MatClaw
Autonomous materials simulations, DFT, and molecular dynamics
All Skills in This Repository (18)
Pure Emerald Level Indicatorsuse-local-whisper
Replace cloud-based voice transcription with local whisper.cpp processing on macOS Apple Silicon.
add-whatsapp
Add a WhatsApp channel to MatClaw with Baileys authentication and chat registration.
qodo-pr-resolver
Fetch, deduplicate, and resolve Qodo review comments for pull requests.
add-voice-transcription
Transcribes WhatsApp voice notes into text using OpenAI Whisper for MatClaw's agent.
add-vasp
Configure VASP access for MatClaw on local or SSH HPC systems.
get-qodo-rules
Load Qodo coding rules by severity before generating or modifying code.
setup
Automate MatClaw installation and configuration on fresh development machines.
add-telegram
Integrate Telegram messaging into MatClaw for sending and receiving chat messages.
update-matclaw
Synchronize a customized MatClaw fork with upstream repository changes.
convert-to-apple-container
Switch MatClaw container runtime from Docker to Apple Container on macOS.
x-integration
Automate X posting, liking, replying, retweeting, and quoting via IPC-driven browser automation.
add-telegram-swarm
Configure Telegram bot pools to present subagents as distinct identities.
Frequently Asked Questions
FAQPage SchemaHow to install MatClaw?▼
Run `npx skills add DingyangLyu/MatClaw --all -g -y` in your terminal to install all skills in this suite globally.
What can MatClaw do for materials research?▼
It writes and runs simulation code for DFT, molecular dynamics, Monte Carlo, and ML potentials, then returns parsed results and plots. It covers 240 built-in skills across electronic structure, catalysis, batteries, defects, and more.
Does MatClaw support VASP calculations?▼
Yes. The add-vasp skill connects your own VASP installation via SSH on an HPC cluster or a local mount, and the agent generates inputs, submits jobs, and parses results automatically.
Which chat apps work with MatClaw?▼
It supports WhatsApp, Telegram, Slack, Discord, DingTalk, Gmail, and Feishu through dedicated channel skills that handle authentication and registration.
Do I need coding experience to run simulations?▼
No. You describe the materials problem in plain language in your chat app, and the agent writes the code, runs it in an isolated container, and returns the analysis.
Related Repositories in Education & Research
View All in Education & Research→learn-claude-code
Learn to build AI agent harnesses from scratch
ai-agents-for-beginners
Learn to build, deploy, and secure AI agents step by step
33-js-concepts
Master 33 essential JavaScript concepts with tested, verified guides