372 skills · sorted by relevance
Automate website navigation, form filling, content collection, and Windows desktop interactions. The skill selects browser or desktop tools for the task and guides screenshot capture and desktop network traffic observation when needed.
Build a PowerPoint file with Python when no Office app is open. It uses python-pptx, applies a supplied firm template when available, and saves the deck locally with a path for collection by the surrounding workflow.
Generate an Excel workbook file in an agent session without an open Office app. Use Python and openpyxl to organize inputs, formulas, and checks, then save the .xlsx file and return its relative path.
Build C++ applications for custom Zoom video sessions on Linux, including bots that run without a display. Get guidance on capturing and supplying raw audio and video, connecting Qt or GTK interfaces, and configuring Docker environments.
Develop C++ bots that join existing Zoom meetings from Linux servers without a graphical interface. Follow guidance for recording raw audio and video, feeding transcription or AI workflows, and handling authentication, recording permissions, and Docker audio setup.
Build Zoom meeting integrations in Windows C++ applications, including custom interfaces and bots that run without a visible interface. Guidance covers authentication, audio and video data access, project setup, and troubleshooting callbacks through the Windows message loop.
Coordinate multiple Mastra Code workers to investigate and fix GitHub issues in parallel. Keep each issue in a separate working directory, track progress in reports, review changes, and manage pull requests, reviewer feedback, and automated checks.
Reproduce Mastra Code bugs with a real model and compare timestamped logs across network, streaming, execution, and terminal interface layers. Use the evidence to locate timing problems, incorrect token rates, flicker, or stuck status displays.
Convert Markdown files into styled HTML suitable for WeChat and other platforms. Choose themes, colors, and fonts, preserve code and diagrams, and optionally turn external links into numbered references at the end.
Control a running OpenWork app from the shell to inspect UI changes and reproduce chat states. Start fresh sessions, select models, send prompts, wait for completion, capture screenshots, and run JavaScript, with no visible window by default.
Turn 3D models into printer instructions called G-code with OrcaSlicer. The skill selects existing printer and material presets, slices the model, and checks dimensions and output settings before handing over the files.
Create and edit Kortix presentations as web pages, with diagrams revealed step by step and presenter scripts. The skill also covers product films rendered to MP4, plus keyboard controls, recording procedures, and quality checks.
Delegate development tasks to external coding agents such as Codex and Claude Code through command-line tools. Choose local or container execution, check setup, provide a self-contained task brief, and inspect important changes afterward.
Build and run computer-use-demo in Docker, then use Playwright to test its Streamlit interface without opening a visible browser. Save conversation transcripts, API exchanges, and screenshots to inspect behavior after changes.
Turn a research paper into a conference poster using its figures and findings. Produce one HTML/CSS file and a print-ready PDF, with measured layout checks and Gemini reviews of content accuracy and final appearance.
Turn a research paper into a conference poster using HTML/CSS and figures from the paper. Check claims against evidence, measure the print layout, and produce a PDF matched to the venue’s required dimensions.
Manage Contentful spaces, the containers used to organize content, from Claude Code through Composio. List accessible spaces, inspect creation dates and current versions, rename spaces, and review the organization's space inventory.
Test local web applications with Python scripts using Playwright, a browser automation tool. Inspect rendered pages, exercise interface controls, capture screenshots and console logs, and use a helper to manage one or more application servers during tests.
Design browser-based pages, dashboards, prototypes, and decks using existing brand guidance and a clear visual process. Build local files, then check rendering, layout, links, and accessibility before handing over the finished artifact.
Operate real desktop apps and browser windows by inspecting controls, clicking, typing, and checking the result after each action. Use it for settings changes, window arrangement, or verifying a complete workflow through the interface.
Import FBX 3D models into CARLA on UE 5.8 and register them as props that can be placed in a simulation. Check measured dimensions, adjust scale, verify placement on a running server, and undo imports when needed.
Run Scenic traffic scenarios on a CARLA server. First test whether a valid scene can be generated, then simulate with limits on runs and steps, record the outcome, and restore the world's asynchronous setting afterward.
Evaluate NVIDIA Cosmos Policy for robot manipulation in LIBERO and RoboCasa simulations. Follow GPU environment setup, configure rendering without a display, run small checks before larger benchmarks, inspect success rates, and profile inference latency.
Build and debug Shopify themes, custom apps, and storefronts connected through APIs. The skill covers Liquid templates, app authentication, checkout extensions, performance improvements, and the configuration, testing, and deployment steps needed for implementation.