agent-skills-for-compute
AGENTS.md8 starsChanged 8 months agoMITView on GitHub
Markdown-only repository of agent-optimized skills for GPU-TPU-QPU-accelerated computing. No build step required. Each skill follows a hybrid format: - Quick Pattern: Correct/incorrect code snippets - Quick Command: Shell commands for common tasks - Quick Config: Configuration snippets - Quick Reference: Summary tables - Deep Dive: Full context in reference files See agentskills.io specification and run /validate-skills.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.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
Files
Agent Skills for Compute
Markdown-only repository of agent-optimized skills for GPU-TPU-QPU-accelerated computing. No build step required.
Structure
skills/
cuda-quantum/ # CUDA-Q quantum computing (NVIDIA)
SKILL.md # Main skill file
references/ # Deep-dive reference docs
qiskit/ # Qiskit quantum computing (IBM)
SKILL.md
references/
physicsnemo/ # PhysicsNeMo physics-informed ML
SKILL.md
references/
bionemo/ # BioNeMo computational biology
SKILL.md
references/
alchemi-toolkit-ops/ # GPU infrastructure and MLOps
SKILL.md
references/Skill Format
Each skill follows a hybrid format:
- Quick Pattern: Correct/incorrect code snippets
- Quick Command: Shell commands for common tasks
- Quick Config: Configuration snippets
- Quick Reference: Summary tables
- Deep Dive: Full context in reference files
Adding New Skills
See agentskills.io specification and run /validate-skills.
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.

