236 skills · sorted by relevance
Operate an isolated Browser Use Cloud browser from a machine without usable local Chrome. Navigate pages, inspect content, fill forms, manage tabs, and capture screenshots through the Browser Use CLI, then stop the browser after use.
Controls a browser directly to click, type, navigate, extract page data, and take screenshots. Useful for testing websites and working with pages that require JavaScript rendering, interaction, or an existing signed-in browser session.
Use a real browser to verify web pages and apps through short, supervised interactions. Capture screenshots, inspect errors and network requests, and document reproducible steps for UI bugs or expected behavior checks.
Inspect and test web pages through a browser automation command-line tool. Navigate, click, enter text, capture screenshots, and extract page details, with a focus on checking local OpenDesign previews and reviewing web app quality.
Search people, companies, and deals in Attio using natural language. Apply detailed filters, sort records, review related notes, and inspect available fields through Composio, a service that connects agents to external tools.
Review page landmarks, the named regions screen reader users navigate between. The skill checks semantic HTML elements, a single main content region, and labels for repeated region types, then identifies markup changes and ways to verify them.
Review web page headings for skipped levels, unclear labels, and incorrect structure. Organize HTML headings around the content so people using screen readers can understand page sections and navigate between them.
Find empty headings or headings containing only whitespace in rendered web pages. Guide fixes by adding descriptive text or removing unnecessary heading tags, helping screen reader users navigate a meaningful document structure.
Automate website navigation, form filling, screenshots, data extraction, and web app testing while keeping page state between scripts. Works with a fresh Chromium session or an existing Chrome session through an extension.
Organize existing ChatGPT Pages and Spaces around the work readers need to do. The skill reviews page structure, moves pages, consolidates duplicate content, and improves navigation while preserving distinct requirements, historical context, and relevant layout details.
Handle Slack tasks through browser automation, including checking unread channels, searching conversations, and sending messages. Extract channel details or message text, and save screenshots to document what was found in the workspace.
Set up a browser automation command-line tool for agents to navigate sites, fill forms, extract data, and capture screenshots. It also points to dedicated guides for app testing, Electron desktop apps, and cloud browsers.
Create technical documentation that people and AI can navigate by separating facts, context, known bugs, and uncertain claims. Convert existing Markdown to HADS, a structured documentation format, and check its required elements.
Build a connected Markdown Wiki from documents, notes, transcripts, research, and code. Organize knowledge by subject, attach evidence to claims, maintain a navigation index, and integrate new material into existing pages while preserving disagreements and context.
Explore an unfamiliar codebase using a graph of code relationships. Inspect its structure, find functions and classes, trace calls and imports, follow execution paths, and locate large functions for closer investigation.
Choose research problems, refine new ideas, or rethink stalled projects through structured conversation. Assess feasibility, potential impact, and risks, then develop success criteria, decision points, and backup plans for a clearer research strategy.
Automate website navigation, form entry, button clicks, and data extraction using the agent-browser command-line tool. Capture screenshots or PDFs, reuse login sessions, and inspect page elements while checking web application behavior.
Operate Chrome from Qwen Code to navigate pages, click controls, fill forms, and capture screenshots. It can work with existing tabs or new ones, using page structure and visual controls to carry out browser tasks.
Prepare medical device regulatory strategies and submission documents for FDA, EU, and other markets. Compare application routes, organize technical and clinical evidence, draft responses to regulator questions, and track submission schedules.
Manage multiple apps and shared packages in one repository. Analyze dependencies and change impacts, limit builds and tests to affected packages, configure caching, and plan repository consolidation while preserving Git history.
Turn a Markdown slide deck into a single HTML file for browser presentations. Navigate with the keyboard, view speaker notes and the next slide in presenter mode, and print the deck as a PDF with one slide per page.
Automate a real browser from the terminal to navigate pages, fill forms, extract data, and investigate interface problems. Use page snapshots to identify controls, and capture screenshots or traces, records of browser activity, for review.
Route code changes and SQL analysis to isolated Kortix work sessions with clear requirements and workspace details. Coordinate parallel investigations or independent pull request reviews, then summarize deliverables, verification results, and differences between findings.
Organize knowledge notes with links that explain their relationships, search saved information, review conflicting claims, and prepare weekly digests. Retrieve earlier work sessions and conversations by topic or date to recover context before continuing a task.