Skill Claude CodeCodex
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance…
Skill Claude CodeCodex
Outlines: structured JSON/regex/Pydantic LLM generation.
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.
Skill Claude CodeCodex
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
Skill Claude CodeCodex
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best…
Skill Claude CodeCodex
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
Skill Claude CodeCodex
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or…
Skill Claude CodeCodex
OBLITERATUS: abliterate LLM refusals (diff-in-means).
Skill Claude CodeCodex
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.
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.
Skill Claude CodeCodex
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2.
Skill Claude CodeCodex
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.
johnson7788/meta-analysis-assistant
Plugin Claude Code
A coordinated writing assistant made up of six specialist agents for the full meta-analysis process. It supports medical researchers from planning a study through preparing the final paper.
johnson7788/meta-analysis-assistant
Agent
A research-data assistant for collecting comparable information from studies included in a systematic review or meta-analysis. It also supports study-quality and risk-of-bias assessments, which examine how trustworthy each study's results may be.
johnson7788/meta-analysis-assistant
Agent
A writing assistant for turning completed systematic-review or meta-analysis work into a research manuscript. It can also prepare a PRISMA 2020 checklist, a reporting checklist for systematic reviews.
johnson7788/meta-analysis-assistant
Agent
A planning assistant for starting a systematic review or meta-analysis, a statistical summary that combines results from several studies. It helps define the research question and the rules for deciding which studies belong in the project.
johnson7788/meta-analysis-assistant
Agent
A literature-search planning assistant for systematic reviews, which are structured summaries of research on a specific question. It builds database-specific search queries using subject headings and text terms for sources such as PubMed and Embase.
johnson7788/meta-analysis-assistant
Agent
A statistical-analysis assistant for meta-analyses, which combine results from multiple studies. It can work with study data to calculate effects and produce common evidence-review charts.
johnson7788/meta-analysis-assistant
Agent
A literature-screening assistant for reviewing search results against predefined inclusion and exclusion rules. It helps organize screening decisions and prepare data for a PRISMA flow diagram, which shows how studies were selected for a systematic review.
johnson7788/meta-analysis-assistant
Command
A command that starts a guided assistant for meta-analysis writing. Meta-analysis combines numerical results from multiple studies to estimate an overall effect.
johnson7788/meta-analysis-assistant
Skill Claude CodeCodex
A reference guide for meta-analysis and systematic-review methods. Meta-analysis combines results from multiple studies, while PRISMA is a reporting guideline for systematic reviews.
Skill Claude CodeCodex
A paper-search skill that uses arXiv's official public API, a free service for finding research papers, to retrieve academic publications without a token.
Skill Claude CodeCodex
A web-search skill that uses Bing to find information, limit results to selected sites, filter results, and retrieve webpage text. Bing is a search engine, and this skill includes methods for handling its anti-automation checks.
Skill Claude CodeCodex
A presentation-making tool that creates offline HTML slide decks in preset visual themes. The slides can be edited in a browser and exported as PPTX or PDF files.