mxslr

mxslr/mlcraft

Plugin Claude Code

Marketplace hosting the mlcraft plugin, a professional AI/ML research-engineering workflow for AI coding assistants.

mxslr/mlcraft

Plugin Claude Code

Professional AI/ML research-engineer workflow: research papers first, pick the best method for each problem (computer vision, medical imaging, NLP/LLM, tabular, time-series, audio and speech, recommendation, generative, reinforcement learning, graph, multimodal, video, 3D, and anomaly detection), train and fine-tune…

mxslr/mlcraft

Agent

Read-only research agent that finds, reads, and critically appraises academic papers and benchmarks for an ML/AI task. Returns a structured literature brief - SOTA methods, the realistic accuracy/AUC ceiling, dataset pitfalls, and which reported numbers are likely inflated by data leakage or ROI-cropping. Use during…

mxslr/mlcraft

Command

Start a professional AI/ML research-engineer workflow for a task (any domain - CV, medical imaging, NLP/LLM, tabular, time-series). Researches papers first, picks the best method, trains/evaluates rigorously and honestly.

mxslr/mlcraft

Skill Claude CodeCodex

Use when an existing model's results are disappointing and the user wants higher accuracy - 'accuracy is still too low', 'improve/boost the model', 'why is it bad', 'make it better than the paper', 'combine methods to beat SOTA'. Diagnoses the real bottleneck first (error analysis, learning curves, leakage, saliency)…

mxslr/mlcraft

Skill Claude CodeCodex

Use BEFORE training any model, to build correct train/val/test splits and hunt data leakage - the #1 cause of fake-high accuracy. Covers group/patient/subject splits, temporal splits, official-benchmark splits, label correctness, class balance, and preprocessing parity. Triggers on 'split the data', 'train/test…

mxslr/mlcraft

Skill Claude CodeCodex

Use as the FIRST step of any ML task, before choosing a model, to inspect and understand the actual dataset. Works for a LOCAL dataset (Claude reads the files directly) and for a KAGGLE dataset (Claude cannot read /kaggle/input from your machine, so it emits a small profiling cell you run on Kaggle and paste back, or…

mxslr/mlcraft

Skill Claude CodeCodex

Use when turning a trained model into something usable (an app, an inference function, a demo) or adding explainability. Selects the RIGHT interpretability method per problem: Grad-CAM for CNN image classification, predicted boxes for detection, mask overlays for segmentation, embedding neighbors for face recognition…

mxslr/mlcraft

Skill Claude CodeCodex

Use for 3D and point cloud tasks: point cloud classification, 3D semantic or instance segmentation, 3D object detection from LiDAR, and depth or mesh analysis, including autonomous-driving and indoor-scan settings. Picks the right 3D backbone, representation, and scene-level split and metric. Triggers on 'point…

mxslr/mlcraft

Skill Claude CodeCodex

Use for anomaly, outlier, and novelty detection across data types: industrial or visual defect detection, time-series or sensor anomalies and predictive maintenance, tabular fraud or intrusion detection, and out-of-distribution detection. Usually one-class or unsupervised. Picks the method by data type, sets the…

mxslr/mlcraft

Skill Claude CodeCodex

Use for audio and speech tasks: speech recognition (speech to text, ASR, transcription), audio or sound classification and tagging, keyword spotting, speaker identification or verification, sound event detection, and music or audio analysis. Picks the best model per sub-task and the right features, splits, and…

mxslr/mlcraft

Skill Claude CodeCodex

Use for computer-vision tasks on natural/general images: image classification, object detection (vehicles, faces, people, products), face recognition/verification, semantic/instance segmentation, keypoints/pose, OCR. Picks the best architecture per sub-task and the right transfer-learning + augmentation recipe.…

mxslr/mlcraft

Skill Claude CodeCodex

Use for generative modeling of images and audio: text-to-image, image editing or image-to-image, unconditional image generation, inpainting, super-resolution, style transfer, and audio or music generation, including fine-tuning or personalizing a base model. Picks diffusion vs GAN, the right adaptation method, and…

mxslr/mlcraft

Skill Claude CodeCodex

Use for graph machine learning: node classification, link prediction, graph classification or regression, recommendation on graphs, molecule or network analysis, community detection, and graph anomaly detection with graph neural networks. Picks the GNN by task, enforces transductive vs inductive splits (a common…

mxslr/mlcraft

Skill Claude CodeCodex

Use for medical-image AI: tumor/cancer detection & classification, brain tumor MRI, mammography (benign vs malignant), chest X-ray, CT, histopathology, retinal/fundus, ultrasound, dermoscopy. Encodes hard-won rigor: patient-level splits (no leakage), medical preprocessing (CLAHE, ROI/organ cropping, artifact/pectoral…

mxslr/mlcraft

Skill Claude CodeCodex

Use for vision-language and multimodal tasks: image-text retrieval, zero-shot image classification, visual question answering (VQA), image captioning, document or chart understanding, and visual grounding. Picks a contrastive dual-encoder or an instruction-tuned VLM, and uses task-appropriate evaluation. Triggers on…

mxslr/mlcraft

Skill Claude CodeCodex

Use for text / NLP / LLM tasks: text classification, sentiment, NER/token tagging, QA, summarization, translation, semantic search / embeddings, retrieval-augmented generation (RAG), chatbots/agents, and fine-tuning language models. Picks prompt vs fine-tune vs RAG, the right model, and rigorous text evaluation.…

mxslr/mlcraft

Skill Claude CodeCodex

Use for recommendation and ranking systems: product or content recommendation, collaborative filtering, candidate retrieval, learning to rank, next-item or sequential recommendation, and cold start. Picks retrieve-then-rank architecture, the right model, honest temporal splits, and ranking metrics. Triggers on…

mxslr/mlcraft

Skill Claude CodeCodex

Use for reinforcement learning and sequential decision making: game or control agents, robotics, continuous or discrete control, offline RL from logged data, and contextual bandits. Picks the algorithm by setting, defines reward and state carefully, and evaluates with proper multi-seed protocol. For aligning an LLM…

mxslr/mlcraft

Skill Claude CodeCodex

Use for structured/tabular data prediction: churn, fraud, credit/risk scoring, price/demand regression, conversion, recommendation features, any CSV/database ML. Picks gradient boosting vs deep tabular, robust feature engineering, correct CV, calibration, and imbalance handling. Triggers on 'predict…

mxslr/mlcraft

Skill Claude CodeCodex

Use for time-series tasks: forecasting (demand, sales, energy, finance), time-series classification, and anomaly detection over time (sensors, logs, monitoring). Picks classical vs ML vs deep forecasters, enforces temporal splits (no future leakage), and uses proper time-series metrics/backtesting. Triggers on…

mxslr/mlcraft

Skill Claude CodeCodex

Use for video understanding: action or activity recognition, video classification, temporal action detection or localization in untrimmed video, gesture recognition, and general video analysis. Picks the right video model and the correct video-level split and metric. Triggers on 'video classification', 'action…

mxslr/mlcraft

Skill Claude CodeCodex

Use when starting an ML task or choosing a method, to research papers/benchmarks and find the best approach and the REALISTIC accuracy ceiling. Finds SOTA, critically appraises reported numbers, and flags claims inflated by data leakage or ROI-cropping. Triggers on 'what's the best model/method for', 'state of the…

mxslr/mlcraft

Skill Claude CodeCodex

Use at the START of ANY machine-learning / deep-learning / AI modeling task - building, training, fine-tuning, or choosing a model for image classification, object/face/vehicle detection, segmentation, medical imaging (tumor/cancer/MRI/X-ray/mammogram), text/NLP/LLM, tabular prediction (churn, price, risk), or…