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 5 of 78
- View details
query-token-infoSkillWeb & browsing
Lets your agent look up crypto token details like price, charts, creators, and social links by name or contract address.
Ready to connect★ 44k
- View details
analyzing-insights-across-teamsSkillWeb & browsing
Analyze PostHog insights, dashboards, or teams beyond the current project by querying the prod Postgres replicas synced into the dogfood data warehouse (US project 2, "PostHog App + Website"). Use when asked to analyze insights across all teams or projects, another team's insights, or fleet-wide ins
Ready to connect★ 40k
- View details
building-canvasesSkillWeb & browsing
Create or edit a PostHog freeform canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in PostHog and rendered by the desktop/web app. Use when a task asks to build, generate, update, or fix a standalone canvas app, or when a freeform canvas i
Ready to connect★ 40k
- View details
building-html-canvasesSkillWeb & browsing
Author a PostHog canvas with semantic HTML, CSS, and direct browser APIs — documents, articles, generative graphics, 2D canvas and WebGL experiences, and focused experiments where React components add no useful structure. Use after building-canvases has routed a canvas request to a plain-HTML/browse
Ready to connect★ 40k
- View details
investigating-error-issueSkillWeb & browsing
Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature f
Ready to connect★ 40k
- View details
playwright-testSkillWeb & browsing
Write a playwright test, make sure it runs, and is not flaky.
Ready to connect★ 40k
- View details
qa-frontendSkillWeb & browsing
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code
Ready to connect★ 40k
- View details
suppressing-noisy-errorsSkillWeb & browsing
Create PostHog error tracking suppression rules to drop high-volume, low-value errors at ingestion. Use when the user asks "stop capturing this error", "drop browser extension errors", "ignore ResizeObserver loops", "suppress bot-driven errors", or wants to reduce ingestion cost from noisy unactiona
Ready to connect★ 40k
- View details
writing-testsSkillWeb & browsing
Gates whether a new test should exist and forces it to be efficient, protecting CI from low-value test bloat. Use before any change to what a pytest, Jest, or Playwright test asserts or sets up, down to one fixture or one assertion added to an existing block. Front-loads the value bar (every test mu
Ready to connect★ 40k
- View details
chrome-devtoolsSkillWeb & browsing
Lets your agent open web pages in Chrome, take screenshots, inspect network traffic, and measure page performance.
Ready to connect★ 39k
- View details
daily-focus-boardSkillWeb & browsing
Lets your agent create a personal daily focus board in the browser that tracks task progress as you talk to it.
Ready to connect★ 39k
- View details
add-anydocSkillWeb & browsing
Lets your agent convert Word, PowerPoint, Excel, PDF and other document files into Markdown text it can read.
Ready to connect★ 31k
- View details
frontend-engineerSkillWeb & browsing
Makes your agent follow a strict build-test-verify workflow so websites are tested, responsive, and accessible before being called done.
Ready to connect★ 31k
- View details
onecli-gatewaySkillWeb & browsing
Lets your agent call external services like email, calendar, GitHub, and Stripe using stored credentials.
Ready to connect★ 31k
- View details
cognee-communitySkillWeb & browsing
Lets your agent connect cognee to extra databases and data sources like Slack, Gmail, Notion, and Google Drive.
Ready to connect★ 31k
- View details
playwright-interactiveSkillWeb & browsing
Lets your agent control a browser or Electron app to test and debug its interface step by step.
Ready to connect★ 27k
- View details
vercel-deploySkillWeb & browsing
Lets your agent deploy apps and websites to Vercel and share a live link.
Ready to connect★ 27k
- View details
browser-automationSkillWeb & browsing
Lets your agent drive a web browser to scrape data, fill forms, and capture screenshots automatically.
Ready to connect★ 26k
- View details
baoyu-markdown-to-htmlSkillWeb & browsing
Converts Markdown text into styled HTML pages with themes, code highlighting, and diagrams.
Ready to connect★ 26k
- View details
baoyu-url-to-markdownSkillWeb & browsing
Lets your agent fetch any webpage and save it as clean markdown text.
Ready to connect★ 26k
- View details
ce-dogfoodSkillWeb & browsing
Lets your agent test the current branch in a real browser, fix small breakages, and write a QA report.
Ready to connect★ 25k
- View details
ce-polishSkillWeb & browsing
Lets your agent refine a working web feature through live browser feedback before shipping.
Ready to connect★ 25k
- View details
ce-test-browserSkillWeb & browsing
Lets your agent run browser tests for the pages changed in your current branch or pull request.
Ready to connect★ 25k
- View details
browserstack-liveSkillWeb & browsing
Use when testing a local or public URL on a real device via BrowserStack, opening a live browser session on Android, iOS, or desktop browsers, or when the user mentions BrowserStack, real device testing, mobile testing, cross-browser testing, touch testing, or wants to verify behavior on a specific
Ready to connect★ 22k
- View details
handsontable-e2e-testingSkillWeb & browsing
Use ONLY when maintaining the FROZEN legacy Jasmine/Puppeteer E2E suite (*.spec.js) — editing an existing spec, or migrating a broken one to Playwright. Do NOT use for new E2E: new E2E is Playwright (skill handsontable-playwright-e2e). Covers the legacy boilerplate, async/await rules, global helpers
Ready to connect★ 22k
- View details
handsontable-playwright-e2eSkillWeb & browsing
Use when writing or modifying real-browser Playwright E2E / functional tests for Handsontable (specs in tests/e2e/, core, wrappers, or walkontable). Covers the Page Object Model, hooking in by data-testid, deterministic web-first waits, wrapper-specific gotchas, recording via the CLI, and the new-vs
Ready to connect★ 22k
- View details
visual-testingSkillWeb & browsing
Use when writing Playwright visual regression tests or creating visual test examples for Handsontable - covers the custom tablePage fixture, screenshot workflow, reg-suit comparison, and example creation in examples/next/docs/
Ready to connect★ 22k
- View details
playwright-pom-discoverySkillWeb & browsing
Lets your agent pick stable selectors and build page objects for Playwright end-to-end tests by inspecting a live app.
Ready to connect★ 22k
- View details
docs-build-and-verifySkillWeb & browsing
Use when asked to build, preview, or verify the Flet documentation website, including checking for broken links, broken images, and unresolved reST cross-references.
Ready to connect★ 17k
- View details
test-flet-apps-devSkillWeb & browsing
Use when testing or debugging Flet apps in maintainer/contributor development mode with local Python package sources and the local Flutter client, including web, desktop, browser, and computer-use verification workflows.
Ready to connect★ 17k
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.