Daniel Avila

Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.

中文简介正在准备中。当前显示英语简介。

• Generate document embeddings for RAG
• Find sentences with similar meanings
• Group documents by topic

Execute an implementation plan in one session by assigning a fresh subagent, a separate task-focused agent, to each task. Check specification compliance first, then code quality, and repeat fixes and reviews before proceeding.

中文简介正在准备中。当前显示英语简介。

• Execute an existing plan with mostly independent tasks
• Check specification compliance before reviewing code quality
• Repeat fixes and reviews for each implementation task

Set up reinforcement learning, which trains models using rewards, with verl. Follow workflows for preparing data, configuring GRPO or PPO training, scaling across GPUs, and addressing memory errors or unstable training.

中文简介正在准备中。当前显示英语简介。

• Training a math reasoning model with GRPO
• Configuring PPO training with a critic model
• Scaling large model training across multiple nodes

Coordinate specialized agents in Claude Code to divide development and review tasks, pass findings between stages, and combine results into one report with prioritized recommendations and action items.

中文简介正在准备中。当前显示英语简介。

• Reviewing code from security, performance, and quality perspectives
• Coordinating frontend, backend, and database work
• Combining specialist findings into a prioritized report

Provides prompt templates for coding, writing, analysis, and creative work. Helps define the AI's role, specify the desired output, add examples and constraints, and refine requests using a practical checklist.

中文简介正在准备中。当前显示英语简介。

• Draft a prompt for code review
• Create requests for clear technical documentation
• Prepare prompts for feature and naming ideas

Guide the design of AI product features with output validation, responses displayed as they arrive, prompt versioning, and testing. Address API costs, failures, and unsafe input when preparing language model integrations for production.

中文简介正在准备中。当前显示英语简介。

• Reviewing AI features before production release
• Designing validation for AI-generated output
• Managing prompt versions and regression tests

Build AI workflows with DSPy by defining inputs and outputs and combining reusable components. Create question answering systems that use retrieved documents, tool-using agents, and automatically optimized prompts, then compare results with evaluation data.

中文简介正在准备中。当前显示英语简介。

• Build question answering systems that use retrieved documents
• Optimize prompts using examples and evaluation metrics
• Combine AI tasks into reusable processing stages

Turn feature requirements into test plans, step-by-step manual tests, regression suites for checking existing features, and reproducible bug reports. The skill also supports comparing implemented interfaces with Figma designs and documenting visual differences.

中文简介正在准备中。当前显示英语简介。

• Plan tests for a new feature
• Write manual checkout test cases
• Organize regression checks before a release

Design focused products built around AI APIs, with guidance on prompts, model selection, output validation, and user experience. Track usage and set cost limits to connect product behavior with operating costs and pricing decisions.

中文简介正在准备中。当前显示英语简介。

• Design an AI service for a specific task
• Create prompt templates and validate responses
• Track API costs and set usage limits

Build and operate LLM applications with guidance on RAG, which uses retrieved documents to inform answers. Covers document indexing, vector database selection, prompt improvement, response evaluation, caching, and estimates of model usage costs.

中文简介正在准备中。当前显示英语简介。

• Building an assistant that answers from documents
• Choosing a vector database for document search
• Comparing answer quality after prompt changes

Build AI agents with LangGraph by connecting processing steps into a graph. Define shared state, conditional paths, tool calls, saved checkpoints, and human review points to create workflows that retain information as they run.

中文简介正在准备中。当前显示英语简介。

• Building an agent that calls tools in a loop
• Sharing accumulated findings between multiple agents
• Routing requests to different processing paths

Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill explains model selection, batch processing, and memory-saving settings, with Python examples for connecting image understanding to language models.

中文简介正在准备中。当前显示英语简介。

• Generating captions for multiple images
• Building a question-answering system for images
• Searching an image collection with text

Reduce GPU memory use by loading language models in 8-bit or 4-bit formats with bitsandbytes and HuggingFace Transformers. Includes configuration examples, QLoRA fine-tuning of compressed models, and optimizers that reduce memory needed during training.

中文简介正在准备中。当前显示英语简介。

• Load larger models within limited GPU memory
• Compare 8-bit and 4-bit model settings
• Fine-tune a model with QLoRA

Design LLM applications using patterns for answers grounded in documents, agents that use tools, and prompt testing. Implementation examples also cover monitoring response quality, latency, costs, and failures during operation.

中文简介正在准备中。当前显示英语简介。

• Building an assistant that answers from internal documents
• Choosing an architecture for an agent that uses tools
• Comparing and versioning prompts

Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.

中文简介正在准备中。当前显示英语简介。

• Compare models using the same benchmark tests
• Run large evaluations on a Slurm cluster
• Evaluate safety and image understanding

Get guidance on adapting LLMs with Unsloth, including implementation, API usage, and debugging. Covers LoRA and QLoRA, methods for adjusting models with fewer trainable parameters, with a focus on training speed and memory use.

中文简介正在准备中。当前显示英语简介。

• Learning how to fine-tune models with Unsloth
• Exploring LoRA and QLoRA for efficient training
• Implementing features using Unsloth APIs

Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.

中文简介正在准备中。当前显示英语简介。

• Exploring features with a pretrained SAE
• Training and evaluating a custom SAE
• Studying overlapping concepts in model activity

Integrate Flash Attention into transformer models to reduce processing time and GPU memory use for long sequences. Covers PyTorch integration, advanced attention options, and benchmarks that compare speed, memory use, and output accuracy.

中文简介正在准备中。当前显示英语简介。

• Speeding up transformer training on long sequences
• Reducing GPU memory use during attention
• Adding Flash Attention to a PyTorch model

Set up Langfuse to record LLM application activity, costs, and response times. Manage prompt versions, organize evaluation datasets, and compare results to investigate failures and guide improvements using recorded evidence.

中文简介正在准备中。当前显示英语简介。

• Investigating failures in LLM applications
• Comparing prompt versions and evaluation scores
• Monitoring LLM costs and response times

Deploy language models with vLLM through an OpenAI-compatible API or offline batch processing. Tune response speed, throughput, and GPU memory use with quantization, which reduces numerical precision, and execution across multiple GPUs.

中文简介正在准备中。当前显示英语简介。

• Deploy an OpenAI-compatible language model API
• Generate text from many prompts in a batch
• Serve quantized models with limited GPU memory

Guides experiments that inspect and change internal model values using nnsight. Covers local PyTorch models and remote experiments through NDIF, including replacing intermediate values to test how particular layers affect a model’s predictions.

中文简介正在准备中。当前显示英语简介。

• Inspecting layer outputs and attention patterns
• Replacing internal values to compare predictions
• Running large-model experiments through NDIF

Investigate why a PyTorch model behaves a certain way by changing its internal values with pyvene. The skill guides experiments that swap or remove activations, train interventions, compare outputs, and save or share intervention configurations.

中文简介正在准备中。当前显示英语简介。

• Locating model components that affect an output
• Swapping activations to test behavioral hypotheses
• Training interventions to investigate causal structure

Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.

中文简介正在准备中。当前显示英语简介。

• Inspecting attention patterns and intermediate values
• Testing output changes by replacing internal activations
• Analyzing attention head contributions to predictions

Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.

中文简介正在准备中。当前显示英语简介。

• Setting up an LLM server on NVIDIA GPUs
• Configuring FP8 or INT4 quantization
• Distributing large models across multiple GPUs