Agent Skills

web-artifacts-builder

✓★ 158,100

by anthropic

Multi-component React artifacts for Claude with bundling, state management, and shadcn/ui component library. Scaffolds React 18 + TypeScript projects with Vite, Tailwind CSS, and 40+ pre-installed shadcn/ui components via automated initialization script Bundles complete artifacts into single self-contained HTML files with inlined assets, ready for Claude artifact display Includes design guidance to avoid common "AI slop" patterns like excessive centering, purple gradients, and uniform...

Docx

✓★ 158,000

by Anthropic

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks" license: Proprietary. LICENSE.txt has complete terms

Artifacts Builder

✓★ 158,000

by Anthropic

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts. license: Complete terms in LICENSE.txt

Webapp Testing

✓★ 158,000

by Anthropic

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. license: Complete terms in LICENSE.txt

Skill Creator

✓★ 158,000

by Anthropic

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. license: Complete terms in LICENSE.txt

sandbox-npm-install

✓★ 36,200

by github

Install npm packages in a Docker sandbox environment. Use this skill whenever you need to install, reinstall, or update node_modules inside a container where…

chrome-devtools

✓★ 36,200

by github

Expert-level browser automation, debugging, and performance analysis via Chrome DevTools protocol. Four tool categories cover navigation, interaction, debugging, and performance profiling across 25+ commands Snapshot-first workflow provides element UIDs for reliable targeting; screenshots offer visual verification Network request inspection, console message analysis, and JavaScript evaluation support troubleshooting and validation Performance tracing with Core Web Vital analysis identifies...

quality-playbook

✓★ 36,200

by github

Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol…

playwright-automation-fill-in-form

✓★ 36,200

by github

Automate form filling with Playwright MCP, including text input, date/time selection, and file uploads. Supports multiple form field types: text inputs, date pickers, time selectors, and file uploads Navigates to specified URLs and populates forms with provided data without automatic submission Includes review checkpoint before form submission to allow manual verification of filled fields

geofeed-tuner

✓★ 36,200

by github

This skill helps you create and improve IP geolocation feeds in CSV format by:

webapp-testing

✓★ 36,200

by github

Browser automation and testing toolkit for local web applications using Playwright. Supports core browser interactions including navigation, form filling, clicking, dropdown selection, and dialog handling Includes verification capabilities for element presence, text content, visibility, URLs, and responsive design across viewports Provides debugging tools: screenshot capture, console log inspection, network request monitoring, and error handling patterns Works with Node.js environments and...

qdrant-monitoring

✓★ 36,200

by github

Guides Qdrant monitoring and observability setup. Use when someone asks 'how to monitor Qdrant', 'what metrics to track', 'is Qdrant healthy', 'optimizer…

drawio

✓★ 36,200

by github

Generate draw.io diagrams as .drawio files and export to PNG/SVG/PDF with embedded XML

breakdown-test

✓★ 36,200

by github

Comprehensive test planning and quality assurance documentation generator aligned with ISTQB and ISO 25010 standards. Generates three core deliverables: test strategy, test issues checklist, and QA plan from feature PRDs and technical breakdowns Applies ISTQB test design techniques (equivalence partitioning, boundary value analysis, decision table testing, state transition testing) and test types (functional, non-functional, structural, change-related) Maps all eight ISO 25010 quality...

playwright-explore-website

✓★ 36,200

by github

Automated website exploration and test case generation using Playwright. Navigates to provided URLs and systematically identifies 3-5 core features and user flows Documents UI elements, their locators, and expected outcomes for each interaction Generates test cases based on exploration findings for immediate use in testing workflows Manages browser context lifecycle automatically, closing sessions upon completion

playwright-generate-test

✓★ 36,200

by github

Generate Playwright tests from scenarios using interactive browser exploration and validation. Guides you through step-by-step test creation: scenario review, browser exploration, element inspection, interaction validation, and final test generation Integrates with Playwright MCP tools to inspect page elements, capture selectors, and validate interactions before writing test code Generates TypeScript tests using @playwright/test framework and automatically saves them to the tests directory...

xlsx-author

✓★ 33,000

by anthropic

Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.

pptx-author

✓★ 33,000

by anthropic

Produce a .pptx file on disk (headless) instead of driving a live PowerPoint document — for managed-agent sessions with no open Office app.

xlsx-author

✓★ 33,000

by anthropic

Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.

pptx-author

✓★ 33,000

by anthropic

Produce a .pptx file on disk (headless) instead of driving a live PowerPoint document — for managed-agent sessions with no open Office app.

find-skills

★ 25,000

by vercel

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities. Helps identify relevant skills by domain and task when users ask "how do I do X" or "find a skill for X" Integrates with the Skills CLI ( npx skills find , npx skills add ) to search, verify, and install packages from the skills.sh directory Recommends skills based on install count, source reputation, and GitHub stars to ensure quality before suggesting installation Presents skill...

playwright

✓★ 23,200

by openai

Terminal-driven browser automation with element snapshots and interactive UI workflows. Operates via playwright-cli wrapper script (requires npx ); supports headless and headed modes for visual debugging Core workflow: open page, snapshot for stable element references, interact using refs, re-snapshot after navigation or DOM changes Includes form filling, clicking, typing, multi-tab management, screenshot/PDF capture, and trace recording for flow debugging Element refs (e.g., e3 , e15 )...

playwright-interactive

✓★ 23,200

by openai

Persistent browser and Electron debugging with live session handles across code iterations. Maintains the same Playwright handles ( browser , context , page ) across multiple js_repl cells, eliminating restart overhead during iterative UI testing and QA. Supports desktop web (explicit viewport or native-window mode), mobile web emulation, and Electron app debugging from a single persistent session. Includes structured QA workflow: write a coverage inventory upfront, run functional tests with...

train-sentence-transformers

✓★ 10,800

by huggingface

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity,…

health

★ 6,200

by tw93

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/检查pi/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

vitest

★ 5,500

by antfu

Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.

game-playtest

✓★ 4,000

by openai

Run browser-game playtests and frontend QA. Use when the user asks for smoke tests, screenshot-based verification, browser automation, HUD or overlay review,…

browser

✓★ 3,600

by browserbase

Browser automation with local Chrome or remote Browserbase for protected sites, bot detection, and CAPTCHAs. Two modes: local Chrome (default, no setup) or remote Browserbase (anti-bot stealth, automatic CAPTCHA solving, residential proxies, session persistence) Core commands cover navigation, page inspection, interaction (click, type, fill, select, drag), and session management via CLI Use browse snapshot to read the accessibility tree and get element refs for reliable interactions; reserve...

fetch

✓★ 3,600

by browserbase

Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers,…

functions

✓★ 3,600

by browserbase

Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron,…