Resources

Set up your AI agent tooling before the hackathon. The track lead’s harness assumes you can fork a repo, run a make target, and converse with an agent in your terminal — we don’t run an introductory installfest on Day 1.

// AI Coding Tools Guide

Get one installed and authenticated before July 26. Verify by running the tool in your terminal and asking it to read a file.

// Learning Resources

• Documentation: The Complete Guide to Building Skills for Claude
• Video: Agentic Coding (MIT Open Course)

// MCP Servers & CLI Tools

A curated subset relevant to many-body physics simulation. Star counts shown for reference. For an exhaustive list across research domains, see the HKUST-Got-Skills resources page.

Literature & Papers

• arxiv-mcp-server — MCP: search and analyze arXiv papers (2.4k stars)
• paper-search-mcp — MCP: multi-source search (arXiv, Semantic Scholar, Crossref, OpenAlex) (900+ stars)
• arxiv-latex-mcp — MCP: fetch arXiv LaTeX source for precise math reading (110+ stars)
• doi2bib — CLI: convert DOI/arXiv ID to BibTeX (66+ stars)
• arxiv-dl — CLI: download papers by URL or arXiv ID (55+ stars)

Reference Management

• zotero-mcp — MCP: search, summarize, export BibTeX from Zotero (2.1k stars)
• zotero-cli — CLI: Zotero web API from the terminal (310+ stars)

Jupyter & Notebooks

• jupyter-mcp-server — MCP: full notebook control (960+ stars)
• nbconvert — CLI: convert notebooks to PDF, HTML, LaTeX
• nbstripout — CLI: strip output for clean git diffs

Scientific Computing

• mcp.science — MCP: Materials Project, GPAW DFT, sandboxed Python (120+ stars)
• mcp-wolframalpha — MCP: Wolfram Alpha (75+ stars)
• Wolfram MCP Service — MCP: official Wolfram cloud service

Plotting & Visualization

• mcp-server-chart — MCP: 25+ chart types via AntV (3.9k stars)
• gnuplot — CLI: scientific plotting from the terminal
• ffmpeg — CLI: encode media, build animations from frame sequences
• imagemagick — CLI: convert, resize, annotate images

SSH, Remote & HPC

Useful if your track’s challenge needs a cluster.

Student HPC accounts for the hackathon week are TBD. The target is to confirm login-node access, scratch space, and queue access before harness release in mid-July; CTMRG and QMC may assume real compute once the cluster details are confirmed.

• ssh-mcp — MCP: SSH exec/sudo (350+ stars)
• sbatch / squeue / scancel — CLI: SLURM job scheduler
• rsync / scp — CLI: efficient file transfer
• tmux — CLI: persistent terminal sessions (survives SSH disconnect)
• GNU parallel — CLI: parallel command execution across cores/nodes
• rclone — CLI: sync to/from S3, Drive, Dropbox, 70+ providers

Git, GitHub & Data Versioning

• github-mcp-server — MCP: official GitHub: code search, PRs, issues, CI (28k stars)
• gh — CLI: GitHub CLI — issues, PRs, actions, releases
• git-lfs — CLI: version large files in Git
• dvc — CLI: Data Version Control for datasets and pipelines

Build & Dev Utilities

• uv — CLI: fast Python package/project manager (82k stars)
• ripgrep (rg) — CLI: fast recursive search (62k stars)
• fd — CLI: fast find alternative (42k stars)
• hyperfine — CLI: statistical command-line benchmarking (28k stars)
• ruff — CLI: fast Python linter + formatter (47k stars)
• make / cmake / ninja — CLI: build automation
• duckdb — CLI: analytical SQL on CSV/Parquet/JSON (37k stars)
• jq — CLI: JSON slice/filter/transform (34k stars)

// Skills for Researchers

Skills are reusable instruction files (SKILL.md) that teach AI agents domain-specific workflows. Drop a skill into .claude/skills/ to use it from Claude Code.

Install a Skill

# Option 1: clone into your project's .claude/skills/
git clone https://github.com/anthropics/skills.git /tmp/skills
cp -r /tmp/skills/skills/pdf .claude/skills/pdf

# Option 2: skills CLI (12k stars)
npx skills install anthropics/skills/pdf

# Option 3: skillkit (680+ stars)
npx skillkit@latest init

Recommended Collections

Especially Relevant for Many-Body Simulation

• test-driven-development (superpowers) — every numerical claim should be a passing test before you trust it.
• systematic-debugging (superpowers) — root-cause for the inevitable convergence/sign-problem/integration bugs.
• pdf (anthropics) — read the canonical paper and your reproduction target.
• qiskit / cirq / pennylane / qutip (K-Dense-AI) — quantum computing tooling.
• matplotlib / scientific-visualization (K-Dense-AI) — produce publication-grade plots.

Skill Tutorials

• Claude Code Skills Docs — official documentation
• Anthropic Guide to Building Skills (PDF)
• Claude Skills Deep Dive

// Background Reading

Method-specific reading lives in each track’s harness folder under tracks/<track>/.knowledge/. Track-specific reading lists: TBD (lands as track leads ship their harnesses).