OpenLAIR/dr-claw

OpenLAIR/dr-claw

Skill Claude Code

Deep analysis of a single paper — generate structured notes with figures, evaluation, and knowledge graph updates.

OpenLAIR/dr-claw

Skill Claude Code

Search existing paper notes by title, author, keyword, or research domain.

OpenLAIR/dr-claw

Skill Claude Code

Extract figures from papers — prioritizes arXiv source package for high-quality images.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

OpenLAIR/dr-claw

Skill Claude CodeCodex

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…

OpenLAIR/dr-claw

Skill Claude CodeCodex

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance…

OpenLAIR/dr-claw

Skill Claude CodeCodex

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.

OpenLAIR/dr-claw

Skill Claude CodeCodex

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.

OpenLAIR/dr-claw

Skill Claude CodeCodex

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…

OpenLAIR/dr-claw

Skill Claude CodeCodex

Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

OpenLAIR/dr-claw

Skill Claude Code

Daily paper recommendation workflow — search arXiv and Semantic Scholar, score and recommend papers.

OpenLAIR/dr-claw

Skill Claude CodeCodex

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.