Cursor rule Cursor
When discovering any issue during a session, organically update skills, rules, recipes, and scripts across all models and runtimes as a side-effect of the fix.
4 1mo ago A 619 tokens
original MIT
Cursor rule Cursor
Conventions for dockerrun.sh scripts in model examples.
4 1mo ago A 0 tokens
original MIT
Cursor rule Cursor
Guardrails for healthcare and life sciences content.
4 1mo ago A 0 tokens
original MIT
model-readme
28Cursor rule Cursor
Structure requirements for model README.md files.
4 1mo ago A 0 tokens
original MIT
Cursor rule Cursor
Conventions for preflight check scripts.
4 1mo ago A 0 tokens
original MIT
Cursor rule Cursor
Structure requirements for recipe README.md files.
4 1mo ago A 0 tokens
original MIT
run-scripts
31Cursor rule Cursor
Conventions for run.sh and run.py scripts in model examples.
4 1mo ago A 0 tokens
original MIT
Cursor rule Cursor
Conventions for SLURM sbatch scripts in model examples.
4 1mo ago A 0 tokens
original MIT
Skill Claude CodeCodexCursor
How to answer user questions about what models are available, filter by domain/task/license, and compare models in AI4Science Studio.
4 1mo ago A 32 tokens
original MIT
Skill Claude CodeCodexCursor
Applies to Earth-system ML in AI4Science Studio—climate, weather, geospatial data, and model folders under earthscience/models/. Includes validated AMD/ROCm HPC patterns for earth science models.
4 1mo ago C 50 tokens
original MIT
Skill Claude CodeCodexCursor
Applies to healthcare and life sciences ML recipes under healthcare/models/ in AI4Science Studio, with privacy and non-clinical-use guardrails.
4 1mo ago A 36 tokens
original MIT
Skill Claude CodeCodexCursor
Guides creation and editing of Hugging Face–centric recipes in AI4Science Studio—discovery, task alignment, scripting, documentation, and attribution.
4 1mo ago A 41 tokens
original MIT
Skill Claude CodeCodexCursor
Applies to material science and chemistry ML recipes under materialscience/models/ in AI4Science Studio.
4 1mo ago A 28 tokens
original MIT
Skill Claude CodeCodexCursor
Runs the AMD AI agents bottleneck-analysis workflow on a HydraGNN or ORBIT-2 training job using TraceLens + Omnistat user-mode + paired analyst/verifier subagents, or drives the iterative perf-optimizer-loop (accept/revert on throughput or epoch time). Use when the user wants to analyze a perf run, analyze a 2-node…
4 1mo ago A 127 tokens
original MIT
Skill Claude CodeCodexCursor
Applies to protein structure, folding, and protein LM recipes under proteinfolding/models/ in AI4Science Studio.
4 1mo ago A 32 tokens
original MIT
Skill Claude CodeCodexCursor
Step-by-step instructions for how Cursor should run any model in AI4Science Studio — read model.yaml, check preflight, select container runtime, launch.
4 1mo ago A 38 tokens
original MIT
Skill Claude CodeCodexCursor
Applies when working in the AI4Science Studio repository. Describes domain layout, model slug rules, where recipes live, safety expectations, and AMD/ROCm HPC patterns (Apptainer and Docker) validated in practice.
4 1mo ago C 52 tokens
original MIT
Instructions file
Instructions for AMDResearch/ai4science-studio, covering claude.md, repository purpose, agent entry points (read these first), directory layout and model slug rule.
4 1mo ago A 1,388 tokens
original MIT
launcher
43Agent
Submits a 2-node ORBIT-2 training (AMD Instinct MI355X) with PyTorch profiling and Omnistat user-mode telemetry, waits for completion, and writes manifest.json for downstream subagents.
4 1mo ago A 0 tokens
original MIT
Agent
Drive omnistat-inspect (PR #271) through the analyze-job phases on the user-mode VictoriaMetrics database, then map findings to the bottleneck taxonomy.
4 1mo ago A 0 tokens
original MIT
Agent
Independently re-derive the top 2-3 claims from omnistat/claims.json by issuing raw PromQL via curl against the same VictoriaMetrics endpoint, at the finest sampling step. Optionally probe one cheap remedy on a 1-node interactive srun.
4 1mo ago A 0 tokens
original MIT
Agent
You are the GEMM-time bottleneck orchestrator for ORBIT-2 (Bayes-CAST EDM, 8M) on MI355X / ROCm 7.2.2 / PyTorch 2.10. You run unattended via the Claude Code CLI in tmux. Goal: produce a TraceLens + Omnistat analyst/verifier bottleneck analysis of where compute time goes — with a focus on the GEMMs — at 1 node and 2…
4 1mo ago A 0 tokens
original MIT
synthesizer
47Agent
Merge tracelens/verifiedclaims.json and omnistat/verifiedclaims.json into a single ranked, deduplicated bottleneck report.
4 1mo ago A 0 tokens
original MIT
Agent
Generate a TraceLens performance report for the rank-0 PyTorch trace and produce structured claims.json mapped to the bottleneck taxonomy.
4 1mo ago A 0 tokens
original MIT