Skill rankings

Best browser automation skills for AI agents

Find skills that help agents click through websites, fill forms, test user flows, verify UI state, and interact with browser-based tools.

Shown: 30 · Candidates: 471

Compare top 4

01
Webapp Testing
Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
@anthropicsBrowser Automation180,766
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
100/100
Quality
100/100
Freshness
93/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
32/100
02
Playwright Browser Skill
Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.
@openaiBrowser Automation28,031
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
89/100
Quality
100/100
Freshness
31/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
30/100
03
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
@LeonxlnxDesign95,198
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
100/100
Quality
100/100
Freshness
99/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
20/100
04
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
@anthropicsDesign180,766
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
100/100
Quality
100/100
Freshness
93/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
20/100
05
Crawlee
Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
@apifyBrowser Automation25,731
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
88/100
Quality
100/100
Freshness
34/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
27/100
06
GenericAgent
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
@lsdefineAgent Frameworks14,276
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
83/100
Quality
100/100
Freshness
74/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
20/100
07
Scrapling
Adaptive web scraping for agent data collection
@D4VinciWeb Automation70,009
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
97/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
87/100
Task fit
26/100
08
Browser Use
Make AI agents interact with websites using natural language
@browser-useWeb Automation100,530
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
100/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
25/100
09
Midscene
AI-powered, vision-driven UI automation for every platform.
@web-infra-devAutomation14,188
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
83/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
26/100
10
Crawlee Python
Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Parsel, BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.
@apifyBrowser Automation9,507
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
80/100
Quality
100/100
Freshness
34/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
23/100
11
OpenCLI
Make Any Website into CLI & Use your logged-in browser by AI agent.
@jackwenerAgent Frameworks26,604
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
89/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
23/100
12
Browser Harness
Browser Harness | Self-healing harness that enables LLMs to complete any task.
@browser-useAgent Frameworks17,301
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
85/100
Quality
100/100
Freshness
15/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
20/100
13
Figma Implement Design
Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.
@openaiDesign28,031
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
89/100
Quality
100/100
Freshness
31/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
14
Ui Ux Pro Max Skill
An AI agent skill that provides design intelligence and UI/UX guidelines for building professional interfaces across multiple platforms.
@nextlevelbuilderDevelopment107,051
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
100/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
19/100
15
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
@bytedanceAutomation36,958
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
91/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
87/100
Task fit
21/100
16
Grill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
@mattpocockCoding164,748
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
100/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
19/100
17
Maxun
🔥 The open-source no-code platform for web scraping, crawling, search and AI data extraction • Turn websites into structured APIs in minutes 🔥
@getmaxunWeb Automation16,203
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
84/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
20/100
18
Video Use
A tool that lets AI agents like Claude Code edit videos by cutting filler words, color grading, adding subtitles, and more, all via natural language commands.
@browser-useMedia17,140
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
85/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
20/100
19
Taste Skill
A portable AI agent skill that enhances AI-generated user interfaces with better layout, typography, motion, and spacing to avoid generic outputs.
@LeonxlnxDevelopment64,963
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
96/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
20
Web Design Guidelines
Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.
@vercel-labsDesign32,304
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
90/100
Quality
100/100
Freshness
9/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
21
Skyvern
Automate browser workflows with AI agents
@Skyvern-AIWeb Automation22,501
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
87/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
87/100
Task fit
20/100
22
Career Ops
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
@santiferDevelopment59,910
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
96/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
23
Vercel React Best Practices
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
@vercel-labsCoding32,304
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
90/100
Quality
100/100
Freshness
9/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
24
Apple Design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.
@emilkowalskiDesign34,452
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
91/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
25
Huginn
Create agents that monitor and act on your behalf. Your agents are standing by!
@huginnAutomation49,478
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
94/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
26
ToolJet
ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀
@ToolJetAutomation38,020
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
92/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
27
Oh My Claudecode
Teams-first Multi-agent orchestration for Claude Code
@Yeachan-HeoAgent Frameworks36,986
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
91/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
28
Frontend Slides
Create beautiful slides on the web using a coding agent's frontend skills
@zarazhangruiCoding28,772
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
89/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
29
Conductor
Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
@conductor-ossAutomation31,951
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
90/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
100/100
Task fit
18/100
30
Antigravity Awesome Skills
A comprehensive library of over 1,273 agentic skills for various AI coding assistants, featuring clear documentation and installation instructions.
@sickn33Development43,550
Review before use
View details
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
Popularity
93/100
Quality
100/100
Freshness
0/100
Agent evidence
0/100
Evidence confidence
0/100
Install readiness
87/100
Task fit
18/100

A shortlist from up to 480 directory candidates, not the entire registry. Stars belong to repositories. Signals are not safety guarantees or runtime verification.

How this list works

Matches task and source metadata, then considers quality, popularity and freshness. Source descriptions are not execution evidence.

Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.