Daniel Avila

Plan and improve paid advertising on Google Ads, Meta, LinkedIn, and other platforms. Develop ad copy, audience targeting, and budget plans, then use acquisition costs and advertising returns to guide campaign improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose advertising platforms for a goal and budget
• Develop ad copy and creative test ideas
• Review campaigns with high customer acquisition costs

Create or fix structured data, code that describes page content to search engines. The skill selects suitable schema.org types, prepares JSON-LD markup, and provides placement instructions and validation checks for products, articles, FAQs, and other pages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add structured data to product pages
• Describe articles and FAQs for search engines
• Fix errors in existing structured data

Design or improve customer referral and affiliate programs. Plan rewards, sharing methods, recruitment, and launch steps, then assess referral performance and costs to identify improvements, including measures to reduce abuse.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a customer referral program
• Designing affiliate commissions and recruitment
• Reviewing referral performance and acquisition costs

Review signup and trial registration flows to identify obstacles to completion. The skill produces prioritized recommendations for fields, authentication, wording, and layout, plus measurement plans and A/B test ideas for checking proposed improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating signup drop-off
• Reviewing required registration fields
• Improving mobile signup usability

Prepare for a career change by identifying skills that apply across industries and rewriting experience in language suited to a target role. Develop resume structure, identify skill gaps, and draft a clear explanation for the transition.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Identifying skills useful in another industry
• Rewriting work experience for a target role
• Planning ways to fill skill gaps

Compare a job posting with your experience to score how well the requirements match. Identify strengths, missing qualifications, and potential concerns, then plan application priorities, resume adjustments, and points to address in a cover letter.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare a job's requirements with your experience
• Prioritize jobs before preparing applications
• Plan resume adjustments and cover letter points

Creates tailored cover letters from a resume and job description, connecting experience and achievements to the role’s requirements. Adapts tone to the company, addresses qualification gaps, and provides alternative openings and interview talking points.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing a cover letter for a specific role
• Explaining transferable skills during a career change
• Addressing gaps in required qualifications

Plan large sets of search-focused pages using templates and data, such as location guides, comparisons, and directories. Define unique content for each page, URL patterns, internal links, and quality checks before launch.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning service pages for multiple locations
• Designing templates for product comparison pages
• Structuring a directory or industry glossary

Design and refine prompts for LLM applications by organizing roles, context, instructions, constraints, and output formats. Develop representative examples, manage the information supplied to the model, and evaluate changes to improve how consistently responses match expectations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Structuring a system prompt for an LLM application
• Specifying response formats and constraints
• Creating examples that include edge cases

Plan caching for repeated LLM requests by choosing what to reuse: shared prompt beginnings, complete responses, or documents loaded in advance. Covers Anthropic prompt caching, cache invalidation, and problems caused by changing inputs or outdated answers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reusing shared instructions across Claude requests
• Caching answers to repeated or similar questions
• Planning document preloading with CAG

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Train language models with SimPO using pairs of preferred and rejected answers. Configure preference training without a separate reference model, adapt settings for base or instruction models, and address unstable training, memory limits, or lost capabilities.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Training a base model with preferred and rejected answers
• Further tuning an instruction model with preference data
• Adjusting training settings for math and code tasks

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compressing LLMs without calibration datasets
• Serving quantized models with vLLM or HuggingFace Transformers
• Comparing bit widths and inference backends

Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run a language model within limited GPU memory
• Load a pre-quantized model for text generation
• Quantize and save your own trained model

Design RAG systems that retrieve relevant documents to support LLM answers. The skill guides document splitting, meaning-based and keyword search, result reranking, and separate retrieval evaluation to improve the context passed to the model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing document retrieval for LLM answers
• Reviewing document splitting strategies
• Combining keyword and meaning-based search

Design and improve RAG systems, which retrieve documents to support language model answers. Explore meaningful document splitting, vector storage, combined keyword and semantic search, and relevance ranking while checking common causes of poor retrieval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design a system that answers questions using documents
• Review document splitting when search misses relevant content
• Combine keyword search with search based on meaning

Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting contact and company details from text
• Classifying articles into predefined categories
• Checking review analysis against validation rules

Guides Python agent development with PydanticAI, covering tool calls and structured outputs checked against defined data types. Explains service injection, provider switching, streaming responses, and tests that run without calling a real language model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building agents that return validated structured data
• Connecting customer support agents to order data
• Testing agent logic without real model calls

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• 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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Guides language model training with GRPO in TRL, comparing several responses and rewarding better results. Covers dataset preparation, scoring rules for correctness and format, training configuration, monitoring, and saving models for later use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Training models to follow JSON or XML formats
• Designing rewards for math and coding tasks
• Adjusting training to available GPU memory

Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a method for training models on human preferences
• Setting up PPO training with a reward model
• Configuring GRPO training without a critic model