cat ~/الجديد

ray-data @zechenzhangAGI

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images....

nemo-curator @zechenzhangAGI

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16×...

transformer-lens-interpretability @zechenzhangAGI

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate...

sparse-autoencoder-training @zechenzhangAGI

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network...

pyvene-interventions @zechenzhangAGI

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention...

nnsight-remote-interpretability @zechenzhangAGI

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote...

unsloth @zechenzhangAGI

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

peft-fine-tuning @zechenzhangAGI

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models...

llama-factory @zechenzhangAGI

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA,...

axolotl @zechenzhangAGI

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO,...

typefully @typefully

>

typescript-craft @fredericvilcot

Apply software craftsmanship principles to TypeScript code: type safety, functional patterns, clean architecture,...

nchan-expert @tailuge

Expert guidance for Nchan, a scalable pub/sub server for Nginx. Use this skill when you need to configure Nchan...

ops-incident-workload @buyangnie

|

ops-incident-sla-analysis @buyangnie

|

ops-incident-quality @buyangnie

|

ops-incident-major-analysis @buyangnie

|

customer-cross-overview @buyangnie

|

adhoc-cross-analysis @buyangnie

|

using-pandas @indiosmo

Idiomatic pandas usage patterns and performance best practices. Use when writing or reviewing pandas code to ensure:...

searching-docs @indiosmo

Search library/API documentation using Context7 and Ref MCP tools. Use when Claude needs to: (1) Look up API syntax...

processing-xlsx @indiosmo

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and...

processing-pdfs @indiosmo

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting...

creating-skills @indiosmo

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an...