before doing anything else:
Parse $ARGUMENTS into a URL and an optional environment type before doing anything else:
Parse $ARGUMENTS into a URL and an optional environment type before doing anything else:
Merge the three QA reports into one comprehensive report by running:
Parse $ARGUMENTS into a URL and an optional environment type before doing anything else:
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin for testing WordPress sites. Run automated functional, performance, accessibility, and AEO audits against any live URL using real browser automation via Playwright MCP.
Kosh tests a site across four dimensions:
Each test visits 4–6+ pages, simulates real user behavior, and outputs a structured JSON report. A render script converts the JSON into a self-contained HTML report with color-coded severity, collapsible sections, and inline screenshots. The functional, performance, and accessibility test types can also be merged into one comprehensive report.
git clone https://github.com/a8cteam51/kosh.git
cd kosh
claude --plugin-dir .
On first run, Claude Code will ask you to trust this project's settings — accept the prompt. This pre-approves the Playwright browser tools so you don't get prompted for each one during a test.
Then run a test:
/kosh:functional-design https://example.com
/kosh:performance https://example.com
/kosh:a11y https://example.com
/kosh:aeo https://example.com
For detailed setup instructions (including troubleshooting), see the Getting Started guide.
commands/ Slash commands (/kosh:a11y, /kosh:aeo, /kosh:functional-design, /kosh:performance)
skills/ Full testing procedures for each command
schemas/ JSON schemas for report validation
scripts/ Report generation and merge scripts
hooks/ Session hook that creates reports/data/ on startup
.mcp.json Playwright MCP server configuration
.claude/ Project settings and Playwright tool permissions
Every test type emits a JSON report with this common frame:
{
"url": "https://example.com",
"websiteName": "Example",
"timestamp": "2026-03-20T10:00:00.000Z",
"visitedPages": ["https://example.com", "..."],
"issues": {
"critical": [],
"high": [],
"medium": [],
"low": []
}
}
Beyond that frame, each test type has its own shape — see schemas/ for the authoritative per-type definitions:
qa-report-functional-schema.json, qa-report-performance-schema.json, qa-report-accessibility-schema.json) — mobile and desktop blocks carry the viewport-specific findings (page metadata, network errors, contrast failures, etc.).qa-report-aeo-schema.json) — criteria block with eight criterion sub-blocks (each containing pass / partial / fail / N/A signal evaluations), a top-level summary with signal counts, plus siteType, siteTypeConfidence, and a technicalNotes.applicableSchemas relevance map.npx claudepluginhub a8cteam51/kosh20 SEO/GEO skills and 5 commands on one shared contract for keyword research, content creation, technical audits, schema markup, monitoring, quality gates, entity truth, and campaign memory.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development