Skill Claude CodeCodex
Generate a Python code skeleton from an experiment blueprint.
not rated 1.3k
+2 10d ago A SkillSpector: pass 15 tokens
original MIT
1.3kStars on the repository
27Mods indexed here, across every type
10d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Search academic literature and generate research hypotheses.
not rated 1.3k
+2 10d ago A SkillSpector: pass 14 tokens
original MIT
Skill Claude CodeCodex
Produce an experiment blueprint from a research hypothesis.
not rated 1.3k
+2 10d ago A SkillSpector: pass 14 tokens
original MIT
Skill Claude CodeCodex
Draft a LaTeX research paper from all previous stage outputs.
not rated 1.3k
+2 10d ago A SkillSpector: pass 17 tokens
original MIT
autoresearch
05Skill Claude CodeCodex
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
not rated 1.3k
+2 10d ago A 98 tokens
copy · 100% MIT
Skill Claude CodeCodex
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
not rated 1.3k
+2 10d ago A 68 tokens
copy · 100% MIT
Skill Claude CodeCodex
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.
not rated 1.3k
+2 10d ago A 69 tokens
copy · 88% MIT
Skill Claude CodeCodex
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
not rated 1.3k
+2 10d ago A 43 tokens
copy · 100% MIT
Skill Claude CodeCodex
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
not rated 1.3k
+2 10d ago A 50 tokens
copy · 100% MIT
Skill Claude CodeCodex
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
not rated 1.3k
+2 10d ago A 85 tokens
copy · 89% MIT
Skill Claude CodeCodex
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification…
not rated 1.3k
+2 10d ago A 80 tokens
copy · 86% MIT
Skill Claude CodeCodex
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
not rated 1.3k
+2 10d ago A 88 tokens
copy · 100% MIT
Skill Claude CodeCodex
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
not rated 1.3k
+2 10d ago A 82 tokens
copy · 84% MIT
ray-data
14Skill Claude CodeCodex
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
not rated 1.3k
+2 10d ago A 70 tokens
copy · 100% MIT
Skill Claude CodeCodex
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.
not rated 1.3k
+2 10d ago A 51 tokens
copy · 100% MIT
unsloth
16Skill Claude CodeCodex
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
not rated 1.3k
+2 10d ago A 39 tokens
copy · 81% MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: