Quantizes 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,...
6997 results
(69.2ms)
page 5 / 350
Quantizes 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,...
gpui-style-guide
0.00
GPUI Component project style guide based on gpui-component code patterns. Use when writing new components, reviewing code, or ensuring consistency with existing gpui-component implementations....
m14-mental-model
0.00
Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why...
Use when designing or reviewing systems handling sensitive data (PII, PHI, financial, auth credentials), building features with security implications (auth, payments, file uploads, APIs),...
shaoji-style-writer
0.00
A specialized scriptwriting persona (Shaoji Style) that packages deep existential tragedy within a "wholesome, positive" facade. Expert in constructing emotional traps, tragic aesthetics, and...
Write LinkedIn posts in Kasper Junge's distinctive Danish style. Use when asked to write LinkedIn content, social media posts, or project announcements in Kasper's voice. Triggers include "skriv i...
styled-components best practices for CSS-in-JS development in React applications
Expertise in Go programming decisions according to the Google Go Style Guide. Focuses on specific choices for naming, error handling, and language usage.
go-uber-style-guide
0.00
Use this skill to write, refactor, or review Go code according to the Uber Go Style Guide. It ensures strict adherence to correctness, safety, and idiomatic patterns.
Expertise in Go programming according to the Google Go Style Guide. Use when the user needs to write, refactor, or review Go code for clarity, simplicity, and maintainability. This skill ensures...
General principles for structured content modeling that apply across CMSs, with Sanity-specific guidance. Use when designing content schemas, planning content architecture, or evaluating content...
claude-extensibility
0.00
Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents,...
fal-text-to-image
0.00
Generate high-quality images from text prompts using fal.ai's text-to-image models. Supports intelligent model selection, style transfer, and professional-grade outputs.
runtime-skills
0.00
Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning.
html-style
0.00
>
pymc-modeling
0.00
>
topic-modeler
0.00
Extract topics from text collections using LDA (Latent Dirichlet Allocation) with keyword extraction and topic visualization.
go-style
0.00
|
voxel-art
0.00
Expert voxel artist with deep knowledge of MagicaVoxel workflows, palette design, animation techniques, mesh conversion, and game engine optimization. This skill represents insights from...