Skill rating

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or

Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "start a research project", or when a task requires mor

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biome

Single-cell RNA-seq analysis. Load .h5ad/10X data, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, cell type annotation, trajectory, for scRNA-seq analysis.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard w

Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems,

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Deploy code to Railway using "railway up". Use when user wants to push code, says "railway up", "deploy", "ship", or "push". For initial setup or creating services, use railway-new skill. For Docker i

Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conf

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering mo

Document frontend data needs for backend developers. Use when frontend needs to communicate API requirements to backend, or user says 'backend requirements', 'what data do I need', 'API requirements',

Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when draft

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

Investigates Google Cloud networking issues by analyzing logs, metrics, and diagnostics. Use when investigating VPC Flow Logs, NAT, firewall, or threat logs, querying latency and throughput metrics, o

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 (

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features,

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange interven

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignme

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

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad c

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). I

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

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

Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique.

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, N

Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task li

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture fro

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNe

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of arc

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 fo

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string upda

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a p

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Comprehensive React and Next.js performance optimization guide with 40+ rules for eliminating waterfalls, optimizing bundles, and improving rendering. Use when optimizing React apps, reviewing perform

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 opti

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, Offi

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systemati

Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x bet

When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "registration friction," "signup form optimizat

Transform resume bullets into detailed portfolio case studies with context, action, and outcome. Use when the user mentions portfolio, case study, project write-up, or expanding a resume bullet into a