القائمة
Search HuggingFace Hub for datasets by keyword. Use when the user wants to find training data, benchmarks, or evaluation datasets for ML/NLP/CV research.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Fetch the FULL TEXT of an arXiv paper (all sections — introduction, method, results, conclusion). Use when you need to read beyond the abstract into the paper's actual content. Only works for arXiv papers. For metadata/abstract only, use paper-read. For local PDFs, use paper-read-pdf.
Two-layer memory system with grep-based recall for research sessions.
Track specific scientific claims across the literature over time — who made it, who replicated it, who challenged it, whether it still stands. Use when verifying a key assumption before building on it, or when checking whether a published result has been updated or superseded.
Scan papers for conflicting empirical claims, methodological disagreements, or opposing conclusions on the same topic. Use when writing discussion sections, evaluating conflicting results, or checking if a claim is contested before building on it.
Synthesize findings across multiple papers into a coherent narrative, structured comparison table, or temporal evolution. Use after collecting papers via survey or paper-search. Goes beyond summarizing individual papers to produce insights that only emerge when reading across the corpus as a whole.
Full end-to-end deep research pipeline on a topic. Use when the user wants thorough, rigorous research — not just a survey. Orchestrates all research skills in sequence: collect → synthesize → critique claims → grade evidence → find gaps → assess reproducibility → optionally reproduce → write report.
| name | dataset-search |
| description | Search HuggingFace Hub for datasets by keyword. Use when the user wants to find training data, benchmarks, or evaluation datasets for ML/NLP/CV research. |
| always | false |
Search for datasets on HuggingFace Hub using web_fetch.
GET https://huggingface.co/api/datasets
| Parameter | Type | Default | Description |
|---|---|---|---|
search | string | required | Search keywords |
limit | int | 10 | Number of results (1–100) |
sort | string | downloads | Sort by: downloads, likes, lastModified, createdAt |
direction | int | -1 | -1 = descending (most popular first) |
full | bool | false | Include full dataset card info |
https://huggingface.co/api/datasets?search=<query>&limit=10&sort=downloads&direction=-1
web_fetch("https://huggingface.co/api/datasets?search=sentiment+analysis&limit=10&sort=downloads&direction=-1")
The response is a JSON array:
[
{
"id": "stanfordnlp/sst2",
"downloads": 5000000,
"likes": 320,
"tags": ["task_categories:text-classification", "language:en"],
"description": "The Stanford Sentiment Treebank...",
"lastModified": "2023-10-01T00:00:00.000Z",
"cardData": {
"license": "mit",
"task_categories": ["text-classification"],
"language": ["en"]
}
}
]
For each dataset, show:
stanfordnlp/sst2) — use with HuggingFace datasets libraryhttps://huggingface.co/datasets/<id>web_fetch("https://huggingface.co/api/datasets?search=sentiment+analysis&limit=10&sort=downloads&direction=-1")
web_fetch("https://huggingface.co/api/datasets?search=image+classification&limit=10&sort=downloads&direction=-1")
web_fetch("https://huggingface.co/api/datasets?search=question+answering&limit=10&sort=likes&direction=-1")
web_fetch("https://huggingface.co/api/datasets/stanfordnlp/sst2")
Once you have the dataset ID, the user can load it with:
from datasets import load_dataset
ds = load_dataset("stanfordnlp/sst2")
Or download via CLI:
huggingface-cli download stanfordnlp/sst2 --repo-type dataset
downloads by default — gives most widely-used datasets firstsort=likes gives community-favorite datasets (newer, high quality)dataset_download tool to generate a full download script