Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Web & browsing
2,332 results · page 23 of 78
- View details
google-adsSkillWeb & browsing
Query, audit, and optimize Google Ads campaigns. Supports two modes: (1) API mode for bulk operations with google-ads Python SDK, (2) Browser automation mode for users without API access - just attach a browser tab to ads.google.com. Use when asked to check ad performance, pause campaigns/keywords,
Ready to connect★ 611
- View details
qa-executionSkillWeb & browsing
Runs real-user dogfooding sessions through the product's public interfaces: a persona walks a journey in the browser, takes a thematic tour, probes edges, hunts paper cuts, and reports what a real user would experience. Reads its plan from the living QA docs tree (<qa-docs-path>, default docs/qa/).
Ready to connect★ 611
- View details
tandem-browserSkillWeb & browsing
Use Tandem Browser's MCP server (local and remote agents) or HTTP API (local and remote agents) to inspect, browse, and interact with the user's shared browser safely. Prefer targeted tabs and sessions, use snapshot refs before raw DOM or JS, verify action completion explicitly, and leave durable ha
Ready to connect★ 606
- View details
agent-canvas-setupSkillWeb & browsing
Dependency checker and installer for agent-canvas, agent-eyes, and canvas-edit skills. Use BEFORE running any canvas skill for the first time, or when canvas skills fail with import/browser errors. Triggers on "setup agent canvas", "install canvas dependencies", "canvas not working", "playwright not
Ready to connect★ 603
- View details
ciSkillWeb & browsing
Use when running headless inside a GitLab CI job in the Gramax repo (the `ai` job). Establishes environment — repo checked out, glab/gh authenticated, what tools exist, how to read/post on GitLab, how to diagnose failed pipeline jobs. Triggers on "ci", "running in CI", "headless CI job", "ты в CI",
Ready to connect★ 602
- View details
news-extractorSkillWeb & browsing
Extracts content from news sites. Supports 12 platforms: WeChat Official Accounts, Toutiao, NetEase News, Sohu News, Tencent News, BBC News, CNN News, Twitter/X, Lenny's Newsletter, Naver Blog, Detik News, Quora. Activates when the user needs to extract news content, scrape WeChat articles, crawl ne
Ready to connect★ 600
- View details
handoffSkillWeb & browsing
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md
Ready to connect★ 596
- View details
web-publishSkillWeb & browsing
Publishing a 1C infobase via Apache. Use when the user asks to publish a database or services, set up web access, the web client, or open it in a browser.
Ready to connect★ 592
- View details
web-testSkillWeb & browsing
Testing 1C via the web client — browser action automation. Use when the user asks to check, test, or automate actions in 1C through a browser.
Ready to connect★ 592
- View details
privacy-usSkillWeb & browsing
Automatically generates Privacy Policies based on US CCPA/CPRA plus major state laws (VCDPA, CPA, CTDPA, UCPA, ICDPA, KCDPA, RIDPA). Covers the 2026.1.1 CPPA update rules, Sensitive Personal Information, Do Not Sell/Share, ADMT disclosures, and GPC browser signals. For services serving California re
Ready to connect★ 583
- View details
web-scraperSkillWeb & browsing
Scrape, crawl, and extract data from websites. Use when users ask to scrape web pages, extract content, crawl websites, or collect data from the internet.
Ready to connect★ 581
- View details
32-seo-growthSkillWeb & browsing
When the user wants to increase traffic from SEO, AI SEO, GEO/AEO, Google, ChatGPT, Perplexity, schema, structured data, llms.txt, programmatic SEO, local SEO, directory submissions, Product Hunt, G2/Capterra, backlinks, or audit a website that isn't reaching the top. Use for 'SEO audit', 'AI search
Ready to connect★ 574
- View details
extract-to-jasprSkillWeb & browsing
Extracts a part of a website and converts it to a Jaspr component. Use when you need to migrate a part of a website to Jaspr.
Ready to connect★ 568
- View details
common-dast-toolingSkillWeb & browsing
Standardize dynamic application security testing for backend APIs, frontend web apps, and mobile clients. Covers ZAP, Nuclei, Nikto, sqlmap, ffuf, browser automation, mobile proxy interception, and AI-driven curl probes. Use when advising on or running dynamic security scans on local/staging environ
Ready to connect★ 565
- View details
common-web-visual-testingSkillWeb & browsing
Standardizes visual audits, responsive design, and behavioral testing for web apps. Use to verify a web UI fix or cross-browser behavior; defer backend API refactors, Playwright installation/tooling setup, and Appium/mobile automation.
Ready to connect★ 565
- View details
qa/e2e-playwrightSkillWeb & browsing
Complete Playwright E2E testing methodology, covering project setup, Page Object Model, authentication reuse, API mocking, visual regression, multi-browser testing, CI integration, and debugging tips
Ready to connect★ 555
- View details
Maestro ImpeccableSkillWeb & browsing
Use when designing, auditing, polishing, or improving frontend UI — websites, dashboards, landing pages, components
★ 549
- View details
fixSkillWeb & browsing
Fix a GitHub issue end-to-end — fetches issue, creates worktree, plans and implements fix, runs validation, opens PR, cleans up.
Ready to connect★ 548
- View details
clickhouse-managed-postgres-rcaSkillWeb & browsing
MUST USE when investigating performance issues on a ClickHouse-managed Postgres instance. Provides an evidence-based RCA workflow that scrapes the Prometheus endpoint for system signal, pulls per-digest evidence from the Slow Query Patterns API, and recommends (does not apply) a fix.
Ready to connect★ 532
- View details
browser-debuggingSkillWeb & browsing
Chrome DevTools MCP ile browser debugging. Console, network, performance, DOM analizi.
Ready to connect★ 530
- View details
clone-websiteSkillWeb & browsing
Reverse-engineer and clone a website in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on p
Ready to connect★ 530
- View details
harvest-deep-crawlSkillWeb & browsing
Multi-page deep crawling - documentation sites, wikis, knowledge bases
Ready to connect★ 530
- View details
browser-searchSkillWeb & browsing
Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research.
Ready to connect★ 521
- View details
browser-e2e-testsSkillWeb & browsing
Authoring browser end-to-end tests for the Composer app with Playwright. Use when writing, editing, or reviewing *.spec.ts under packages/apps/composer-app/src/playwright, adding page-object helpers, or deciding how to target elements (always data-testid, never labels/roles).
Ready to connect★ 520
- View details
cloud-sandboxSkillWeb & browsing
Working inside the Claude Code cloud sandbox (Claude Code on the web, remote sessions, scheduled runs). Use when CLAUDE_CODE_REMOTE is set; when `moon`, `gh`, or `oxfmt` are "command not found"; when Chromium or Playwright fails with ERR_CONNECTION_RESET or a TLS error against an HTTPS host that cur
Ready to connect★ 520
- View details
composer-forensicsSkillWeb & browsing
Forensically inspect and repair Composer browser profiles — offline (Chrome OPFS / SQLite extract) or live via /recovery.html debug port. Use for data loss, corruption, slow space open, Automerge bloat, or when the app won't boot. Follow DOCTOR.md for live sessions: user opens debug port, agent expl
Ready to connect★ 520
- View details
debuggingSkillWeb & browsing
Use when instrumenting code with runtime logs to test a hypothesis — @dxos/log debug lines captured to app.log (browser), test.log (node tests), or test-browser.log (browser tests/storybook), and querying them with query-logs.mjs. Reference for the log-exfiltration pipeline and instrumentation mecha
Ready to connect★ 520
- View details
google-analyticsSkillWeb & browsing
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
Ready to connect★ 500
- View details
omd-setupSkillWeb & browsing
Guided setup of the tools the design harness can use — image/video generation channels, browser, encoders. Detects what the user already has, explains pros/cons/costs, asks instead of instructing, and saves choices to .omd/config.json so every later design task reuses them. Trigger: 'omd setup', '도구
Ready to connect★ 500
- View details
geo-auditSkillWeb & browsing
GEO + AEO audit — `llms.txt`, `AGENTS.md`, AI-crawler robots, JSON-LD citation grounding. Sibling to /seo-audit.
Ready to connect★ 498
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
52,524 of the 52,958 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.