Classify images using written labels without additional training data, or find images that match a text query. This skill provides CLIP workflows for image-text similarity, batch processing, and storing searchable image representations in vector databases.
Control the Unreal Engine editor to build scenes, place objects, adjust lighting and materials, and frame camera shots. The skill guides inspection, incremental edits, visual checks, saving, and producing screenshots or renders.
Look up stock and cryptocurrency prices, find ticker symbols by company name, and compare several stocks. Uses Yahoo Finance data to return daily price history, trading volume, and performance statistics in a structured JSON format.
Build Python MCP servers that let AI agents use APIs, databases, and file workflows. MCP is a connection standard for agent tools. The skill covers starter templates, local testing, client registration, and deployment as HTTP endpoints.
Build document search with Chroma, a database that stores text as numerical representations of meaning. Save and update documents, filter by metadata, and connect retrieval to AI applications using LangChain or LlamaIndex.
Fine-tune large language models with LoRA and QLoRA, methods that train small additions to a base model while limiting GPU memory use. Configure training, save task-specific adapters, switch between them, and merge them for deployment.
Train language models on pairs of preferred and rejected answers without a separate reference model. The skill guides training setup, model-specific configurations, parameter tuning, and troubleshooting for unstable training or memory limits.
Create financial Excel workbooks with Python, using formulas, color-coded inputs, source comments, and consistency checks. Build models that reviewers can trace and users can adjust by changing assumptions.
Adapt existing PyTorch training scripts to use multiple GPUs or machines with limited code changes. The skill guides configuration, launch commands, mixed precision, which uses lower-precision numbers, and DeepSpeed or FSDP settings for distributing training work and memory.
Let an AI play Pokemon through an emulator, using screenshots and game memory to guide movement, dialogue, and battles. The skill covers browser viewing, progress tracking, and saving or resuming play with a user-provided ROM.
Implement and debug large-model training with PyTorch FSDP, which splits training state across devices. Consult documentation and code patterns for sharding choices, mixed precision, and checkpoints when building or reviewing distributed training code.
Build an Excel workbook comparing similar companies by revenue, margins, and valuation multiples, which relate company value to sales or earnings. Include formulas, medians, quartiles, and documented sources to support investment or acquisition analysis.
Test an app from the perspective of a frustrated, less technical user. Find confusing steps and barriers, separate actionable usability problems from personal complaints, and produce screenshots, suggested fixes, and prioritized tickets.
Monitor RSS feeds, JSON APIs, and GitHub activity at regular intervals. Included scripts track previously seen item IDs and output only new entries, letting an agent report updates while staying silent when nothing has changed.
Analyze and modify refusal behavior in open-weight language models without retraining. Use OBLITERATUS to select methods suited to available hardware, compare approaches, and evaluate changes in refusal rates and response quality.
Build an Excel workbook showing how an acquisition changes earnings per share. Organize purchase price, funding, and synergy assumptions, compare deal scenarios, calculate the synergies needed to avoid reducing earnings per share, and prepare a concise summary.
Turn written requirements or Mermaid diagram text into interactive HTML diagrams of systems, workflows, sequences, data flows, and states. Explore connections, search the diagram, export images or video, and receive results from nine validation checks.
Create clear educational diagrams for scientific concepts, physical structures, workflows, and data. Output SVG, a scalable vector image format, inside one standalone HTML file with consistent styling and automatic light and dark modes.
Inspect Solana wallet balances, token holdings, transactions, and NFTs with USD pricing. Check portfolio value, token details, recent activity, large SOL transfers, and network statistics through eight commands that require no API key.
Delegate feature development, refactoring, and pull request reviews to Grok Build CLI. Use single-task runs or interactive sessions, monitor longer jobs, and resume earlier work with the project's existing instructions.
Use AudioCraft to generate music, sound effects, and environmental audio from text descriptions. Follow implementation examples for model selection, melody and reference audio guidance, stereo output, batch generation, and saving audio files.
Create hand-drawn architecture diagrams, flowcharts, and sequence diagrams as editable .excalidraw files. Open them in Excalidraw to review or adjust the layout, or optionally upload them to generate a shareable link.
Run ComfyUI workflows to generate images, video, audio, and 3D content. Prepare models and processing nodes, adjust generation settings, create batches of variations, monitor progress, and download results from a local server or Comfy Cloud.
Create poster or cover images that look printed with one or two inks, using a theme, phrase, or photo. Shape the layout, typography, and print texture, and receive the final prompt and design notes.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)