agentmods.dev

ai4science-studio: Skill for Cursor

.cursor/skills/ai4science-huggingface-recipes/SKILL.md

ai4science-huggingface-recipes is a skill for Cursor from AMDResearch/ai4science-studio. It costs 41 tokens per session (802 once invoked), scanned A, original, MIT.

A workflow for creating and editing recipes for machine-learning models hosted on Hugging Face, a service that publishes models and datasets.

In plain words
What is it for?
Use it for training, fine-tuning, inference, or evaluation recipes. It covers model discovery, folder placement, official scripts, version details, and AMD GPU documentation.
Why use it?
It helps match each recipe to what the model actually supports and keeps model identifiers, dependencies, scripts, hardware notes, and attribution accurate.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is AMDResearch/ai4science-studio's own configuration. It tells Cursor how to work on ai4science-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai4science-studio configures →

not rated 4repo changed 1mo ago A scan 41 tokens original MIT
View source ↗ AMDResearch/ai4science-studio
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-huggingface-recipes/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.

agentmods badge for ai4science-huggingface-recipes

README.md
[![agentmods](https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes/github.svg)](https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes)
Your own site
<a href="https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes"><img src="https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes/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.

agentmods 80×15 button for ai4science-huggingface-recipes

Your own site · 80×15
<a href="https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes"><img src="https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 802 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00802
Opus 5.5 $0.00016 $0.00321
Sonnet 5.5 $0.00008 $0.00160
Haiku 4.5 $0.00004 $0.00080

Measured 1mo ago against content hash f79990305ffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai4science-huggingface-recipes 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 1mo 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-huggingface-recipes/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hugging Face recipes workflow

Use this skill when adding or refactoring train / fine-tune / inference / eval material for models hosted on Hugging Face inside this repo.

Steps

  1. Identify the model on Hugging Face (model card, license, intended use, dependencies). Record the full id org/model in the model folder README.md.
  2. Map to a folder name under the correct domain’s models/ directory. Default: replace / with __ in the Hub id (org__model). Alternative: a public model name on disk (e.g. HydraGNN, ORBIT-2) is acceptable when that domain’s models/README.md allows it and the model README.md states the full org/model id at the top—do not rename those folders to org__model unless the user asks.
  3. Align the task with what the model card and upstream code support (inference-only vs fine-tuning vs training from scratch).
  4. Reuse upstream scripts or minimal wrappers: prefer calling official examples with pinned versions rather than reimplementing full training stacks unless necessary.
  5. Document Python/PyTorch (or other) versions, ROCm builds and versions for AMD Instinct when validated, and how to run from the repo root or from recipes/ subfolders.
  6. Attribute authors, papers, and license in the model README.md and in recipe comments where helpful.

Recipe folder tips

  • Use subfolders under recipes/ for distinct tasks, e.g. recipes/inference/, recipes/finetune/.
  • Keep entrypoints small and documented; link to Hugging Face Spaces or Colab only as supplements, not replacements for reproducible commands.

Avoid

  • Committing token values or private Hub tokens.
  • Checking in large *.bin, *.safetensors, or full datasets when .gitignore already excludes them—point users to Hub or documented download steps instead.
  • Hardcoding HF repo filenames without verifying: model repos ship different names than recipes assume (e.g. walrus.pt not model.pt). Use list_repo_files() to discover actual names, filter by extension, pick smallest or first match.
  • Assuming a _mi300x.sh SLURM script name — use _amd.sh (covers MI250X, MI300X, MI350X with the same rocm7.2.x image). Overlay/--no-deps details: ai4science-studio/reference/rocm.md.

Read the full file on GitHub · 51 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.

  1. 1mo ago Changed f79990305ffe
  2. 2mo ago First seen · 51 lines · 41 tokens per session scan A 847a2d492122

Subscribe to this mod's changes

ai4science-huggingface-recipes is a skill published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 802 once invoked, about $0.0002 per session on Opus 5.5. 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 AIScientificai-for-scienceamddrug-discoveryearth-sciencefine-tuninghealthcare
Related

ai4science-huggingface-recipes compared with skills from other repositories

ai4science-huggingface-recipes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ai4science-huggingface-recipesAMDResearch/ai4science-studioSkill4yesterdayMITA41Cursor
batch-processing-clinical-textmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A161Claude Code
exporting-to-fhirmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A163Claude Code
choosing-openmed-modelsmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A134Claude Code
extracting-clinical-entitiesmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A118Claude Code
loading-openmed-modelsmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A118Claude Code
normalizing-rxnormmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A187Claude Code