A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.
This repository also configures its own agents. See what dr-claw tells them →
Skill Claude Code
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
Skill Claude Code needs its repo
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
Skill Claude CodeCodex
Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. 9 subcommands: plan, debug, fix, security, ship, scenario, predict, learn.
Skill Claude CodeCodex needs its repo
This skill should be used when the user asks to "run initial analysis", "analyze single-cell data", "QC my data", "run bioinformatics pipeline", "generate analysis report", "explore my dataset", "do exploratory data analysis", "initial data analysis", or needs to perform quality control, dimensionality reduction…
Skill Claude CodeCodex needs its repo
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Skill Claude CodeCodex
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or…
Skill 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.
Skill Claude CodeCodex needs its repo
Multi-source ML dataset discovery. Search HuggingFace Hub, OpenML, GitHub, and paper cross-references for datasets relevant to a research task. Use when asked to "find datasets for", "search ML datasets", "what datasets exist for", or "discover training data for".
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.
Skill Claude CodeCodex
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
Skill Claude CodeCodex
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA…
Skill Claude CodeCodex
Adds PyTorch FSDP2 (fullyshard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
Skill Claude CodeCodex
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
Skill Claude CodeCodex
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
Skill Claude CodeCodex
Use when a quest needs one or more follow-up runs such as ablations, robustness checks, error analysis, or failure analysis after a main experiment.
Skill Claude CodeCodex
Use when a quest needs to attach, import, reproduce, repair, verify, compare, or publish a baseline and its metrics.
Skill Claude CodeCodex
Use when the quest needs an explicit go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition with reasons and evidence.
Skill Claude CodeCodex
Use when a quest is ready for a concrete implementation pass or a main experiment run tied to a selected idea and an accepted baseline.
Skill Claude CodeCodex
Use when a quest needs a polished milestone chart, paper-facing figure, appendix figure, or a mandatory render-inspect-revise pass before treating a figure as final.
Skill Claude CodeCodex
Use when the quest is ready to consolidate final claims, limitations, recommendations, summary state, and graph exports before stopping or archiving.
Skill Claude CodeCodex
Full DeepScientist research pipeline: scout → baseline → idea → experiment → analysis → optimize → write → review → finalize. End-to-end autonomous research lifecycle.
Skill Claude CodeCodex
Use when a quest needs concrete hypotheses, limitation analysis, candidate directions, or a selected idea relative to the active baseline.
Skill Claude CodeCodex
Use when a quest does not start from a blank state and the agent must first audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials before choosing the next anchor.
Skill Claude CodeCodex
Use when an algorithm-first quest should manage candidate briefs, optimization frontier, branch promotion, or fusion-aware search instead of the paper-oriented default loop.
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: