@davila7
Building AI dev tools with LLMs
350 skills4 repositories 32.9K
Reduce LLM weight usage through pruning, which removes selected model parameters. Explore Wanda and SparseGPT for compression without retraining, choose hardware-friendly patterns for faster inference, and compare the compressed model's accuracy with the original.
Design autonomous AI agents that break goals into tasks, use tools, and review their own work. Covers reasoning and action loops, separate planning and execution, and reliability measures such as cost limits, validation, and logging.
Combine capabilities from multiple fine-tuned LLMs without retraining using mergekit. Choose a merging method, configure how models are blended, and evaluate the resulting model on tasks such as math, code generation, and conversation.
Configure large language model training with NVIDIA Megatron-Core across multiple GPUs. This skill helps choose how to split computation, set training parameters, monitor GPU efficiency, and address memory limits or unstable training.
Build AI agents that inspect screenshots, choose actions, and operate a mouse and keyboard. Covers the observation and action loop, desktop control examples, and isolated environments that restrict access to files, credentials, and networks.
Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.
Design and implement systems that collect, transform, validate, and store data for analysis. Covers scheduled and real-time processing, data warehouses, quality checks, monitoring, and cost tuning using tools such as Apache Spark, dbt, and Airflow.
Configure Claude Code and improve how you assign coding tasks. This guide provides a CLAUDE.md template, practical prompting examples, debugging approaches using logs, and a workflow for making and checking small changes.
Build AI applications with LangChain, including chatbots with conversation history and systems that search documents before answering. The skill provides examples for connecting models, calling tools, retrieving information, and tracing application runs.
Build collaborating AI teams with CrewAI by defining roles, tasks, and shared context. Configure ordered execution or manager-led delegation, add memory and tools, and create workflows that branch based on events or results.
Query an indexed code graph, a database of code relationships, to find callers, dependencies, model associations, and call paths. Use the results to understand which components may need attention before changing a function or model.
Develop Garry's Mod addons with guidance on Lua scripts, file organization, assets, and packaging. Covers server and client execution contexts, API lookup, and debugging, with in-game testing included in the workflow.
Review security across web apps, APIs, mobile apps, Kubernetes, and AI agents using six OWASP references. Identify risky authentication, access controls, configurations, and prompt handling, then use examples and checklists to plan fixes.
Search past conversations to recover decisions, discussions, and context across sessions. Find related ideas by meaning, match exact terms, or locate code identifiers, with options to search only user or assistant messages through local AI Maestro tools.
Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.
Collect daily AI release news from major labs, product changelogs, blogs, and Hacker News. Remove previously reported items and email a digest with source links and brief explanations tailored to the intended audience.
Send signed messages between AI agents, check inboxes, and reply to requests. Supports file attachments, message types, and priorities, with basic messaging running locally and separate identities for each agent.
Adapt an AI agent’s approach to brainstorming, implementation, debugging, review, teaching, or release preparation. Defines how each mode should ask questions, prioritize work, and present results, with automatic mode selection and explicit switching examples.
Organize PyTorch training code with LightningModule and Trainer. Follow examples for validation, logging, model saving, and distributed training across multiple GPUs, with callbacks that add monitoring or stop training when progress stalls.
Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.
Manage the limited information an LLM can process at once. Use importance-based summaries, selective trimming, token counting, and content placement to plan what stays in context and address information loss during long conversations.
Manage multiple local command-line agents in separate tmux sessions. Start and stop agents, assign tasks, and follow their logs, with support for scheduling recurring work through cron. Requires tmux and python3.
Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.
Search automatically generated code documentation to check function parameters, class definitions, API details, and comments before making changes. Find relevant documents by meaning, exact keywords, or document type, then retrieve their full contents.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)