Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Check that a change to a web app actually works in the running app before calling it done. Drives the real page and returns a pass/fail verdict with the request that fired, the state that moved, and the file:line to fix. Use after editing a component, a form, a route, or an API call; when you have said “fixed” but have not opened the app; when the user asks “does it actually work?”; or when a change looks right on screen and you cannot prove it.
Generate a test suite of natural-language → SQL pairs that becomes the quality benchmark for a nao agent, then run it via `nao test`. Use when the user wants to start measuring agent reliability, extend an existing test suite, or add tests for new metrics. Tests are the only honest answer to "is the context working?". Do not use for writing rules (write-context-rules) or diagnosing failures (audit-context).
Turn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time
Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.
Intelligent network quality analysis with adaptive loading strategies. Detects connection type (2g/3g/4g), bandwidth, RTT, and save-data mode, then automatically triggers appropriate optimization workflows. Includes decision trees that recommend image compression for slow connections, critical CSS inlining for high RTT, and save-data optimizations (disable autoplay, reduce quality). Features connection-aware performance budgets (500KB for 2g, 1.5MB for 3g, 3MB for 4g+) and adaptive loading implementation guides. Cross-skill integration with Loading (TTFB impact), Media (responsive images), and Core Web Vitals (connection impact on LCP/INP). Use when the user asks about slow connections, mobile optimization, save-data support, or adaptive loading strategies. Compatible with Chrome DevTools MCP.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Load tests API endpoints with progressively increasing concurrency. Measures response times, error rates, and throughput, and identifies breaking points. Generates a detailed report with latency percentiles, throughput curves, bottleneck analysis, and optimization recommendations.
Behavior-driven UI testing patterns across Vitest Browser Mode, Playwright E2E evidence boundaries, and DOM Testing Library. Use when testing any front-end application, writing UI or end-to-end tests, querying DOM elements, simulating user interactions, or choosing the lightest harness that proves a browser-observable claim. For React-specific patterns, see the react-testing skill.
Diagnoses LLM output failures, including hallucinations, constraint violations, format errors, and reasoning issues. Provides root cause classification, prompt fixes, tool improvements, and new test cases. Use for “debugging AI,” “fixing prompts,” “quality issues,” or “output errors.”
Guard against breaking the @pierre/diffs integration in Plannotator's code review UI. Use this skill whenever modifying DiffViewer.tsx, upgrading the @pierre/diffs package, changing unsafeCSS injection, adding new props to FileDiff, or touching shadow DOM selectors or CSS variables that cross into Pierre's shadow boundary. Also trigger when someone asks "will this break the diff viewer", "is this safe to change", or when reviewing PRs that touch the review-editor package.
Decide whether a given code change should be placed behind a LaunchDarkly feature flag. Use when a developer asks whether a change should be behind a flag, when reviewing a diff or pull request, or when running in CI on a PR. Reads the diff and surrounding code, then emits a structured advisory recommendation. Read-only: it never creates or modifies flags.
Set up, launch and drive a Decentraland Explorer through its MCP automation server to build and test a local SDK7 scene in-world: screenshot, walk, click and debug the running scene. Use when the user asks to see, test, verify, walk through, screenshot, or debug a scene in-world; when they name the Explorer or its MCP server; when they want the Explorer MCP installed, set up or connected; whenever an `mcp__explorer__*` tool is available; and whenever the `explorer` MCP server failed to connect or was never set up at all — ConnectionRefused, or no such server, only means the Explorer is not running yet, which is this skill's normal starting point, not a reason to skip it.
Comprehensive end-to-end validation of the Archon Web UI using browser automation and codebase review. Use when: User wants to validate, test, or audit the Archon web interface, find UI/UX bugs, test workflow management, verify parallel agent orchestration, or run comprehensive browser-based E2E tests. Triggers: "validate ui", "test the ui", "e2e test", "browser test", "validate archon", "test archon ui", "ui audit", "ux review", "comprehensive test", "validate everything". Capability: Starts Archon, runs exhaustive browser automation tests via agent-browser CLI, performs codebase review, and produces a detailed bug/UX report. NOT for: Unit tests (use `bun test`), CLI-only validation (use /validation:validate-simple).
Generates .http files for the VS Code REST Client extension from Express, Next.js, Fastify, or other API routes. Creates organized request files with variables, environments, and authentication. Use when users request “generate http files,” “rest client requests,” “create .http file,” or “vscode api testing”
Writes and reviews SwiftUI WidgetKit code for Home Screen, Lock Screen, StandBy, and watch widgets — timeline providers and reload policies, StaticConfiguration / AppIntentConfiguration, user-configurable widgets, widget families and sizing, accented/tinted rendering modes, interactive widgets and Controls (Control Center), Live Activities and the Dynamic Island, Smart Stack relevance, push-updated widgets, and visionOS / CarPlay / macOS surfaces. Use when building a widget extension, a timeline provider, a Lock Screen or accessory widget, a watch complication, an interactive button/toggle widget, a Control Center control, a Live Activity, or fixing a widget that won't update or render correctly in tinted mode.
Fast, CI-friendly check for entries whose source files have changed since the last verification. Compares entry source files against git diff without reading source code and flags stale entries in index.json. Use in CI pipelines or before releases to detect outdated documentation
Review plans and code changes. Walks Architecture → Code Quality → Tests → Performance, numbering issues with tradeoff options. Triggers: "review", "review this", "code review", "look over this", "check my changes", "audit", "critique", "what do you think", "sanity check".
Generates Robot Framework tests in keyword-driven syntax with Python. Supports SeleniumLibrary, RequestsLibrary, and custom keywords. Use when the user mentions "Robot Framework", "*** Test Cases ***", "SeleniumLibrary", ".robot file". Triggers on: "Robot Framework", "*** Test Cases ***", ".robot", "SeleniumLibrary", "keyword-driven test".
Launches a persistent, headless-by-default Chromium (playwright-cli's) with an unpacked extension loaded through `web ext`, opens the extension's side panel, popup, or options page, and interacts with it over `web browser eval/cdp`. Handles the Chrome 137+ restriction on loading unpacked extensions and the side panel user-gesture requirement. Use when testing, automating, or validating a Chrome extension's UI
Measure a project's code coverage and report the coverage number. Use whenever coverage needs to be measured — a user asking to run the coverage report or check the current level, and also when the task itself calls for it: recording the starting coverage before development, confirming coverage didn't drop below the committed baseline after a change. Measures the whole project (unit + integration merged) or just one test group — a package/class glob or a subproject.
Pre-production review of a Factorial Code app — clone the workspace read-only, run the static check catalog, classify findings as Blocker/Warning/Suggestion, and write APP_VALIDATION_REPORT.md with a ✅/❌ promotion verdict. Use when validating, reviewing, or auditing a Factorial Code (fcode) app or workspace before a release, or when asked whether an app is ready to ship.
Detects the languages on a webpage, both declared in markup (html lang, hreflang links, nested lang attributes, Content-Language meta) and present in the body text (Google CLD3), and reports where the two disagree. Use for i18n audits, hreflang validation, multilingual page checks, or when asked what language a page is in
Plan and build comprehensive Playwright E2E test suites with Page Object Model, authentication state persistence, custom fixtures, visual regression, and CI integration. Uses interview-driven planning to clarify critical user flows, auth strategy, test data approach, and parallelization before writing any tests.
Use when writing or reviewing TypeScript/full-stack code. Encodes principles for type safety (branded types, discriminated unions, end-to-end types), real tests over mocks, OpenTelemetry observability, and picking the right abstractions instead of premature ones.
Expert-level Rust testing — the "What Could Break?" framework, five transformations from superficial to expert tests, flake hunting protocol, intent-based assertions, naming conventions, and a mandatory self-review checklist. Triggers on writing Rust tests, designing test cases, improving test quality, or reviewing test coverage.
Review what actually changed—in a transport or in your unactivated drafts—by diffing each object's source and summarizing the change set with optional impact and quality signals. Produces a reviewable report (per-object unified diffs + risk flags), not a raw object dump. Use when asked to “review this transport”, “what changed in TR X”, “diff the objects in a transport”, “show my pending changes before I activate/release”, “prepare a transport/change review”, or “what am I about to ship”.
Use sem for entity-level (function/class/method) code questions in any Git repo. Four questions, four verbs — where is it (sem find, sem grep), what does my change touch (sem impact), is it correct (sem check), what should a human review (sem certify). Trigger whenever the user asks where something is defined or called, what a change breaks or which tests to run, whether a change is correct, what changed in a commit or PR, or what to review; also use it proactively before refactors and in code review, where line-level git output is noisy.
Force the states a happy-path run never reaches (a failing API, an empty list, a slow request, a timeout, an expired session, a toast that auto-dismisses) and check the UI actually handles them. Use when error handling was written but never run, when a loading or empty state needs verifying, when a bug only happens on a slow connection, or when a timer, poll, debounce or retry needs testing without sleeping.
Automatically categorizes test failures, suggests responsible owners, and provides common fix checklists. Generates actionable test reports with failure analysis. Use for "test reporting", "failure triage", "test analysis", or "test automation".
Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible". Do NOT use for SEO (use seo), performance (use core-web-vitals), or comprehensive site audits covering multiple areas (use web-quality-audit).
Generates Detox E2E tests for React Native apps in JavaScript. A gray-box testing framework with automatic synchronization. Supports local simulators/emulators and the TestMu AI cloud. Use when the user mentions “Detox”, “React Native test”, “element(by.id())”, or “device.launchApp”. Triggers on: “Detox”, “React Native E2E”, “React Native test”, “element(by.id)”, “device.launchApp”.
Use this skill when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for local uncommitted changes — this skill only reviews pull requests on GitHub.
Next.js 16 App Router performance, caching, server components, server actions, routing, and codebase-hygiene best practices — plus a category-major review/refactor algorithm with codebase-level (remove/dedup/reuse) findings. This skill should be used when writing Next.js 16 App Router code, configuring caching with 'use cache' or the previous fetch-cache model, building Server Components, setting up parallel/intercepting routes, configuring next.config OR proxy.ts, OR auditing/refactoring a Next.js codebase (single file or whole repo). This skill does NOT cover generic React 19 patterns (use vercel-react) or non-Next.js server rendering.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.