yxbian23/ai-research-claude-code

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Use this skill when processing large-scale ML datasets. Covers data loading, preprocessing, augmentation, multimodal data handling, and streaming/sharding techniques.

Use this skill when working with diffusion models for image/video generation. Covers Diffusers library pipelines, custom samplers, ControlNet, model training, and optimization techniques.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Use this skill when setting up ML experiment infrastructure. Covers wandb/tensorboard integration, hydra/omegaconf configuration management, experiment reproducibility, and results visualization.

Use this skill when optimizing GPU training efficiency. Covers memory optimization, mixed precision, gradient accumulation, model parallelism (TP/PP/DP), DeepSpeed, and FSDP integration.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI 顶会论文审稿知识库。包含 ICLR/ICML/NeurIPS/CVPR/ECCV/ICCV 的审稿标准、评分体系、常见表达和伦理准则。用于辅助审稿人撰写专业、建设性的审稿意见。

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Use this skill when implementing deep learning models with PyTorch. Covers model architecture design, custom layers, mixed precision training, distributed training (DDP/FSDP), gradient checkpointing, and checkpointing.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

Use this skill when working with Hugging Face Transformers library. Covers model loading, fine-tuning, LoRA/QLoRA adaptation, tokenizer usage, datasets processing, and Trainer API.

Use this skill when implementing unified understanding and generation models. Covers multi-task architectures, autoregressive vs diffusion approaches, multimodal tokenization, and next-token prediction paradigms.

Use this skill when working with Vision-Language Models. Covers visual encoder selection (CLIP/SigLIP/EVA), vision-language alignment, instruction tuning, multi-image conversation, and VLM evaluation.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas