GitHub

brainstorming-research-ideas

Structured frameworks for discovering the next research idea. This skill provides ten complementary ideation lenses that...

by Orchestra-Research

github

langsmith

Development platform for debugging, evaluating, and monitoring language models and AI applications. Use LangSmith when: ...

by Orchestra-Research

github

miles

miles is a high-performance, enterprise-ready RL framework optimized for large-scale model post-training. Built as a pro...

by Orchestra-Research

github

sentence-transformers

Python framework for sentence and text embeddings using transformers. Use when: Need high-quality embeddings for RAG Sem...

by Orchestra-Research

github

sentencepiece

Unsupervised tokenizer that works on raw text without language-specific preprocessing. Use SentencePiece when: Building ...

by Orchestra-Research

github

torchtitan

TorchTitan is PyTorch's official platform for large-scale LLM pretraining with composable 4D parallelism (FSDP2, TP, PP,...

by Orchestra-Research

github

compiler

You are the ARA Universal Compiler. Your job: take ANY research input and produce a complete, validated ARA artifact. Yo...

by Orchestra-Research

github

ml-training-recipes

Battle-tested patterns for PyTorch training across domains. Drawn from production codebases (Karpathy's autoresearch/nan...

by Orchestra-Research

github

nanogpt

nanoGPT is a simplified GPT implementation designed for learning and experimentation. Installation: pip install torch nu...

by Orchestra-Research

github

weights-and-biases

Use Weights & Biases (W&B) when you need to: Track ML experiments with automatic metric logging Visualize training in re...

by Orchestra-Research

github

nemo-curator

NVIDIA's toolkit for preparing high-quality training data for LLMs. Use NeMo Curator when: Preparing LLM training data f...

by Orchestra-Research

github

lambda-labs

Comprehensive guide to running ML workloads on Lambda Labs GPU cloud with on-demand instances and 1-Click Clusters. Use ...

by Orchestra-Research

github

simpo

SimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model. Install...

by Orchestra-Research

github

xlsx

Every Excel model MUST be delivered with ZERO formula errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?) Study and EXACTLY m...

by OpenCoworkAI

github

skill-creator

This skill provides guidance for creating effective skills. Skills are modular, self-contained packages that extend Clau...

by OpenCoworkAI

github

pptx

Create, edit, or analyze the contents of .pptx files when requested. A .pptx file is essentially a ZIP archive containin...

by OpenCoworkAI

github

pdf

This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced featur...

by OpenCoworkAI

github

docx

A .docx file is a ZIP archive containing XML files. | Task | Approach | |------|----------| | Read/analyze content | pan...

by OpenCoworkAI

github

install-from-remote-library

Install from a shared library repo without guessing, over-installing, or skipping the preview step. Always inspect the r...

by MoizIbnYousaf

github

curate-a-team-library

Build a managed skills library that another teammate or agent can actually browse, trust, and install. Do not hand-edit ...

by MoizIbnYousaf

github

database-design

-- 1NF: Atomic values, no repeating groups -- 2NF: No partial dependencies on composite keys -- 3NF: No transitive depen...

by MoizIbnYousaf

github

content-research-writer

This skill acts as your writing partner, helping you research, outline, draft, and refine content while maintaining your...

by MoizIbnYousaf

github

code-documentation

Brief description of what this project does. \\\bash npm install npm run dev \\\ Detailed installation instructions... \...

by MoizIbnYousaf

github

build-workspace-docs

Keep workspace documentation in sync with the skills catalog after adding, removing, or curating skills. Always use --dr...

by MoizIbnYousaf

github