Explore skills
Showing 57991–58020 of 77104 skills
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexMaterial-UI v7 component library patterns including sx prop styling, theme integration, responsive design, and MUI-specific hooks. Use when working with MUI components, styling with sx prop, theme customization, or MUI utilities.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexDeploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexLLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexGenerate patent-office-compliant figures via the PatentFig AI API — patent line art from text (PNG or SVG), vectorize drawings to SVG/DXF/vector PDF, AI-upscale images, and convert to filing-ready TIFF/PDF/PNG. Use when the user asks for patent drawings, patent figures, invention diagrams, USPTO/EPO-compliant line art, vectorizing a drawing for CAD, or preparing figures for a patent filing. Requires a PATENTFIG_API_KEY environment variable.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
orlandoneto/agent-skills
Stars: 0Claude CodeCodexHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexReact useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexAnalyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task lists from UI designs, (3) Batch analyzing multiple app screens, (4) Conducting competitive analysis from visual references.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexThis skill should be used when the user asks to "create a Telegram bot", "build a Telegram chatbot", "set up a Telegram webhook", "add inline keyboards to a bot", "handle Telegram callback queries", "implement Telegram payments", "send media via Telegram bot", "configure Telegram bot commands", "deploy a Telegram bot", or mentions the Telegram Bot API, telegram bot tokens, getUpdates, setWebhook, or bot frameworks like node-telegram-bot-api, grammy, python-telegram-bot, or aiogram. Provides comprehensive guidance for building production-ready Telegram bots with Node.js and Python.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexYou MUST use this before writing or changing any production code, including one-line fixes and when the user is in a hurry: a new feature, a bug fix, a refactor, a behavior change. Write the failing test first, run it and watch it fail for the right reason, write the minimal code that passes, then run the whole test suite before saying it is done. Skip it only for throwaway prototypes, generated code or configuration-only changes, and only with the user's OK.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
orlandoneto/agent-skills
Stars: 0Claude CodeCodexHelp Steve add a feature or change to the project while teaching him how building software with Claude works. Use when Steve wants a new feature, a new data source, a change to scoring or the report, or asks "can it do X?".
grijalva10/oc-seller-finder
Stars: 1Claude CodeCodexCheck Steve's Gmail for sent outreach and owner replies, and update each home's status. Use when Steve asks about replies, responses, follow-ups, or "who wrote back".
grijalva10/oc-seller-finder
Stars: 1Claude CodeCodex