데이터·AI 스킬

Control local language model output with patterns and grammar rules to generate structured JSON, formatted dates, and fixed classification labels. The skill also covers reusable Python functions and workflows that combine multiple generation steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate JSON that follows a defined schema
• Keep dates and email addresses in a specified format
• Classify text using a fixed set of labels

Helps you build similarity search with FAISS to find nearby vectors, numerical representations of data. Covers index selection, saving and loading, GPU use, and tuning search speed, accuracy, and memory consumption for large datasets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building similarity search over large vector datasets
• Choosing indexes for speed, accuracy, and memory use
• Running batch searches on GPUs

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify photos using written category labels
• Find images by describing their content
• Compare images with candidate descriptions

Find and run over 150 cloud AI apps through a shared command-line tool. Generate images and videos, search for information, or upload local images and audio for tasks such as upscaling and avatar generation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate images from prompts
• Turn a local image into a video
• Create an avatar video from a photo and audio

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Studying how language models produce refusals
• Testing refusal-related weight changes without retraining
• Selecting models and methods for available hardware

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tuning a language model with limited GPU memory
• Choosing LoRA settings for a training task
• Switching between task-specific adapters

Integrate Flash Attention into Transformer models to speed up attention, the calculation that relates input elements, while reducing GPU memory use. Covers PyTorch integration, performance measurement, output comparison, and a separate H100 optimization path.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Optimize training with long input sequences
• Reduce memory use during long-context inference
• Measure speed and compare model outputs

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Move a single-GPU training script to multiple GPUs
• Configure mixed precision training
• Set up DeepSpeed or FSDP to reduce memory use

Explore data and develop Python code in a live Jupyter session that keeps variables between runs. Inspect objects, edit notebook cells, and optionally restart and run the whole notebook to check execution from top to bottom.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring data while keeping variables between runs
• Inspecting DataFrames and live Python objects
• Trying API usage and refining complex code

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a base model using preferred and rejected answer pairs
• Further tune an instruction-following model
• Adjust training settings for math and coding tasks

Explore concepts learned by language models using sparse autoencoders, which separate internal activity into a small set of features. Analyze pretrained models, train custom autoencoders, assess reconstruction quality, and experiment with feature based output adjustments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring features with a pretrained SAE
• Training an SAE for a chosen model layer
• Comparing feature responses across input texts

Extract information from text into defined fields, then check types and values with Pydantic, a Python data validation library. The skill covers structured LLM responses, automatic retries after validation failures, and streaming results as they are generated.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting contact or company details from text
• Classifying articles into predefined categories
• Organizing review analysis into consistent fields

Build search and retrieval systems with Pinecone, a managed database for numerical representations of content. Covers data uploads, filtered similarity searches, combined semantic and keyword search, and connections to LangChain and LlamaIndex.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building retrieval for AI answers grounded in documents
• Combining semantic and keyword search
• Filtering results by category or price

Retrieve Hyperliquid market data, wallet balances, positions, and recent trading history without an API key. Review trades alongside market trends and fees, or export price candles and funding payments as JSON for later analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check market prices, funding, and order book depth
• Inspect wallet positions and spot balances
• Review recent trades alongside fees and market trends

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check a wallet's holdings and total value in USD
• Inspect transaction fees and balance changes
• Look up token prices and major holders

Set up and troubleshoot Honcho memory for Hermes so user preferences and facts carry across conversations. Configure how memory is recalled, manage separate agent identities across profiles, and adjust context size, observation settings, and reasoning frequency.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up cloud or self-hosted memory for Hermes
• Investigating missing memories or profile synchronization issues
• Sharing user context across multiple agent profiles

Compare Claude, GPT, and Gemini on the same skill or prompt. Get a table of response times, token usage, and costs, with optional AI scoring to help choose a model for the task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a model for a specific skill
• Comparing response times and costs
• Comparing output quality with optional AI scoring

Extract information from web pages through Aside using existing signed-in sessions. Collect lists, tables, prices, or links and receive one JSON document, a structured data format, without changing the page.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting product names and prices
• Collecting tables and links as JSON
• Reading information from signed-in pages

Turn a Caveman token-usage report into specific edits to instruction files, repeated context, and memory. Review each proposed change before approval, then measure the result and distinguish confirmed file reductions from less certain session-level effects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trimming a large CLAUDE.md file
• Moving repeatedly pasted context into cavemem
• Reviewing duplicate rules and broken memory links

View recorded output tokens, cache-read tokens, response counts, and available mode attribution for a Claude Code session. In other agent environments, find the native usage report where supported, without treating observed usage as proof of savings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking recorded token usage for the current session
• Reviewing response counts and mode attribution
• Aggregating recorded output across sessions

Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding which workflows drive LLM spending
• Investigating slow responses and errors
• Reviewing measured costs and verified savings separately

Organize the information an AI coding agent needs for each task. This skill guides project rules, relevant file selection, conversation summaries, and session handoffs so the agent can follow existing conventions and retain key decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up project rules for AI coding agents
• Select relevant files before starting a task
• Trim stale information from a long conversation

Create HTML dashboards and reports from local data or connected services, with data that can be refreshed without redesigning the page. Record sources, timestamps, and transformations so readers can trace where displayed information came from.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a dashboard whose data can be refreshed
• Create a report with traceable sources
• Turn connected service data into a status page

Find, compare, and run AI models through Replicate’s API, a service interface for calling models. Use it to explore image, audio, and video generation options and support workflows that frequently switch between models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find models for image generation
• Compare audio generation models
• Try video generation models