Reusable closed loop for exploratory QA over any live web app, driven by Claude via the Chrome DevTools MCP with four expert lenses (QA, Product, Engineering, Security). Read-only on production, writes one markdown report per finding immediately, and hands reviewed findings to a triage agent that emits prioritized tasks + per-fix PLAN stubs.
Drives Claude via the Chrome DevTools MCP to do exploratory QA over ANY live web app with four expert lenses (QA, Product, Engineering, Security). Loads per-screen doc context before navigating, exercises scenarios from the screen manifest, and writes ONE markdown report per finding immediately (never loses progress). Read-only on production. Target app, base URL and screen manifest are configured per repo (chrome-qa-loop.config.json). Use when running the Chrome QA loop or when asked to "explore", "QA", or "test the live app in the browser".
Reads a reviewed QA report folder (from chrome-qa-explorer), dedupes and prioritizes findings (P0–P3), and emits a prioritized task list plus per-fix PLAN.md stubs ready for a Feature-Development loop. The bridge between human review and implementation. Product-agnostic — reads paths from chrome-qa-loop.config.json. Use after you've reviewed a QA run's reports and want to turn accepted findings into actionable work.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Build, Launch, and Scale with AI-Native Architecture.
Lemon AI Hub is a centralized and optimized repository to manage AI Skills and Plugins across different local agents (Claude Code, Codex, OpenCode, Agy). It is the technical foundation of the Lemon.dev ecosystem, designed by Anderson Lima to help founders and developers bridge the gap between AI-generated code and production-ready products.
This project is based on and inspired by Peter Steinberger's pattern (steipete/agent-scripts), but structured with a focus on .claude and shared with other providers via transparent symbolic links.
The best code is invisible—it works, scales, and converts. Lemon AI Hub embodies this by providing:
This repository ships a marketplace manifest (.claude-plugin/marketplace.json) so you can install its plugins directly inside Claude Code.
Inside a Claude Code session, run the slash command:
/plugin marketplace add Andersonlimahw/lemon-ai-hub
Open the interactive installer, or install a plugin by name using the plugin@marketplace syntax:
/plugin # browse the catalog UI
/plugin install spotify-squad@lemon-ai-hub
/plugin install agentic-value-loops@lemon-ai-hub
| Plugin | Description |
|---|---|
a11y-audit | WCAG 2.1 AA/AAA accessibility audit for web components, pages, and apps. Detects contrast failures, missing ARIA labels, keyboard trap issues, focus order problems, and screen-reader gotchas. Use when user wants to audit accessibility, fix a11y warnings, prepare for compliance review, or validate UI against WCAG standards. |
a11y-guardian | Accessibility guardian plugin. Continuous WCAG 2.1 AA/AAA compliance monitoring for web projects. Integrates static analysis of React/Vue/HTML components, contrast ratio checks, ARIA validation, keyboard navigation audit, and generates actionable HTML reports. Pairs with a11y-audit skill. |
agent-sdk-dev | A comprehensive plugin for creating and verifying Agent SDK applications in Python and TypeScript. |
agentic-value-loops | Agentic Value Loops plugin — Continuous improvement engine that ships verified increments with constant quality. Includes loops for Feature Development, Maintenance & Security, Documentation Sync, and AI Tuning. |
ai-workspace-orchestrator | Project and workspace AI setup orchestrator. Builds AGENTS.md/CLAUDE.md contracts, optional global or project skills, Spotify Squad-style agent/subagent topology, and adversarial setup review for single apps, monorepos, and multi-domain workspaces. |
api-test-loop | API Test Loop plugin — Automated REST API validation loop. Executes HTTP requests via CURL, logs findings for REST best practices (method, input/output format, security, performance, docs), and implements backend fixes. |
app-store-connect-api | Apple Store Connect API Expert Agent and Skills. Provides comprehensive tools and knowledge for interacting with the App Store Connect API, covering domains like TestFlight, In-app purchases, Subscriptions, App management, and Provisioning. |
apple-store-release-agent | AI release agent for the Apple App Store. Audits Expo/React Native iOS builds, App Store metadata, App Privacy readiness, TestFlight, RevenueCat/IAP, Firebase, i18n parity, screenshots, and review notes, then emits a GO/GO_WITH_WARNINGS/NO_GO decision with full risk + privacy + IAP reports. Never submits to App Review or alters the store without explicit human approval. Generic core with presets for Expo/RN/Firebase/RevenueCat apps. |
async-advisor | Async and concurrency static analysis plugin. Scans TypeScript/JavaScript codebases for race conditions, unbounded Promise.all, missing AbortController, swallowed rejections, and N+1 async patterns. Runs as a pre-commit hook or CI check and provides inline fix suggestions. |
async-patterns | Async and concurrency pattern advisor for JavaScript/TypeScript, Python, Go, and Rust. Identifies race conditions, missing error handling in promise chains, N+1 async anti-patterns, unbounded parallelism, and missing cancellation. Recommends correct patterns: Promise.all, p-limit, AbortController, AsyncLocalStorage, worker threads. Use when async code has bugs, timeouts, or memory leaks. |
npx claudepluginhub andersonlimahw/lemon-ai-hub --plugin chrome-qa-loopIncident response runbooks, on-call workflows, and postmortem templates. Generates severity-tiered runbooks, communication templates, timeline reconstruction, and blameless postmortem docs. Use when user is in an incident, doing on-call prep, writing a postmortem, or building incident response playbooks.
Load testing setup, execution, and analysis with k6, Artillery, or Locust. Generates test scripts, defines VU ramp-up scenarios, interprets p99 latency and error rate results, and suggests infrastructure fixes. Use when user wants to load test an API, check throughput limits, validate SLO headroom, or diagnose performance under traffic.
Database index optimization advisor for PostgreSQL, MySQL, and SQLite. Analyzes slow queries, missing indexes, unused indexes, and over-indexed tables. Generates CREATE INDEX statements with EXPLAIN ANALYZE estimates. Use when queries are slow, p99 DB latency spikes, or when reviewing a new schema.
AI release agent for Google Play Store: audits Android/Expo/React Native/Firebase/RevenueCat before submission. Validates build readiness (app.json, eas.json, AAB, versionCode), Play Console metadata, Data Safety Form, Android permissions, RevenueCat/IAP, i18n parity (PT/EN/ES), policy-risk copy, internal/closed testing and staged rollout. Generates reports + GO/NO-GO checklist. Never publishes or rolls out without explicit human approval. Use when preparing an Android app for Google Play, auditing a submission, generating release notes, validating Data Safety or permissions, or running a release go/no-go.
>
Automated web QA from Claude Code: /qa:test drives browser-based test runs against a running application.
Run an autonomous QA review of a web UI by invoking the local qa-cli command via Bash: structured reviews (accessibility, usability, correctness) and quick visual checks on live pages.
Quality assurance and testing agents for accessibility auditing, API testing, performance benchmarking, Playwright automation, test architecture, and workflow optimization
QA skills for accessibility-testing domain.
AI 測試大師 — v1.1 QA testing skill backed by an MCP server. 22 tools (21 v1.0-frozen + analyze_stream): run / generate / debug / harden software tests via mk-qa-master. Includes the AI Visual Challenge Solver (reCAPTCHA / hCaptcha), OWASP API Security Top 10 scanner, universal qa_plan + verify bookend across 5 core tools, and the v1.1 Edge AI Runner (RTSP + YOLO via the [edge] extras). Same skill folder loads in Claude Code, Codex, OpenClaw, and Hermes.
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs with real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a Playwright sweep. Use after implementation to find typography, wrapping, overlap, overflow, responsive, route, authorization-state, overlay, map, transient-state, data-visualization, runtime-label, browser-output, file-dialog, PDF/print, or Electron-shell defects. Not for greenfield UI design, design-system extraction, general QA-program setup, or nonvisual debugging.