majiayu000/claude-skill-registry - Página 31

chain-of-thought

複雑な問題を分解し、推論の流れを整理して短い根拠サマリーを作成するスキル。 前提整理、論点分解、選択肢比較、判断理由の要約を通じて、説明責任のあるアウトプットを作る。 Anchors: • The Pragmatic Programmer / 適用: 問題分解 / 目的: 実践的な整理 • Thinking, Fast and Slow / 適用: 判断バイアス確認 / 目的: 判断根拠の明確化 • Critical Thinking / 適用: 論点整理 / 目的: 根拠の一貫性 Trigger: Use…

Idioma del texto original: japonés

chaotic-attractor

Strange attractor with sensitive dependence on initial conditions

Idioma del texto original: inglés

cirq

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.

Idioma del texto original: inglés

claude-light

Expert assistant for conducting remote experiments with Claude-Light - a web-accessible RGB LED and spectral sensor instrument for statistics, regression, optimization, and design of experiments

Idioma del texto original: inglés

clip-aware-embeddings

Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries.…

Idioma del texto original: inglés

cloud-neural

Neural network training and deployment in Flow Nexus cloud. Use for distributed ML training, model inference, and neural network lifecycle management.

Idioma del texto original: inglés

bio-single-cell-clustering

Dimensionality reduction and clustering for single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for running PCA, computing neighbors, clustering with Leiden/Louvain algorithms, generating UMAP/tSNE embeddings, and visualizing clusters.

Idioma del texto original: inglés

coequalizers

Quotient redundant skill paths via coequalizers, preserving GF(3) conservation

Idioma del texto original: inglés

comfyui

ComfyUI node-based Stable Diffusion interface. GPU-accelerated image generation with custom node support and CivitAI model downloads. Use 'ujust comfyui' for configuration, lifecycle management, and model/node operations.

Idioma del texto original: inglés

computer-vision-expert

SOTA Computer Vision Expert. Specialized in YOLO, Segment Anything, Vision Language Models, and real-time spatial analysis. Use when building or optimizing computer vision systems.

Idioma del texto original: inglés

computer-vision

Build computer vision systems using CNNs and modern architectures. Use for image classification, object detection (YOLO, Faster R-CNN), image segmentation, face recognition, and visual analysis tasks.

Idioma del texto original: inglés

computer-vision-pipeline

Build production computer vision pipelines for object detection, tracking, and video analysis. Handles drone footage, wildlife monitoring, and real-time detection. Supports YOLO, Detectron2, TensorFlow, PyTorch. Use for archaeological surveys, conservation,…

Idioma del texto original: inglés

confidence-scoring

See the main Model Explainability skill for comprehensive coverage of confidence scoring and calibration.

Idioma del texto original: inglés

confusion-matrix-generator

Inspect classifier errors with confusion matrices after predictions already exist. Use for per-class error analysis, threshold tradeoffs, and label-confusion diagnosis; not for regression metrics or full model training ownership.

Idioma del texto original: inglés

coupled-system

Interacting dynamical systems

Idioma del texto original: inglés

covariant-fibrations

Riehl-Shulman covariant fibrations for dependent types over directed

Idioma del texto original: inglés

create-3d-model-from-image

Use AgentPMT external API to run the Create 3D Model From Image tool with wallet signatures, credits purchase, or credits earned from jobs.

Idioma del texto original: inglés

create-classifier

Train task-specific classifiers for the extractor pipeline. Supports vision, text, and hybrid classifiers with GRPO training and execution feedback. Includes data collection, confidence-based routing, and shadow deployment.

Idioma del texto original: inglés

crispr-designer

Designs guide RNA (gRNA) sequences for CRISPR-Cas9 editing, including off-target analysis. Use when a user needs to edit a gene or asks for gRNA sequences.

Idioma del texto original: inglés

cv-pipeline-builder

Computer vision ML pipelines for image classification, object detection, semantic segmentation, and image generation. Activates for "computer vision", "image classification", "object detection", "CNN", "ResNet", "YOLO", "image segmentation", "image…

Idioma del texto original: inglés

cybernetic-immune

Cybernetic immune system with Varela+Friston+Powers for Self/Non-Self discrimination via reafference, GF(3) trit encoding, and information geometry

Idioma del texto original: inglés

data-ai-mastery

Master Python programming, Data Science, AI/LLM engineering, and Database administration. Use this as a central index to access specialized sub-skills.

Idioma del texto original: inglés

data-scientist

Advanced analytics and machine learning for data-driven insights. Use when performing statistical analysis, building predictive models, designing experiments, or creating data visualizations.

Idioma del texto original: inglés

db-musik-app-bei

Datenbankrecht für Musik-, Film- und Bildarchive: §§ 87a-87e UrhG für Mediendatenbanken, Schichtenschutz (Datenbankherstellerrecht + Urheberrecht an Einzelwerken), Lizenzmodelle für Stock-Media-Portale und Verwertungsgesellschaften (GEMA, VGBild),…

Idioma del texto original: alemán

debug-distributed

Guide for debugging distributed training issues in AReaL. Use when user encounters hangs, wrong results, OOM, or communication errors.

Idioma del texto original: inglés

deep-learning

Build and train deep neural networks including CNNs, RNNs, Transformers, and advanced architectures. Use for image classification, object detection, NLP, sequence modeling, transfer learning, and complex pattern recognition tasks.

Idioma del texto original: inglés

bio-variant-calling-deepvariant

Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Illumina, PacBio, and ONT data.

Idioma del texto original: inglés

design-of-experiments

Expert guidance for Design of Experiments (DOE) in Python - interactive goal-driven design selection, classical DOE (factorial, response surface, screening), Bayesian optimization with Gaussian processes, model-driven optimal designs, active learning, and…

Idioma del texto original: inglés

diffusion-model-patterns

Diffusion model training and inference patterns including UNet/DiT architectures, noise schedules, CFG, ControlNet, and LoRA. Use when building or fine-tuning image generation models.

Idioma del texto original: inglés

digital-twin-patient-builder

Build digital twin patient models to test drug efficacy and toxicity in virtual environments

Idioma del texto original: inglés

discopy-operads

DiscoPy Operads Skill

Idioma del texto original: inglés

discover-ml

Automatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG, embeddings, fine-tuning, LLM, DSPy, HuggingFace, or diffusion models. Activates for ML development tasks.

Idioma del texto original: inglés

discrete-backprop

Gradient-free optimization via discrete perturbations and trit-based learning

Idioma del texto original: inglés

bio-phylo-distance-calculations

Compute evolutionary distances and build phylogenetic trees using Biopython Bio.Phylo.TreeConstruction. Use for creating distance matrices from alignments, building NJ/UPGMA trees, parsimony analysis, and generating bootstrap consensus trees.

Idioma del texto original: inglés

domain-ml

Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理

Idioma del texto original: Sin determinar

downloading-hf-models

Get the correct command syntax for downloading models from HuggingFace. Use when downloading models, running "hf download", or pulling models from HuggingFace repos.

Idioma del texto original: inglés

dpo

Direct Preference Optimization for learning from preference pairs. Covers DPOTrainer, preference dataset preparation, implicit reward modeling, and beta tuning for stable preference learning without explicit reward models. Includes thinking quality patterns.

Idioma del texto original: inglés

drift-detection

This is an **alias skill** so docs can reference `77-mlops-data-engineering/drift-detection`. In this repo, drift guidance is covered by: - `77-mlops-data-engineering/drift-detection-retraining` (trig

Idioma del texto original: inglés

drone-cv-expert

Expert in drone systems, computer vision, and autonomous navigation. Specializes in flight control, SLAM, object detection, sensor fusion, and path planning. Activate on "drone", "UAV", "SLAM", "visual odometry", "PID control", "MAVLink", "Pixhawk", "path…

Idioma del texto original: inglés

dynamic-sufficiency-goblin

Self-regulating Goblins actor implementing Ivan Illich's dynamic sufficiency

Idioma del texto original: inglés