OpenLAIR

OpenLAIR/dr-claw

Skill Claude Code

A tool for analyzing usage logs and suggesting changes to the instructions, review prompts, and default workflows used by ARIS.

OpenLAIR/dr-claw

Skill Claude Code

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

OpenLAIR/dr-claw

Skill Claude Code

A tool for checking whether a research idea appears to be new by comparing it with recent academic literature. Academic literature means published research papers and related scholarly work.

OpenLAIR/dr-claw

Skill Claude Code

A tool for turning a LaTeX research paper into a PDF and checking whether the result builds correctly. LaTeX is a text-based system commonly used to write academic papers.

OpenLAIR/dr-claw

Skill Claude Code

A tool for creating figures and tables from research experiment results.

OpenLAIR/dr-claw

Skill Claude Code

A tool for creating illustrations for academic papers, such as system architecture diagrams and visual explanations of a research method. It uses AI image generation and repeated review to refine the images.

OpenLAIR/dr-claw

Skill Claude Code

A tool for making a structured research-paper outline from review conclusions and experiment results.

OpenLAIR/dr-claw

Skill Claude Code

A tool for turning a compiled research paper into a conference poster, including a PDF, an editable PowerPoint file, and an SVG file. A conference poster is a large visual summary displayed during a poster session.

OpenLAIR/dr-claw

Skill Claude Code

A tool for turning a compiled research paper into conference presentation slides, with both a PDF and an editable PowerPoint file. It also prepares speaker notes and a complete talk script.

OpenLAIR/dr-claw

Skill Claude Code

A LaTeX drafting tool that writes a research paper section by section from an outline. LaTeX is a text-based system commonly used to format academic papers.

OpenLAIR/dr-claw

Skill Claude Code

A full paper-writing workflow that turns a research report into a polished PDF for submission. It coordinates planning, figures, writing, compilation, and improvement.

OpenLAIR/dr-claw

Skill Claude Code

A tool for generating pixel-art illustrations as SVG files. SVG is an image format that can be resized without becoming blurry.

OpenLAIR/dr-claw

Skill Claude Code

A mathematical proof-writing tool for machine-learning and artificial-intelligence theory. It can work with theorems, lemmas, propositions, and corollaries, which are formal statements that need proof.

OpenLAIR/dr-claw

Skill Claude Code

Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.

OpenLAIR/dr-claw

Skill Claude Code

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.

OpenLAIR/dr-claw

Skill Claude Code

A complete research workflow that covers idea discovery, implementation, review, and preparation of a paper for submission.

OpenLAIR/dr-claw

Skill Claude Code

An end-to-end research-planning workflow that combines method refinement with experiment planning. It turns a broad research direction into a focused proposal and a roadmap for testing it.

OpenLAIR/dr-claw

Skill Claude Code

A research-planning guide that turns a broad idea into a specific, practical method plan through repeated AI review.

OpenLAIR/dr-claw

Skill Claude Code

Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

OpenLAIR/dr-claw

Skill Claude Code

A persistent research knowledge base for storing papers, ideas, experiments, claims, and the links between them throughout a research project.

OpenLAIR/dr-claw

Skill Claude Code

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.

OpenLAIR/dr-claw

Skill Claude Code

A workflow for launching machine-learning experiments on local computers, remote servers, Vast.ai, or Modal cloud GPUs.

OpenLAIR/dr-claw

Skill Claude Code

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /aris-arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published…

OpenLAIR/dr-claw

Skill Claude Code

Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.