mlcraft
A research-first AI/ML research-engineer workflow for Claude Code.
23 skills8
@mxslrPlugins
1@mxslrSkills
23accuracy-improvement-l…
Use when an existing model's results are disappointing and the user wants higher accuracy - 'accuracy is still too low',…
@mxslrdata-rigor-and-leakage
Use BEFORE training any model, to build correct train/val/test splits and hunt data leakage - the #1 cause of fake-high accuracy.…
@mxslrdataset-profiling
Use as the FIRST step of any ML task, before choosing a model, to inspect and understand the actual dataset. Works for a LOCAL…
@mxslrdeployment-explainabil…
Use when turning a trained model into something usable (an app, an inference function, a demo) or adding explainability. Selects…
@mxslrdomain-3d
Use for 3D and point cloud tasks: point cloud classification, 3D semantic or instance segmentation, 3D object detection from…
@mxslrdomain-anomaly-detecti…
Use for anomaly, outlier, and novelty detection across data types: industrial or visual defect detection, time-series or sensor…
@mxslrdomain-audio-speech
Use for audio and speech tasks: speech recognition (speech to text, ASR, transcription), audio or sound classification and…
@mxslrdomain-computer-vision
Use for computer-vision tasks on natural/general images: image classification, object detection (vehicles, faces, people,…
@mxslrdomain-generative
Use for generative modeling of images and audio: text-to-image, image editing or image-to-image, unconditional image generation,…
@mxslrdomain-graph
Use for graph machine learning: node classification, link prediction, graph classification or regression, recommendation on…
@mxslrdomain-medical-imaging
Use for medical-image AI: tumor/cancer detection & classification, brain tumor MRI, mammography (benign vs malignant), chest…
@mxslrdomain-multimodal
Use for vision-language and multimodal tasks: image-text retrieval, zero-shot image classification, visual question answering…
@mxslrAgent
1paper-researcher
AgentRead-only research agent that finds, reads, and critically appraises academic papers and benchmarks for an ML/AI task. Returns a…
@mxslrCommand
1ml-project
CommandStart a professional AI/ML research-engineer workflow for a task (any domain - CV, medical imaging, NLP/LLM, tabular,…
@mxslrIs this you? Claim your profilePut a plugin at the top of Plugins, from $9