178 skills · sorted by relevance
Read and display CARLA object bounding boxes, then project them onto a camera image as 2D rectangles. Export an annotated PNG and box coordinates in JSON for object detection annotation work.
Set up ScenarioRunner, CARLA’s scenario engine, with a branch matched to your simulator version. Install dependencies, configure Python search paths, and verify imports to address setup failures before running scenarios.
Read existing CARLA sensors to view live camera or lidar output, save recordings, or inspect a single reading. Display multiple sensors together and check ROS 2 topic names, delivery settings, and whether publishing is enabled.
Creates figures for machine learning papers from draft text or experiment data. Extracts components for Gemini-generated diagrams, chooses suitable charts with matplotlib or seaborn, and adjusts colors, fonts, and export formats for publication.
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
Coordinate AI agents to create short videos, from copy and storyboards to images, narration, subtitles, and MP4 assembly. The workflow includes quality checks, revision requests, and production data reviews to guide later improvements.
Analyze individual stocks using current quotes and historical price data. Calculate trend and momentum measures, identify price gaps and potential support or resistance levels, and produce a three-day outlook with trading scenarios and risk notes.
Transcribe recordings and reshape the text into meeting notes, emails, or social media posts. Combine text from multiple recordings into a continuous document, then prepare the result for copying or sharing while preserving the original meaning.
Generate character images, backgrounds, synthetic speech, and music for product videos featuring 小省导购员, a digital shopping presenter. Coordinate these assets with InfiniteTalk to produce a 25-second vertical video made from five scenes.
Organize audio production into checked stages, from beat timing to mixing and ZIP packaging. Generate and verify each stem, a separate audio part, then check processed files before combining them into a master track.
Produce a master track and separate audio parts through a structured Python workflow. Apply filters and reverb, export WAV files with consistent settings, package them in a ZIP archive, and check that the deliverables meet the requested specifications.
Investigate Python failures in a sandbox, an isolated execution environment, by capturing partial logs, testing functions separately, and checking output files one at a time. Use the findings to identify failing steps and rebuild a working script.
Extract edit times from documents, inspect audio for clicks and level issues, and guide production of stems, or separate audio parts. Each stage includes checks, ending with a mixed export verified for duration, format, and audio levels.
Continue file reading and data processing when execute_code_sandbox or read_file fails. This skill runs multiline Python through run_shell, with examples for text, JSON, spreadsheets, PDF and Word documents, plus basic summaries and grouped calculations.
Produce audio in separate stems, meaning individual instrument tracks, and verify each output as you go. Align track lengths with silence, loops, or crossfades, then apply effects, mix a master, and package the files.
Prepare audio stems, the separate parts of a track, for mixing by matching their durations with silence, loops, or crossfades. Verify each generated and processed file before moving to the next production step.
Add burned-in captions to a finished video using Whisper timings from its own audio. Choose paper, bold, or clean styling, and optionally use narration text to preserve intended spelling. Outputs include the captioned video and an SRT file.
Check whether tools for mathematical modeling, numerical analysis, charts, and paper compilation are installed. Get a report separating required and optional dependencies, platform-specific installation commands, and a follow-up check after approved installation.
Analyze numerical data in Excel with box plots and an outlier summary. Extract error values from text containing the ± symbol, chart their distribution, and export statistical results as a CSV report.
Group Excel figures by department or product line, assign performance tiers, and calculate projections using growth rates set for each tier. Compare current and projected values in charts and summarize overall growth for target setting.
Clean Excel columns by removing unwanted prefixes from numeric values and extracting Chinese characters from text. Add the cleaned results as new columns, then save an Excel file and provide a download link.
Assess numeric Excel columns using IQR, a measure of the middle half of values, to flag outliers. Summarize counts and limits, create box plots, and examine distribution shape to inform data cleaning.
Analyze one Excel worksheet by cleaning column names, extracting numbers, and handling gaps from merged cells. Create category counts, percentages, cross-tabulations comparing groups, high-resolution charts, and CSV exports, with Parquet storage for the data.
Clean Excel data and group records with similar numerical features. Produce a combined view of indicator trends, value distributions, category shares, and grouped data, then export the charts as an image and cleaned records as Excel.