OpenLAIR/dr-claw

ARIS Infra sets up the ARIS research environment by registering MCP review servers, installing Python dependencies, and checking prerequisites. Use it first when configuring ARIS or adding review models.

Ablation Planner designs reviewer-focused ablation studies for ML papers after main results support the claim. It helps plan, prioritize, and implement component, hyperparameter, and design-choice ablations.

Academic Researcher helps review papers, synthesize literature, and draft scholarly summaries and proposals. It also formats citations and structures academic arguments.

ArXiv Paper Search finds academic papers on arXiv, shows paper details, and can download PDFs to a local library. Use it when you need to search by topic or arXiv ID and save papers for later reading.

Aris DSE Loop runs a program, analyzes the results, and iterates parameter choices until the objective is met or a timeout is reached. Use it for design space exploration, parameter sweeps, and other tuning tasks in computer architecture or EDA.

Aris Experiment Plan turns a refined research proposal into a claim-driven experiment roadmap. Use it to decide the main ablations, evaluation protocol, run order, and compute budget for a paper-ready validation.

Aris Meta Optimize analyzes ARIS usage logs and suggests changes to SKILL.md prompts, defaults, and workflow rules. Use it when optimizing the harness based on accumulated runs and manual overrides.

Auto Paper Improvement Loop reviews a compiled paper with GPT-5.4, applies writing and consistency fixes, and recompiles it for up to two rounds. Use it to iteratively polish a generated paper after drafting.

Auto Review Loop runs repeated review, fix, and re-review cycles until an external reviewer gives a passing assessment or the round limit is reached. Use it for autonomous iterative improvement of research or code.

Communications Literature Review gathers papers and related work for communications topics using a knowledge-base-first search order. Use it for wireless, networking, satellite, Wi‑Fi, cellular, transport, routing, MAC/PHY, or congestion-control literature summaries.

Compute Resource Guard checks whether local or remote GPU compute is actually available before experiments start. It stops the pipeline and reports what is missing when no usable resources are found.

Dr Claw helps inspect projects and Claude/Cursor/Codex/Gemini sessions, check TaskMaster progress, and generate OpenClaw-ready JSON reports. Use it for workspace lookup, status checks, and event-driven mobile updates.

Experiment Analysis analyzes ML experiment outputs, computes summary statistics, and builds comparison tables. Use it to compare runs, check reproducibility, and interpret results from JSON or CSV files.

Experiment Bridge implements experiment code from an experiment plan, deploys it to available GPU resources, and collects initial results. Use it when a plan is ready to execute or you need to bridge idea discovery into the auto-review loop.

Experiment Monitor checks running experiments on SSH, Vast.ai, or Modal, then collects logs, JSON outputs, and W&B metrics. Use it to see progress, confirm completion, and compare results against a baseline.

Feishu Notify sends Feishu/Lark alerts through webhook or interactive reply flows. Use it when other skills need status updates, approvals, or manual notifications, or when you want to send a message directly.

Formula Derivation structures and derives research formulas into a coherent theory line, assumption set, and derivation map. Use it when a target equation is still being chosen or when scattered notes need to be turned into a paper-ready derivation document.

Grant Proposal Builder drafts structured funding applications from research ideas and literature. Use it when turning a validated project into agency-specific proposals such as KAKENHI, NSF, NSFC, or ERC.

Idea Discovery Pipeline orchestrates literature review, idea generation, novelty checking, and research review to turn a broad direction into validated ideas. Use it when you want a full workflow for finding and testing research directions.

Mermaid Diagram Generator creates Mermaid diagrams from user requirements and saves matching .mmd and .md files in figures/. It verifies syntax and supports flowcharts, sequence, class, ER, Gantt, and many other diagram types.

Novelty Check verifies whether a proposed research method or idea has already appeared in recent literature. Use it before implementation when you need a blunt assessment of overlap and likely prior work.

Paper Compile compiles a LaTeX paper into a PDF, diagnoses build errors, and checks the final output. Use it when you need to build a submission-ready paper or fix compilation issues.

Paper Figures generates publication-quality plots and tables from experiment data for papers. Use it for training curves, method comparisons, multi-panel figures, and LaTeX comparison tables.

Paper Illustration generates publication-quality figures for academic papers, including architecture diagrams and method illustrations. Use it when you need a paper visual or when prompted to generate diagrams or AI drawings.

Research Idea Creator generates, validates, and ranks publishable research ideas from a broad topic. Use it when you need brainstormed directions, quick novelty checks, and a shortlist of ideas to test.