Find the best CLAUDE.md, AGENTS.md and Claude skills

Clay-HHKSkill

peft-fine-tuning

Clay-HHK/claude-skills/peft/SKILL.md

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Clay-HHKSkill

phoenix-observability

Clay-HHK/claude-skills/phoenix/SKILL.md

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

Clay-HHKSkill

pinecone

Clay-HHK/claude-skills/pinecone/SKILL.md

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

Clay-HHKSkill

planning-with-files

Clay-HHK/claude-skills/planning-with-files/SKILL.md

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

Often used withreact-best-practices·web-artifacts-builder·webapp-testing

Clay-HHKSkill

post-acceptance

Clay-HHK/claude-skills/post-acceptance/SKILL.md

This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter thread", or mentions post-acceptance conference preparation. Provides comprehensive workflow for presentation, poster, and promotion content creation.

Clay-HHKSkill

pptx

Clay-HHK/claude-skills/pptx/SKILL.md

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Often used withfile-reading·context7-efficient·import-memory

Clay-HHKSkill

pytorch-fsdp2

Clay-HHK/claude-skills/pytorch-fsdp2/SKILL.md

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

Clay-HHKSkill

pytorch-lightning

Clay-HHK/claude-skills/pytorch-lightning/SKILL.md

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 when you want clean training loops with built-in best practices.

Clay-HHKSkill

pyvene-interventions

Clay-HHK/claude-skills/pyvene/SKILL.md

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Clay-HHKSkill

qdrant-vector-search

Clay-HHK/claude-skills/qdrant/SKILL.md

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Clay-HHKSkill

ray-data

Clay-HHK/claude-skills/ray-data/SKILL.md

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

Clay-HHKSkill

ray-train

Clay-HHK/claude-skills/ray-train/SKILL.md

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

Clay-HHKSkill

Research Ideation

Clay-HHK/claude-skills/research-ideation/SKILL.md

This skill should be used when the user asks to "brainstorm research ideas", "use 5W1H framework", "identify research gaps", "conduct gap analysis", "start research project", "conduct literature review", "define research question", "select research method", "plan research", or mentions research project initiation phase. Provides comprehensive guidance for research startup workflow from idea generation to planning.

Clay-HHKSkill

results-analysis

Clay-HHK/claude-skills/results-analysis/SKILL.md

This skill should be used when the user asks to "analyze experimental results", "generate results section", "statistical analysis of experiments", "compare model performance", "create results visualization", or mentions connecting experimental data to paper writing. Provides comprehensive guidance for analyzing ML/AI experimental results and generating paper-ready content.

Clay-HHKSkill

review-response

Clay-HHK/claude-skills/review-response/SKILL.md

Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.

Clay-HHKSkill

rwkv-architecture

Clay-HHK/claude-skills/rwkv/SKILL.md

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, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Clay-HHKSkill

sparse-autoencoder-training

Clay-HHK/claude-skills/saelens/SKILL.md

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Clay-HHKSkill

segment-anything-model

Clay-HHK/claude-skills/segment-anything/SKILL.md

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

Often used withpopular-web-designs·himalaya·blogwatcher

Clay-HHKSkill

sentencepiece

Clay-HHK/claude-skills/sentencepiece/SKILL.md

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, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

Clay-HHKSkill

sentence-transformers

Clay-HHK/claude-skills/sentence-transformers/SKILL.md

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.