dr-claw

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard. Also covers DeepSpeed and PyTorch Lightning (guides in references/).

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 tokenization or custom tokenizer training. Also covers SentencePiece (guides in references/).

This skill should be used when the user asks to "run initial analysis", "analyze single-cell data", "QC my data", "run bioinformatics pipeline", "generate analysis report", "explore my dataset", "do exploratory data analysis", "initial data analysis", or needs to perform quality control, dimensionality reduction, clustering, or marker analysis on single-cell biology data (CyTOF, scRNA-seq, flow cytometry, proteomics).

Acquires missing code repositories for the selected idea (Phase A) and conducts comprehensive code survey mapping academic concepts to implementations (Phase B). Outputs acquired_code_repos, updated_prepare_res, and model_survey for downstream use by inno-experiment-dev.

Comprehensive research assistant that synthesizes information from multiple sources with citations. Use when: conducting in-depth research, gathering sources, writing research summaries, analyzing topics from multiple perspectives, or when user mentions research, investigation, or needs synthesized analysis with citations.

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.

Creates implementation plan, writes project code with judge feedback loop, and submits final experiment run. Use after code-survey in both Idea and Plan branches.

Generate/edit images with OpenAI gpt-image-2 by default, falling back to Gemini (gemini-3.1-flash-image-preview) when OPENAI_API_KEY is unset. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image for editing, --provider to force a provider, --model to override the model.

Help professors and researchers write, revise, adapt, and polish grant proposals for US agencies (NSF, NIH, DOE, DARPA, NASA), Chinese agencies (NSFC 国自然), and other national agencies (JSPS KAKENHI 科研費, ERC, DFG, SNSF, ARC, NWO). Use this skill whenever the user mentions grants, proposals, funding applications, 基金申请, 本子, R01, R21, CAREER, 面上, 青年基金, specific aims, 立项依据, broader impacts, or wants to plan, draft, review, or resubmit any research funding proposal — even if they don't explicitly say "grant". Also use this skill when the user wants to adapt a previous proposal for a new submission. Six-phase workflow: profiling → planning → drafting → quality review → simulated peer review → submission prep.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Multi-persona idea evaluation with quality gate. Evaluates ideas across 5 InnoEval dimensions (Clarity, Novelty, Validity, Feasibility, Significance) using 3 reviewer personas and a meta-review. Sits between inno-idea-generation and inno-code-survey in the Idea branch. Use after inno-idea-generation.

Generates research ideas for a defined research problem. Reads the project's literature and context, explores directions with research ideation lenses, writes three full candidate proposals, and selects one through an explicit gate. Writes Ideation/ideas/selected_idea.txt for inno-idea-eval. Use when the user wants research ideas, hypotheses, a research direction, or a method idea for a paper or project. Runs after literature survey and before inno-idea-eval.

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), ML/CS conference review forms (NeurIPS/ICML/ICLR/ACL style), and constructive feedback. Best for actual review writing and manuscript revision. To evaluate a research idea rather than a manuscript, use inno-idea-eval.

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

Guides the user through an interactive conversation to define their research project, then generates research_brief.json and tasks.json. Use when starting a new project, when no research_brief.json exists, when the user wants to start from a specific pipeline stage, or when the user wants to redefine their research pipeline.

Prepares the research materials for a project: collects the source papers, searches GitHub for their code, picks and clones reference codebases, describes the datasets, and downloads arXiv paper sources into Ideation/references/papers. Works from the research brief, the user's paper list, or instance.json. Use before inno-idea-generation or inno-code-survey, or when the user asks to gather papers and code for a research task.

Access Overleaf projects via CLI. Use for reading/writing LaTeX files, syncing local .tex files to Overleaf, downloading projects, and managing Overleaf project structure. Triggers on Overleaf, LaTeX sync, or tex file uploads to Overleaf.

Drafting and refining academic rebuttals for top-tier AI/CS conferences (NeurIPS, ICML, ICLR, CVPR, ECCV, AAAI, ARR, KDD, UAI, AISTATS, TMLR, etc.). Use this skill whenever the user needs to respond to reviewer comments, write a rebuttal, handle reviewer feedback, clarify technical misunderstandings, present additional experimental results, or deal with borderline accept/reject decisions. Also trigger when the user mentions keywords like "rebuttal", "reviewer", "review response", "author response", "camera-ready", "rebut", "AC", "area chair", "meta-review", or discusses conference review scores. Trigger for Chinese-language requests too, e.g. "写rebuttal", "回复审稿人", "审稿意见", "rebuttal怎么写", "reviewer说我的baseline不够".

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed verification principles and common error patterns.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.