Skill Creator

davila7

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

huggingface-accelerate

davila7's avatarfrom davila7★ 15.4k

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

code-review

davila7's avatarfrom davila7★ 15.4k

Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.

dspy

davila7's avatarfrom davila7★ 15.4k

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

tensorboard

davila7's avatarfrom davila7★ 15.4k

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

model-pruning

davila7's avatarfrom davila7★ 15.4k

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

moe-training

davila7's avatarfrom davila7★ 15.4k

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

lambda-labs-gpu-cloud

davila7's avatarfrom davila7★ 15.4k

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

n8n-workflow-patterns

davila7's avatarfrom davila7★ 15.4k

Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.

evaluating-code-models

davila7's avatarfrom davila7★ 15.4k

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

hqq-quantization

davila7's avatarfrom davila7★ 15.4k

Half-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.

planning-with-files

davila7's avatarfrom davila7★ 15.4k

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

clip

davila7's avatarfrom davila7★ 15.4k

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

gptq

davila7's avatarfrom davila7★ 15.4k

Post-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.

unsloth

davila7's avatarfrom davila7★ 15.4k

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

json-canvas

davila7's avatarfrom davila7★ 15.4k

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

instructor

davila7's avatarfrom davila7★ 15.4k

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

phoenix-observability

davila7's avatarfrom davila7★ 15.4k

Open-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.

model-merging

davila7's avatarfrom davila7★ 15.4k

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

nanogpt

davila7's avatarfrom davila7★ 15.4k

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

screenshot-feature-extractor

davila7's avatarfrom davila7★ 15.4k

Analyze 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.

task-execution-engine

davila7's avatarfrom davila7★ 15.4k

Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-design-assistant output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.

skill-creation-guide

davila7's avatarfrom davila7★ 15.4k

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

feature-design-assistant

davila7's avatarfrom davila7★ 15.4k

Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.

railway-domain

davila7's avatarfrom davila7★ 15.4k

Add, view, or remove domains for Railway services. Use when user wants to add a domain, generate a railway domain, check current domains, get the URL for a service, or remove a domain.