Skill Creator

davila7

337 published skills · 4,987,025 GitHub stars across the catalog. View on GitHub ↗

long-context

davila7's avatarfrom davila7★ 15.4k

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

commit

davila7's avatarfrom davila7★ 15.4k

Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

skypilot-multi-cloud-orchestration

davila7's avatarfrom davila7★ 15.4k

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

find-bugs

davila7's avatarfrom davila7★ 15.4k

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

n8n-validation-expert

davila7's avatarfrom davila7★ 15.4k

Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.

create-pr

davila7's avatarfrom davila7★ 15.4k

Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.

training-llms-megatron

davila7's avatarfrom davila7★ 15.4k

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

ray-train

davila7's avatarfrom davila7★ 15.4k

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

n8n-mcp-tools-expert

davila7's avatarfrom davila7★ 15.4k

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

n8n-code-javascript

davila7's avatarfrom davila7★ 15.4k

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.

segment-anything-model

davila7's avatarfrom davila7★ 15.4k

Foundation 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.

llama-cpp

davila7's avatarfrom davila7★ 15.4k

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

deslop

davila7's avatarfrom davila7★ 15.4k

Remove AI-generated code slop from a branch. Use when cleaning up AI-generated code, removing unnecessary comments, defensive checks, or type casts. Checks diff against main and fixes style inconsistencies.

pytorch-fsdp

davila7's avatarfrom davila7★ 15.4k

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

faiss

davila7's avatarfrom davila7★ 15.4k

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

iterate-pr

davila7's avatarfrom davila7★ 15.4k

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

speculative-decoding

davila7's avatarfrom davila7★ 15.4k

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

n8n-expression-syntax

davila7's avatarfrom davila7★ 15.4k

Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.

gguf-quantization

davila7's avatarfrom davila7★ 15.4k

GGUF 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.

rwkv-architecture

davila7's avatarfrom davila7★ 15.4k

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

deepspeed

davila7's avatarfrom davila7★ 15.4k

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

sentence-transformers

davila7's avatarfrom davila7★ 15.4k

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

optimizing-attention-flash

davila7's avatarfrom davila7★ 15.4k

Optimizes 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.

sentencepiece

davila7's avatarfrom davila7★ 15.4k

Language-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.