What is ai4science-perf-analysis?

A workflow for diagnosing slow multi-node machine-learning runs with TraceLens and Omnistat, then checking the findings with separate analyst and verifier agents. Multi-node means the job runs across several connected computers.

Use it to analyze HydraGNN or ORBIT-2 runs and, when appropriate, try performance changes iteratively by keeping improvements and reverting changes that do not help.

It organizes performance diagnosis into evidence gathering, independent checking, and reconciliation, helping identify whether time is lost in computation, memory, communication, or data handling.

How AMDResearch/ai4science-studio configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to AMDResearch/ai4science-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AMDResearch/ai4science-studio/main/.cursor/skills/ai4science-perf-analysis/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-perf-analysis/github.svg)](https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-perf-analysis)

Your own site

<a href="https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-perf-analysis"><img src="https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-perf-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-perf-analysis"><img src="https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-perf-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,894 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00127	$0.10894
Opus 5	$0.00063	$0.05447
Sonnet 5	$0.00025	$0.02179
Haiku 4.5	$0.00013	$0.01089

Measured 9d ago against content hash 177ce84d8841, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai4science-perf-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/ai4science-perf-analysis/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI4Science perf-analysis (multi-subagent bottleneck workflow)

When this skill applies

The user wants an automated bottleneck analysis of a multi-node training/inference run using AMD's open-source observability tooling (TraceLens, Omnistat). This is distinct from the ai4science-run-models skill — that one launches a model; this one diagnoses a model after it runs.

Default target: HydraGNN on AMD MI355X. ORBIT-2 training uses the same perf-analysis pattern; see earth_science/models/ORBIT-2/recipes/perf-analysis/. ORBIT-2 iterative sysopt (throughput-primary FOM) lives in earth_science/models/ORBIT-2/recipes/perf-optimizer-loop/ (run_optimizer_loop.sh, lever_catalog.yaml).

Repository entry points

HydraGNN

Recipe: material_science/models/HydraGNN/recipes/perf-analysis/
Iterative-loop recipe: material_science/models/HydraGNN/recipes/perf-optimizer-loop/ — see dispatch-attribution.md (current-best attribution) and lever_catalog.yaml (levers tried / blocked with evidence)
Sbatch wrapper: material_science/models/HydraGNN/examples/sbatch_train_perf_amd.sh
Reusable node-health probe: material_science/models/HydraGNN/examples/microbench_node_health.sh
Agent prompt files: material_science/models/HydraGNN/recipes/perf-analysis/agents/*.md and material_science/models/HydraGNN/recipes/perf-optimizer-loop/agents/*.md

ORBIT-2

Recipe: earth_science/models/ORBIT-2/recipes/perf-analysis/ — see README.md (FOM contract, defaults, landmines) and gemm-attribution.md (GEMM-time finding + levers)
Iterative sysopt loop: earth_science/models/ORBIT-2/recipes/perf-optimizer-loop/ — primary accept/revert FOM throughput_samples_per_s (run_fom_extractor.py + manifest.global_batch_size)
Sbatch: earth_science/models/ORBIT-2/examples/sbatch_train_perf_amd.sh
Plain training: earth_science/models/ORBIT-2/examples/sbatch_train_amd.sh
Scaling: run_scaling_study.sh + collate_scaling_study.py
FOM parser: parse_training_log.py — latency steady_batch_time_s; throughput when global_batch_size is known; loss_sanity_pass requires strictly decreasing epoch losses
FOM extractor: run_fom_extractor.py — writes foms.json; optional PromQL via ORBIT2_TSDB_URL; omnistat template defaults to bf16 MFMA profile hbm_flops_bf16 (FETCH_SIZE + SQ_INSTS_VALU_MFMA_MOPS_BF16); set OMNISTAT_ROCPROF_PROFILE=hbm_flops_f64 to revert to fp64 HydraGNN-style counters
Artifacts: $AI4S_SHARED_DIR/models/ORBIT-2/perf-runs/<jobid>/
Workload: intermediate_downscaling.py via run_orbit2_train.py, or Bayes-CAST train_edm.py / launch_diffusion.sh when present (see sbatch_train_amd.sh / sbatch_train_perf_amd.sh). Studio orbit2_rank_hook_runner.py applies ORBIT2_RANK_PRE_TRAIN_HOOK before the launcher (set hook path before sbatch so the wrapper bakes it into the rank script).
Data: 10.0_arcmin PRISM same-dir (interm_8m_prism.yaml) or ERA5 1.0° same-dir (interm_8m_era5.yaml, ORBIT2_CONFIG_TEMPLATE) — timing only until true downscaling targets are staged; for HBM saturation see STAGING_ERA5_FOR_HBM.md
Profiler: orbit2_profiler_hook.py via ORBIT2_RANK_PRE_TRAIN_HOOK (res_slimvit path; Bayes EDM defaults to no hook unless overridden)

Read the full file on GitHub · 155 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 155 lines · 127 tokens per session scan A 177ce84d8841

Subscribe to this mod's changes

ai4science-perf-analysis is a skill published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 10,894 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Scientific ai-for-science amd drug-discovery earth-science fine-tuning healthcare

batch-processing-clinical-text

Run large-scale batch NER, PII extraction, or de-identification over many clinical notes on-device with OpenMed, with sharding, checkpointing, resumability, and append-only JSONL output. Use when the user needs to process a corpus or folder of notes, de-identify a dataset, run NER over thousands of documents, build a…

maziyarpanahi/openmed · 161 tokens

exporting-to-fhir

Convert OpenMed NER output (entities from openmed.analyzetext) into FHIR R4 resources — Condition, MedicationStatement, Observation — using OpenMed's built-in FHIR R4 export helpers in openmed.clinical.exporters. Covers the verified CodeableConcept builder (coding, codeableconcept, systemuri), deterministic fullUrl…

maziyarpanahi/openmed · 163 tokens

loading-openmed-models

Load OpenMed clinical/biomedical NER models from the Hugging Face Hub or a local path and reuse them efficiently across calls. Use when the user wants to load an OpenMed model, control the model cache, run fully offline after a one-time download, reuse a ModelLoader to avoid reloading, set a cachedir or device, or…

maziyarpanahi/openmed · 118 tokens

choosing-openmed-models

Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language. Use when the user asks which OpenMed model to use, wants to list model categories, find a Disease vs Oncology vs Privacy/PII model, get a PII model for a specific language, search models by size or task, or inspect a…

maziyarpanahi/openmed · 134 tokens

extracting-clinical-entities

Run clinical and biomedical named-entity recognition on medical text with OpenMed's analyzetext. Use when the user wants to extract diseases, drugs, anatomy, genes, or other biomedical entities from notes; needs NER output as dict/json/html/csv; wants to filter by confidence, group entities, toggle sentence detection…