Testing and QA: skills, plugins, subagents and slash commands

skill-creator official anthropics skill Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs improve-codebase-architecture Matt Pocock skill This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock skill Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs prototype Matt Pocock skill Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. Claude Code 986,201installs codebase-design Matt Pocock skill This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write. Claude Code 850,344installs diagnosing-bugs Matt Pocock skill This skill guides an agent through reproducible diagnosis of hard bugs and performance regressions. Use it when code fails, produces wrong results, or becomes slow. Claude Code 834,802installs implement Matt Pocock skill Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine. Claude Code 774,700installs to-spec Matt Pocock skill Turns the current conversation and repository context into a spec, then publishes it to the project issue tracker. Use it when a feature discussion is ready to hand off to an agent. Claude Code 715,388installs webapp-testing official anthropics skill This skill tests local web apps with Playwright, helping agents debug UI behavior, capture screenshots, and inspect browser logs. Claude Code Claude.ai 186,758installs setup-pre-commit Matt Pocock skill This skill configures pre-commit checks for a JavaScript repository, running Prettier, type checking, and tests before each commit. Claude Code 489,289installs migrate-to-shoehorn Matt Pocock skill Replaces as type assertions in tests with helpers from @total-typescript/shoehorn. Use it when tests need partial objects or deliberately invalid data. Claude Code 475,388installs systematic-debugging Jesse Vincent skill Makes the agent investigate the cause of a failure before it suggests a patch. Use it for failing tests, build errors, and behaviour that does not match expectations. Claude Code CX Codex 306,118installs writing-plans Jesse Vincent skill Creates an implementation plan from a spec before code changes begin. Use it when a task has multiple steps, files, and tests. Claude Code CX Codex 282,859installs implement-spec Matt Pocock skill Implements a prepared spec from its ticket graph on one integration branch, using parallel subagents. Use it when tickets have blocking dependencies. Claude Code 283,700installs retro Matt Pocock skill Reviews a coding session and suggests changes to the agent environment for later runs. Use it after mistakes, slow repository navigation, or costly tool calls. Claude Code 276,027installs requesting-code-review Jesse Vincent skill Sends completed work to a reviewer subagent after a task, major feature, or before merging to main. It keeps the review focused on the change and its requirements. Claude Code CX Codex 262,135installs test-driven-development Jesse Vincent skill Guides feature work and bug fixes through TDD: write a failing test, then add minimal code. Use it when test-first discipline matters. Claude Code CX Codex 259,292installs verification-before-completion Jesse Vincent skill This skill blocks completion claims until the agent runs a fresh check and reads the result. Use it before commits or PRs when an agent report is not enough. Claude Code CX Codex 251,313installs executing-plans Jesse Vincent skill Runs an implementation plan in the current session instead of assigning each task to a subagent. Use it for inline work with TDD, a decision ledger, and a final branch review. Claude Code CX Codex 242,988installs receiving-code-review Jesse Vincent skill Reviews code review feedback before changes: it clarifies unclear points, checks the repository, and supports reasoned pushback. Use it before acting on review comments. Claude Code CX Codex 221,216installs dispatching-parallel-agents Jesse Vincent skill Dispatches independent tasks to separate subagents so they can investigate them in parallel. Use it for unrelated test failures and separate broken subsystems. Claude Code CX Codex 218,235installs writing-skills Jesse Vincent skill Applies a TDD workflow to authoring and checking agent skills: observe failure first, then write instructions that address it. Use it when creating or editing SKILL.md files. Claude Code CX Codex 217,894installs using-git-worktrees Jesse Vincent skill Prepares an isolated workspace before feature work or plan execution. It checks the repository first, then uses native worktree support or Git. Claude Code CX Codex 217,153installs finishing-a-development-branch Jesse Vincent skill This skill checks the test suite and guides branch completion: merge locally, open a Pull Request, or leave the work in place. Claude Code CX Codex 214,439installs java-springboot official github skill Gives GitHub Copilot Spring Boot development practices, from project layout to tests and security. Use it when writing or reviewing Java application code. GitHub Copilot 21,272installs playwright-generate-test official github skill Generates a Playwright test from a scenario through Playwright MCP. Use it when the browser flow should be completed before test code is written. GitHub Copilot 18,162installs dotnet-best-practices official github skill Guides reviews and edits of selected .NET/C# code with project rules for structure, DI, tests, logging and security. Use it when changing an existing solution. GitHub Copilot 15,752installs chrome-devtools official github skill Controls a live Chrome browser through Chrome DevTools MCP for page actions, debugging, and performance traces. Use it when an agent needs to inspect a web interface. GitHub Copilot 15,258installs playwright-explore-website official github skill Explores a website through Playwright MCP, records user flows, and proposes test cases. Use it when you need a starting point for UI testing. GitHub Copilot 14,792installs web-design-reviewer official github skill This skill inspects a running website, spots layout, responsive, and accessibility issues, and can fix them in the source code. Use it when a UI review should lead to verified code changes. GitHub Copilot 13,957installs playwright-automation-fill-in-form official github skill Fills a preset form through Playwright MCP, uploads an image, and stops before submission. It fits the Playwright Live demo scenario. GitHub Copilot 13,693installs pytest-coverage official github skill Runs pytest with coverage, flags lines that tests miss, and guides work toward 100% line coverage. Use it when coverage gaps need concrete test cases. GitHub Copilot 12,826installs webapp-testing official github skill Tests local web apps with Playwright, covering UI behavior, forms and browser flows. Use it to investigate interface failures and capture screenshots during a test run. GitHub Copilot 12,447installs java-junit official github skill Writes, reviews and fixes Java tests with JUnit, AssertJ and Mockito. Use it when adding, refactoring or debugging tests in Maven and Gradle projects. GitHub Copilot 11,632installs dotnet-upgrade official github skill Plan a .NET upgrade by reviewing project dependencies, choosing a migration order and preparing post-upgrade checks. GitHub Copilot 11,475installs apple-appstore-reviewer official github skill Reviews an iOS project from an Apple App Store reviewer’s perspective and ranks rejection risks. Use it before submitting an app for review. GitHub Copilot 11,295installs python-mcp-server-generator official github skill Builds Python MCP servers that expose functions, APIs, or databases as tools for AI clients. Use it when starting a server with MCP Python SDK v2. GitHub Copilot 10,418installs csharp-xunit official github skill This skill guides C# unit testing with XUnit, including data-driven cases. Use it when creating or reviewing tests in a .NET project. GitHub Copilot 10,328installs agentic-eval official github skill Use evaluation and refinement patterns to improve AI agent outputs. It suits code, reports and analysis with defined quality criteria. GitHub Copilot 10,213installs refactor-method-complexity-reduce official github skill Refactors a chosen method by moving complex logic into helpers. Use it when nested conditions or branching make a method hard to follow. GitHub Copilot 9,992installs