Menu
Skills in this repository
SkillsMP has collected 313 skills from synthetic-sciences/openscience. Open a skill to review its source and details.
synthetic-sciences/openscienceShowing 40 of 313 collected skills.
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…
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with…
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any…
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
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…
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups…
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
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…
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model…
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic…
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training…
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium…
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL…
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing…
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works…
Fast LLM fine-tuning with Unsloth - 2-5x faster training, 50-80% less VRAM. Use for single-GPU LoRA/QLoRA SFT, GRPO/RL reasoning training, vision/TTS fine-tuning, and GGUF export to Ollama/vLLM/llama.cpp. Supports 300+ models including Llama, Qwen, Gemma,…
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that…
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating…
Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.
Install or remove third-party openscience skills from a public git repository. Use when the user says "add this skill <url>", "install skill <url>", or "remove skill <namespace>". The skill runs locally via `openscience skill add|list|remove`, fetches the…
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems…
Training patterns for autoregressive neural PDE solvers (FNO, DeepONet, CNO). Covers rollout training, noise injection for stability, multi-component loss functions (H1, frequency-sensitive, boundary-aware), per-channel normalization for coupled…
Bayesian parameter estimation with MCMC (emcee) and probabilistic programming (PyMC). Posterior distributions, corner plots, model evidence, convergence diagnostics. Use when you need full posterior distributions, not just point estimates.
Discover conserved quantities and symmetries from trajectory data. Identifies energy, momentum, angular momentum, and custom invariants using neural networks and symbolic methods. Inspired by Noether's theorem.
Automated dimensional analysis — Buckingham Pi theorem, non-dimensionalization, unit validation with pint, and characteristic scale estimation. Use before any physics computation to verify consistency and reduce parameter space.
Analyze nonlinear dynamical systems — phase portraits, fixed points, stability analysis, bifurcation diagrams, Poincare sections, Lyapunov exponents, and chaos detection. Use for any autonomous or non-autonomous ODE system where qualitative behavior matters.
Computational fluid dynamics — Navier-Stokes solvers, lid-driven cavity, channel flow, vortex methods, turbulence statistics, drag/lift computation. Spectral and finite-difference methods for incompressible and compressible flows.
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or…
Hamiltonian mechanics — symplectic integrators (leapfrog, Yoshida), Hamilton's equations, Poisson brackets, canonical transformations, action-angle variables, and KAM theory analysis. Use for energy-conserving long-time integration of conservative systems.
Train neural operators (FNO, DeepONet) to learn solution maps for parametric PDE families. Once trained, solve new PDE instances in milliseconds. Use when you need to solve many instances of the same PDE with different parameters/ICs/BCs.
Solve ordinary differential equations (initial and boundary value problems). Supports stiff/non-stiff systems, event detection, Hamiltonian/symplectic integration, parameter sweeps, and phase space analysis. Use for any ODE system in physics, engineering, or…
Solve partial differential equations — finite differences, spectral methods, and physics-informed neural networks (PINNs via DeepXDE). Supports 1D/2D/3D, steady/transient, linear/nonlinear PDEs with Dirichlet, Neumann, and periodic boundary conditions.
Query physics databases — NIST CODATA constants, NIST Chemistry WebBook, Materials Project, Particle Data Group (PDG), OEIS sequences. Always use these instead of hardcoding physical constants.
Nonlinear curve fitting for physics data with proper error propagation, chi-squared analysis, residual diagnostics, confidence intervals, and model comparison (AIC/BIC). Use for any parameter extraction from experimental or simulation data.