Claude Code Plugins

Best Plugins for
QA & SDET Engineers

Supercharge Claude Code with skills that make test automation, debugging, and AI-assisted QA faster, smarter, and tighter.

7 Plugins
35+ Skills
75% Token Savings (Caveman)
1 Script to install all

Contents

qaskills.sh — Install Everything

One script to install all essential Claude Code plugins for QA/SDET work. Run these install commands from within Claude Code.

qaskills.sh

Copy these commands into Claude Code to get the full QA plugin stack. Each /plugin install command runs in your Claude Code terminal.

🧰
bash — qaskills.sh
#!/usr/bin/env bash # ───────────────────────────────────────────────────────── # qaskills.sh — Claude Code Plugin Installer for QA/SDET # Run each line inside Claude Code (not in your shell) # ───────────────────────────────────────────────────────── # 1. Superpowers — full dev methodology (TDD, agents, plans) /plugin install superpowers@claude-plugins-official # 2. Caveman — ~75% token savings, terse mode for daily use /plugin install caveman@caveman # 3. Frontend Design — bold, distinctive UI generation /plugin install frontend-design@claude-plugins-official # 4. Everything Claude Code — coding standards + security + TDD patterns /plugin install everything-claude-code@everything-claude-code # 5. MCP Server Dev — build MCP tools that connect to any API /plugin install mcp-server-dev@claude-plugins-official # 6. Skill Creator — write your own reusable skills /plugin install skill-creator@claude-plugins-official # 7. Playwright — official Playwright testing assistant /plugin install playwright@claude-plugins-official
💡
Pro tip — scope your installs

Add --scope user to install globally across all projects, or --scope project to pin to one repo. Default is user scope. Use /plugin list to verify installed plugins.

Superpowers

A complete software development methodology baked into Claude Code. Superpowers intercepts every task — exploring intent, writing specs, building plans, executing via subagents, and reviewing output. The most impactful single install.

superpowers@claude-plugins-official

Full-stack dev methodology: brainstorm → spec → plan → TDD → parallel agents → review → verify. Each skill triggers automatically at the right moment. You don't need to invoke them — Claude does.

14 Skills Official Auto-triggers v5.1.0
install
/plugin install superpowers@claude-plugins-official
🧠
brainstorming

Triggers before ANY creative work. Explores user intent and requirements before a single line of code is written.

auto — creative tasks
📋
writing-plans

When you have a spec, converts it to a step-by-step implementation plan clear enough for any subagent to follow.

auto — before multi-step tasks
🧪
test-driven-development

Enforces true red/green TDD. Write test first, fail it, implement, pass. No exceptions.

auto — any feature/bugfix
🔍
systematic-debugging

Structured root-cause analysis before any fix is proposed. No shotgun debugging.

auto — any bug or test failure
🤖
subagent-driven-development

Dispatches parallel subagents to execute independent tasks from a plan. Hours of autonomous work without deviation.

/subagent-driven-development
dispatching-parallel-agents

When 2+ tasks are independent — spawns concurrent agents, merges results. Cuts wall-clock time dramatically.

auto — 2+ independent tasks
verification-before-completion

Forces verification commands to run before any "done" claim. Evidence before assertions — always.

auto — before any PR/commit
🌿
using-git-worktrees

Isolates feature work in a clean git worktree before executing plans. No cross-contamination of in-progress work.

auto — before plan execution
👁️
requesting-code-review

Structured code review request. Ensures the reviewer gets all context: what changed, why, what to watch for.

auto — after task completion
📝
receiving-code-review

Before implementing review feedback — rigorously checks if feedback is technically correct. No blind agreement.

auto — when feedback arrives
🚀
finishing-a-development-branch

When implementation is done and tests pass — guides merge, PR creation, or cleanup decision.

auto — end of feature branch
🛠️
writing-skills

Create your own reusable skills: structure, triggers, content format, deployment and verification.

/writing-skills
Why Superpowers matters for QA

The TDD + systematic-debugging + verification-before-completion trio prevents the #1 QA failure mode: tests that pass locally but lie. Superpowers enforces discipline at the skill level, not the prompt level.

Caveman — Why Use Many Token When Few Do Trick

Caveman mode cuts Claude's output tokens by ~75% while keeping every technical detail. Same fix, 75% fewer words. Brain still big. Three intensity levels, terse commits, compressed reviews, and a cavecrew of specialized subagents.

🪨

caveman@caveman

Ultra-compressed communication mode by Julius Brussee. Cuts token usage ~75% via three intensity levels (lite, full, ultra), plus skills for terse commits, compressed reviews, lifetime token stats, and the CaveCrew subagent system.

7 Skills 3 CaveCrew Agents ~75% token savings Community
install
/plugin install caveman@caveman

Before / After

🗣️ Normal Claude (69 tokens)

"The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time..."

🪨 Caveman Claude (19 tokens)

"New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo."

🪨
caveman

Core mode. Three levels: lite (drop filler), full (fragments OK), ultra (minimal grunt). Auto-switches off for security warnings and irreversible ops.

/caveman · /caveman lite · /caveman ultra
📦
compress

Compress CLAUDE.md, todos, preferences into caveman format. Cuts ~46% of input tokens per session on memory files.

/compress
💬
caveman-commit

Ultra-terse commit messages. Conventional Commits format. Subject under 50 chars. Body only when "why" is non-obvious.

/caveman-commit
🔎
caveman-review

Ultra-compressed code review. One line per finding: location, problem, fix. No praise. No scope creep. Severity-tagged.

/caveman-review
📊
caveman-stats

Shows real token usage and estimated savings for the current session. Reads directly from the Claude Code session log.

/caveman-stats
caveman-help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode.

/caveman-help
👥
cavecrew

Decision guide for delegating to 3 specialized subagents: investigator (locate code), builder (surgical edits), reviewer (diff review).

/cavecrew
🪨
CaveCrew agents for QA workflows

cavecrew-investigator — read-only code locator, great for "where is X defined". cavecrew-builder — surgical 1-2 file edits, perfect for typo fixes and single-function rewrites. cavecrew-reviewer — diff/branch reviewer with severity-tagged findings.

Intensity Levels

LevelCommandWhat changesToken savings
lite/caveman liteDrop filler words and pleasantries only~30%
full (default)/cavemanDrop articles, fragments OK, short synonyms~75%
ultra/caveman ultraMinimal output, grunt-level compression~85%

Frontend Design

One skill that makes Claude produce production-grade UIs instead of generic AI-looking interfaces. Bold aesthetic choices, distinctive typography, high-impact animations. Critical for practice pages and dashboards.

🎨

frontend-design@claude-plugins-official

When Claude starts frontend work, this skill activates automatically. It picks a clear aesthetic direction and implements with meticulous attention to detail — bold type, real color palettes, context-aware layouts. No more grey-box Bootstrap defaults.

1 Skill Official (Anthropic) Auto-triggers
install
/plugin install frontend-design@claude-plugins-official
🎨
frontend-design

Generates distinctive, production-grade frontend code. Triggers on "create a dashboard", "build a landing page", "design a settings panel". Avoids generic AI aesthetics.

auto — any UI task
🎨
QA use case — practice page builder

When building TTA practice pages (forms, tables, dialogs), frontend-design ensures each page has a distinct visual identity instead of cookie-cutter Bootstrap layouts. Students recognize the target elements faster.

example prompts
# These prompts auto-trigger the frontend-design skill: "Create a QA dashboard for test run metrics" "Build a login form practice page with dark mode" "Design a settings panel for a test runner config" "Create a table with sortable columns and pagination"

Everything Claude Code

The complete collection of Claude Code configs from an Anthropic hackathon winner — 10+ months of intensive daily use building real products, distilled into production-ready skills for coding standards, security, TDD, and continuous learning.

🧩

everything-claude-code@everything-claude-code

By Affaan Mustafa — winner of an Anthropic hackathon. Provides universal coding standards, backend and frontend patterns, security review checklists, TDD workflow enforcement, continuous learning from sessions, and token optimization techniques.

8+ Skills Community Cross-platform
install
/plugin install everything-claude-code@everything-claude-code
📏
coding-standards

Universal coding standards for TypeScript, JavaScript, React, and Node.js. Applied automatically to new code.

auto — any code task
🔐
security-review

Comprehensive security checklist: auth flows, user input, secrets, API endpoints, payment handling. Auto-triggers on sensitive code.

auto — auth / API / sensitive code
🧪
tdd-workflow

Enforces 80%+ test coverage with unit, integration, and E2E tests. Write tests first — no shortcuts.

auto — new features / bug fixes
🏗️
backend-patterns

API design, database optimization, server-side best practices for Node.js, Express, and Next.js API routes.

auto — backend tasks
🖼️
frontend-patterns

React, Next.js, state management, performance optimization, and UI best practices. Complements frontend-design.

auto — React / Next.js tasks
🎓
continuous-learning

Automatically extracts reusable patterns from each Claude Code session and saves them as learned skills for future use.

auto — end of sessions
🔄
verification-loop

Checkpoint vs continuous evals, grader types, pass@k metrics. Prevents premature "done" claims.

auto — before completions
🗜️
strategic-compact

Suggests manual context compaction at logical intervals. Preserves context through task phases rather than arbitrary auto-compaction.

auto — long sessions

MCP Server Dev

Three skills for designing and building MCP (Model Context Protocol) servers that connect Claude to any API, tool, or data source. Perfect for building QA-specific MCP tools — Jira, TestRail, Allure, CI pipelines.

🔌

mcp-server-dev@claude-plugins-official

Official Anthropic plugin. Three skills that compose into a full MCP build path: pick deployment model (remote HTTP, MCPB bundle, local stdio), add in-chat UI widgets, package with runtime for easy distribution.

3 Skills Official (Anthropic) MCP tooling
install
/plugin install mcp-server-dev@claude-plugins-official
🏗️
build-mcp-server

Entry point. Interrogates use case, picks deployment model, picks tool-design pattern, routes to specialized skill. Start here.

/mcp-server-dev:build-mcp-server
🖥️
build-mcp-app

Adds interactive UI widgets (forms, pickers, confirm dialogs) rendered inline in Claude chat. For MCP servers with rich interaction.

/mcp-server-dev:build-mcp-app
📦
build-mcpb

Packages a local stdio server with its runtime so users install it without Node/Python. For servers that need local machine access.

/mcp-server-dev:build-mcpb
🔌
QA use cases for MCP Server Dev

Build an MCP tool that connects Claude to Jira (auto-generate test plans from tickets), TestRail (sync results), or your CI pipeline (trigger runs, fetch logs). The CrewAI + Jira MCP tutorial on this site uses exactly this pattern.

Skill Creator

Write your own reusable skills and deploy them across projects. If you have a repeating QA workflow — practice page builder, test case generator, API contract checker — turn it into a skill once and invoke it forever.

✏️

skill-creator@claude-plugins-official

Official Anthropic plugin. Guides Claude through writing well-formed SKILL.md files — name, description, trigger conditions, content format, examples, and deployment. Verify and deploy skills to your user or project scope.

1 Skill Official (Anthropic)
install
/plugin install skill-creator@claude-plugins-official
example — create a QA skill
# Ask Claude to create a skill for your QA workflow: "Create a skill called 'api-contract-check' that runs whenever I say 'check this API contract'. It should verify that the OpenAPI spec matches the actual endpoint responses using Playwright's request interception." # Claude will use skill-creator to structure it properly, # including triggers, content, and deployment instructions.

Playwright Plugin

Official Anthropic Playwright plugin — brings deep Playwright knowledge, test patterns, fixture design, and debugging guidance directly into Claude Code. Essential for the entire TTA Playwright curriculum.

🎭

playwright@claude-plugins-official

Official Anthropic plugin for Playwright testing. Provides test patterns, selector strategies, fixture design, network interception, visual testing, CI configuration, and debugging workflows. Pairs directly with the TTA Playwright practice library.

Official (Anthropic) Playwright expertise QA-focused
install
/plugin install playwright@claude-plugins-official
🎭
Pairs with TTA Playwright Library

Install the Playwright plugin, then open any page from the TTA Playwright practice library. Claude will know exactly which locators to use, how to write fixtures, and how to set up CI for the exercises you're practicing.

Plugin Comparison

Quick reference — all 7 plugins, install scope, and primary use case for QA/SDET work.

Plugin Skills Source Best for Auto-trigger?
superpowers 14 Official Full dev methodology — TDD, debugging, parallel agents ✓ Yes
caveman 7 + 3 agents Community Token savings, terse commits, compressed reviews ✓ After /caveman
frontend-design 1 Official Production-grade, distinctive UI generation ✓ Yes
everything-claude-code 8+ Community Coding standards, security, TDD, continuous learning ✓ Yes
mcp-server-dev 3 Official Building MCP tools for Jira, CI, TestRail Manual
skill-creator 1 Official Writing your own reusable QA skills Manual
playwright TBD Official Playwright test patterns, fixtures, CI config ✓ Yes
⚠️
Plugin conflicts

Superpowers and everything-claude-code both include TDD enforcement. They complement rather than conflict, but you may see double prompts for TDD on some tasks. Start with superpowers alone — add everything-claude-code only if you want the extra coding-standards and security-review auto-triggers.

verify installed plugins
# Check what's installed: /plugin list # See all available plugins in the official marketplace: /plugin search # Update a specific plugin: /plugin update superpowers@claude-plugins-official # Remove a plugin: /plugin remove caveman@caveman