agent-skills-for-compute
CLAUDE.md8 starsChanged 8 months agoMITView on GitHub
This repository contains agent-optimized skills for NVIDIA GPU-accelerated computing frameworks. Skills provide structured, actionable instructions for AI coding assistants working with quantum computing, physics-informed ML, and computational biology. Follow the agentskills.io spec. Each skill needs: Run /validate-skills to check compliance.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- validate-skillsSkill
- alchemi-toolkit-opsSkill
- autoresearch-setupSkill
- bionemoSkill
- biosimspaceSkill
- cuda-quantumSkill
- cutileSkill
- daskSkill
- flashinferSkill
- materials-projectSkill
- mpiSkill
- nemotronSkill
- omniverse-simreadySkill
- physicsnemoSkill
- polarsSkill
- prime-verifiersSkill
- qiskitSkill
- raySkill
- rdkitSkill
- slurmSkill
- tinkerSkill
- tritonSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Follow the agentskills.io spec.
- Very specific: line 29
Run /validate-skills to check compliance.
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Skills for Compute
This repository contains agent-optimized skills for NVIDIA GPU-accelerated computing frameworks. Skills provide structured, actionable instructions for AI coding assistants working with quantum computing, physics-informed ML, and computational biology.
Skills
| Skill | Description |
| cuda-quantum | Hybrid quantum-classical programming with CUDA-Q |
| qiskit | IBM Quantum platform with runtime primitives and hardware design |
| physicsnemo | Physics-informed machine learning with PhysicsNeMo |
| bionemo | Computational biology and drug discovery with BioNeMo |
| alchemi-toolkit-ops | GPU cluster operations, Slurm, Docker, Kubernetes |
| autoresearch-setup | Scaffold autonomous experiment loops (Karpathy's autoresearch philosophy) |
| prime-verifiers | Prime Intellect verifiers & PrimeRL for LLM post-training |
| tinker | Thinking Machines Lab training API for LLM fine-tuning |
| biosimspace | Engine-agnostic biomolecular simulation (AMBER, GROMACS, OpenMM) |
| cutile | NVIDIA CuTile Python tile-based GPU kernel DSL (Blackwell) |
Adding Skills
Follow the agentskills.io spec. Each skill needs:
- A directory under
skills/<skill-name>/ - A
SKILL.mdwith required frontmatter (name, description) - Reference files in
references/for deep-dive content - Under 500 lines per SKILL.md
Run /validate-skills to check compliance.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

