Testing Skills Hub

Structures multi-step development with plans, subagents, and TDD.

Audits UI code against 100+ accessibility and UX rules.

Applies 57 performance rules to React and Next.js code.

Tests your local app in a real browser using Playwright.

Runs CodeQL and Semgrep analysis for vulnerability detection.

Cleans up recently written code without changing behavior: readability only, no logic changes.

AI-ready PageSpeed Insights and Lighthouse CLI for Core Web Vitals audits, performance fixes, SEO optimization, and before/after verification.

Loop engineering delivery harness for turning Codex, Claude Code, OpenCode, and other coding agents into repeatable software delivery systems.

Practical loop engineering patterns, starters, and CLIs for AI coding agents, including loop-audit, loop-init, loop-cost, and production loop checklists.

Agent-agnostic loop engineering framework for play-test-fix-verify-improve cycles with logs, heartbeats, baselines, guardrails, and auditable stop conditions.

Skill family for loop engineering with loop-scan, loop-generate, loop-verify, loop-list, loop-run, and loop-status for Claude Code and future Codex ports.

Production-grade frontend design skill for auditing, redesigning, polishing, and implementing interfaces across visual hierarchy, accessibility, responsive behavior, motion, UX copy, and design systems.

Edit and harden computer-science conference papers through direct manuscript editing, adversarial multi-reviewer assessment, consensus-gated revisions, and an optional unattended review-revise loop.

Generate clean 2D game sprites and animation atlases through a component-row pipeline with chroma-key cleanup, frame extraction, deterministic atlas composition, QA reports, and curation tools.

Test local web applications using Playwright

Connect AI agents to 1000+ external apps with managed authentication

GitHub workflow patterns for PRs, code review, branching

Better Auth authentication providers

Create authentication setup with Better Auth

Email and password authentication with Better Auth

Two-factor authentication with Better Auth

Acceptance test patterns for Terraform providers using terraform-plugin-testing

Run acceptance tests for Terraform providers using Go's test runner

Built-in testing framework for Terraform configurations with .tftest.hcl files

Content A/B testing and experimentation workflows

API keys and wallet-based Venice authentication

Comprehensive Cloudflare platform skill covering Workers, Pages, storage, AI, networking, security, and IaC

Review and author Workers code against production best practices and wrangler.jsonc conventions

Managed Postgres with deploy preview branching

Shared authentication, global flags, and output formatting

Build and distribute Expo dev clients locally or via TestFlight

Prompt for clarification on ambiguous requirements

Deep architectural context via ultra-granular code analysis

Smart contract security toolkit with vulnerability scanners for 6 blockchains

Search and extract data from Burp Suite project files

Diagnose and fix Claude in Chrome MCP extension connectivity issues

Detect compiler-induced timing side-channels in crypto code

Index and search culture documentation

Security-focused diff review with git history analysis

DWARF debugging format expertise

Identify state-changing entry points in smart contracts

Scan Android APKs for Firebase misconfigurations and security vulnerabilities

Detect insecure default configurations like hardcoded secrets, default credentials, and weak crypto

Modern Python tooling with uv, ruff, ty, and pytest best practices

Property-based testing for multiple languages and smart contracts

Create and refine Semgrep rules for vulnerability detection

Port existing Semgrep rules to new target languages with test-driven validation

Identify error-prone APIs and dangerous configurations

Specification-to-code compliance checker for blockchain audits

Static analysis toolkit with CodeQL, Semgrep, and SARIF

Testing Handbook skills: fuzzers, static analysis, sanitizers

Find similar vulnerabilities via pattern-based analysis

Set up Sentry in any language or framework — detects platform and routes to the right SDK

End-to-end Sentry workflow: fix production issues and review code with Sentry context

Find and fix Sentry issues with stack trace, breadcrumb, and trace context via MCP

Review code changes using Sentry issue and trace context

Review PR comments from Seer Bug Prediction and Sentry feedback

Create Sentry alerts with email, Slack, PagerDuty, Discord, and more

Configure advanced Sentry features: AI monitoring, OTel pipelines, and alerts

Configure the OpenTelemetry Collector with Sentry Exporter

Instrument OpenAI, Anthropic, Vercel AI, LangChain, Google GenAI, and Pydantic AI

Upgrade the Sentry JavaScript SDK across major versions

Create a new Sentry SDK skill bundle for a platform

Full Sentry SDK setup for Android (Kotlin and Java)

Full Sentry SDK setup for browser JavaScript

Full Sentry SDK setup for Cloudflare Workers, Pages, Durable Objects, Queues, and Workflows

Full Sentry SDK setup for Apple platforms (iOS, macOS, tvOS, watchOS, visionOS)

Full Sentry SDK setup for .NET (ASP.NET Core, MAUI, WPF, WinForms, Blazor, Azure Functions)

Full Sentry SDK setup for Elixir, Phoenix, Plug, LiveView, Oban, and Quantum

Full Sentry SDK setup for Flutter and Dart across all platforms

Full Sentry SDK setup for Go (net/http, Gin, Echo, Fiber, FastHTTP, Iris, Negroni)

Full Sentry SDK setup for NestJS with Express or Fastify, GraphQL, microservices

Full Sentry SDK setup for Next.js 13+ (App Router and Pages Router)

Full Sentry SDK setup for Node.js, Bun, and Deno

Full Sentry SDK setup for PHP, Laravel, and Symfony

Full Sentry SDK setup for Python (Django, Flask, FastAPI, Celery, Starlette, AIOHTTP, Tornado)

Full Sentry SDK setup for React Native and Expo

Full Sentry SDK setup for React (React Router v5-v7, TanStack Router, Redux, Vite, webpack)

Full Sentry SDK setup for Ruby (Rails, Sinatra, Rack, Sidekiq, Resque)

Full Sentry SDK setup for Svelte and SvelteKit

Review and create distinctive frontend interfaces

Microsoft Entra ID authentication

Playwright Testing workspace management

Cryptographic key management

Entra ID custom auth events handler

Microsoft Entra ID authentication

Cryptographic key management

Secret management for passwords and keys

Microsoft Entra ID authentication

Microsoft Entra ID authentication

Microsoft Entra ID authentication

Playwright tests at scale on Azure

Restore and fix image quality — deblur, denoise, fix faces, restore documents

Plugin architecture, hooks, settings API, security

Capability-based permissions and REST API authentication

Build and test web games iteratively using Playwright with time-stepping

Address review and issue comments on open GitHub PRs via CLI

Debug and fix failing GitHub Actions PR checks using log inspection

Read, create, and review PDFs with layout and visual formatting integrity

Review code for language-specific security vulnerabilities

Map people-to-file ownership, compute bus factor, and identify risks

Generate repo-specific threat models identifying trust boundaries

Inspect Sentry issues, summarize production errors, and pull health data

Deploy applications and websites to Vercel with preview or production options

Build, review, and architect ASP.NET Core apps (Blazor, MVC, Minimal APIs, etc.)

Persistent browser and Electron interaction via js_repl for iterative UI debugging

Plan and implement A/B tests or experiments for any digital experience

Expand a core idea into multiple distinct ad angles for creative testing

Remove vague, corporate, or AI-sounding language and replace it with clear, specific, human wording

Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereum

Place and manage spot trading orders on Binance via API key authentication, supporting mainnet and testnet

Add authentication to native Android apps using the Auth0 SDK

Add authentication to Angular apps using @auth0/auth0-angular

Add JWT access token validation to ASP.NET Core APIs

Add session-based authentication to Express.js apps

Add session-based authentication to Fastify web apps

Secure Fastify API endpoints with JWT Bearer token validation

Add Multi-Factor Authentication to Auth0-powered apps

Migrate users and auth flows from other providers to Auth0

Add authentication to Next.js apps

Add Auth0 authentication to Nuxt 3/4 apps with encrypted cookie sessions

Detect your framework and scaffold Auth0 integration automatically

Add authentication to React SPAs using @auth0/auth0-react

Add authentication to React Native and Expo mobile apps

Add authentication to Vue.js apps

Run adversarial UI tests by analyzing git diffs in a real browser

Fetch unresolved CodeRabbit review comments from GitHub PRs and apply fixes

Run AI-powered code reviews through the CodeRabbit CLI

Query Datadog APM data directly from your editor

Look up Datadog documentation via the LLM-optimized docs index

Analyze production LLM traces and generate evaluators

Root-cause LLM app failures using eval traces

Analyze single or comparative LLM experiment results

Search, filter, and archive Datadog logs through pup CLI

Manage Datadog monitors through the pup CLI

Rust-based CLI (pup) for talking to the Datadog API

Set up Firebase Authentication with sign-in providers

Audit Firestore security rules and flag risky patterns

Implement unit, widget, and integration tests

Evaluate channels using unit economics and recommend scale/test/kill decisions

Turn initiatives into testable hypotheses with measurable success metrics

Define lightweight validation experiments to test hypotheses

Plan customer interviews using Mom Test style based on research goals

Generate opportunities and solutions and recommend proof-of-concept tests

Analyze A/B test results with statistical significance and recommendations

Create comprehensive test scenarios from user stories

Design experiments to test assumptions for existing products

Draft privacy policies with GDPR compliance considerations

PM resume review against 10 best practices including XYZ+S formula

iOS development with UIKit, SnapKit, and SwiftUI covering navigation, Dark Mode, and HIG compliance

CEO/Founder plan review with four modes: Expansion, Selective Expansion, Hold Scope, Reduction

Eng Manager review: lock in architecture, data flow, diagrams, edge cases, and tests

Senior Designer review: rates each design dimension 0-10, explains what a 10 looks like, AI Slop detection

Designer Who Codes: visual audit then fixes with atomic commits and before/after screenshots

Staff Engineer code review: finds bugs that pass CI but blow up in production

Systematic root-cause debugging: no fixes without investigation, traces data flow, tests hypotheses

QA Lead: test your app, find bugs, fix them with atomic commits, auto-generate regression tests

QA Reporter: same methodology as /qa but report only, no code changes

Chief Security Officer: OWASP Top 10 + STRIDE threat model with zero false-positive exclusions

Release Engineer: sync main, run tests, audit coverage, push, open PR

Real Chromium browser for QA: real clicks, real screenshots, ~100ms per command

One command, fully reviewed plan: runs CEO → design → eng review automatically

Second Opinion via OpenAI Codex CLI: review, adversarial challenge, and open consultation

Edit Lock: restrict file edits to one directory while debugging

Self-Updater: upgrade gstack to latest version

Comprehensive quality review across performance, accessibility, SEO, and best practices categories

Loading speed, runtime efficiency, and resource optimization

LCP, INP, and CLS-specific optimizations

WCAG compliance, screen reader support, and keyboard navigation

Search engine optimization, crawlability, and structured data

Security, modern web APIs, and code quality patterns

Set up the MongoDB MCP server with authentication and connection configuration

Build, operate, and debug Atlas Stream Processing pipelines with Kafka, S3, and Lambda integrations

CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

Code style and quality rules for Megatron Bridge — ruff configuration, naming conventions, type hints, mypy rules, docstrings, copyright headers, logging, and the code review check...

Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures.

External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron poli...

Structured framework for verifying numerical parity of HFMCore weight conversions.

Testing reference for Megatron Bridge — unit and functional test layout, tier semantics (L0/L1/L2/flaky), script conventions, running tests locally, adding/moving/disabling tests,...

External verl end-to-end validation workflow for Megatron-Bridge model/provider changes.

Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

Test system for Megatron-LM.

Run commands inside a remote Docker container via the file-based command relay (tools/debugger).

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.

>- Use when debugging a Nemo Gym run or reward profiling job.

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery.

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI.

Interactive code review for NVIDIA-NeMo/RL pull requests.

Testing conventions for NeMo-RL.

Finds open GitHub PRs with security and priority-high labels, links each to its issue, detects duplicates (multiple PRs fixing the same issue), and presents a table of review candi...

Performs a comprehensive security review of code changes in a GitHub PR or issue.

Presents a risk framework for every configurable security control in NemoClaw.

> Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline).

> Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.

>- Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability.

Use when adding, modifying, optimizing, or debugging CuTile autotuning code.

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI).

Deploy, debug, or tear down any VSS profile using a compose-centric workflow — config (dry-run) with env overrides, review resolved compose, then compose up.

Generates security-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Google Cloud Well-Architected Framework (WAF).

Understand CVEs, check product lifecycle status, gather diagnostics, and file support cases at the right severity — essential Red Hat skills for everyday operations.

Discover, remediate, and verify CVEs across your RHEL fleet — orchestrating Red Hat Lightspeed and Ansible Automation Platform through a single workflow.

Provision, inventory, and report on OpenShift clusters — spanning Assisted Installer, OCM, ROSA, ARO, and kubeconfig fleets — through a single conversational workflow.

Manage the full VM lifecycle on OpenShift Virtualization — create, clone, snapshot, restore, rebalance, and report — through a single conversational workflow.

Creates, updates, and fixes Cypress E2E and component tests.

Explains Cypress E2E and component tests, and answers questions about Cypress use and behavior.

Search and extract Cypress information from official documentation.

Agent skills for Qdrant vector search, covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, and Java

Generate animation-rich HTML presentations with visual style previews

Debug WhatsApp delivery issues and run health checks

Analyze Rails apps and provide upgrade assessments

Generate marketing screenshots with Playwright

Terraform and OpenTofu patterns: testing, modules, state, CI/CD.

AWS development with infrastructure automation and cloud architecture patterns

AI-powered incident response with ML similarity matching, solution suggestions, and on-call coordination. Requires [Rootly MCP Server](https://github.com/Rootly-AI-Labs/Rootly-MCP-server)

Control iOS Simulator

Audit iOS App against Accessibility norms

Scan iOS/macOS projects to catch common mistakes that lead to App Store rejection before submission

Code review and PR autofix workflows for coding agents

Execute safe read-only SQL queries against PostgreSQL databases

Autonomous multi-step research using Gemini Deep Research Agent

Web fuzzing with ffuf

Browser automation with Playwright

Opinionated, evolving constraints to guide agents when building interfaces

Generate hand-drawn Excalidraw diagrams from a prompt — animated SVG, hosted edit link, and PNG export. Works with Claude Code, Codex, Gemini CLI, and any agent supporting standard skill paths

UI/UX design patterns and best practices

300+ design rules from Apple HIG, Material Design 3, and WCAG 2.2 for cross-platform apps

Vector-powered CLI for semantic file search with a Claude/Codex skill

Write tests before implementing code

Development using multiple sub-agents

Methodical problem-solving in code

Investigate and identify fundamental problems

Collaborative testing approaches

Identify ineffective testing practices

Complete Git code branches

Initiate code review processes

Process and incorporate code feedback

Manage multiple Git working trees

Validate work before finalizing

Manage conditional pauses or delays

Create and manage command structures

Develop and document capabilities

Git and GitHub workflow skills for commits, PRs, and code reviews

Pairwise test generation

Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patterns, and CLI tool orchestration (gh, vercel, supabase)

Makepad UI development skills for Rust apps: setup, patterns, shaders, packaging, and troubleshooting.

Handle long-context tasks (100+ files, 50k+ tokens) through recursive decomposition strategies based on RLM research

Modern SwiftUI best practices and iOS 26+ Liquid Glass adoption

Modern Swift/SwiftUI best practices

Swift Server development guidance with linting tool for best practices

Automate App Store deployments and management using ASC CLI

Skills for building and running software startups, apps, and SaaS

Cost-optimized model routing based on task complexity

Three.js skills for creating 3D elements and interactive experiences

High-agency frontend skill that gives AI good taste with tunable design variance, motion intensity, and visual density to stop generic UI slop

70+ production-tested Playwright automation testing patterns: E2E, POM, CI/CD, migrations, CLI

Comprehensive PR code review using specialized agents: bug-hunter, security-auditor, code-quality-reviewer, contracts-reviewer, historical-context-reviewer, test-coverage-reviewer

Self-refinement loop that forces the LLM to reflect on previous output and correct itself.

Spec-driven development workflow that transforms prompts into production-ready implementations through structured planning, architecture design, and LLM-as-a-Judge based quality gates.

Domain-driven development skills that also include Clean Architecture, SOLID principles, and design patterns.

Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development.

Applies continuous improvement methodology with multiple analytical approaches, based on Japanese Kaizen philosophy and Lean methodology.

Audit LLM eval pipelines and surface problems

Systematically identify failure modes in LLM pipelines

Create diverse synthetic test inputs for LLM evals

Design LLM-as-Judge evaluators for subjective criteria

Calibrate LLM judges against human labels

Evaluate RAG retrieval and generation quality

Anti-over-engineering skill with 5 variants and 10 platforms

Build annotation interfaces for reviewing LLM traces

17 dev workflow skills: PRD writing, TDD, codebase architecture, git guardrails, issue triage, refactoring plans, and more

753 cybersecurity skills across 38 domains: cloud security, pentesting, red teaming, DFIR, malware analysis, threat intel, and more (MITRE ATT&CK mapped)

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits

Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes

Human-like TTS workflows with local/cloud APIs and app delivery

Collaborate with Codex from Claude Code

Rails 8 conventions for consistent production code changes

Self-improving task orchestration for AI agent systems

11 skills by Matteo Collina: Node.js, Fastify, TypeScript, OAuth, Git/GitHub, ESLint neostandard, documentation (Diataxis), Node.js core internals, skill optimizer, and more

Interactive codebase knowledge graphs via multi-agent LLM analysis

Diagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent

TestMu AI (Formerly LambdaTest) Skills is a curated collection of Agent Skills that teach AI coding assistants how to write production-grade test automation.

A skills governed plug-and-play harness for staged, test-driven skill orchestration

Skills that let agents code and test against your Kubernetes cluster using mirrord

UX and design system skills: hierarchy, typography, accessibility, interactions

Evidence-driven method pack for AI coding agents

Build security Blue Books for sensitive apps

Multi-layered security approaches

Epistemic quality verification for RAG systems

Autonomous ML research with cross-model review loops and GPU deployment

Security skill suite with drift detection, automated audits, and skill integrity verification

Helps write secure code by preventing common vulnerabilities including IDOR, XSS, SQL injection, SSRF, and weak authentication, approaching code from a bug hunter's perspective

Ecommerce CSV to business review with KPI decomposition

Russian text quality: ~1,040 rules for typography, info-style, editorial, UX writing, business correspondence. Cross-platform: Claude Code, Codex CLI, Gemini CLI, Cursor.

AI-powered KiCad electronics design review and analysis

Agent skill listed in Awesome Agent Skills.