Python Data Analysis
A-EVO-Lab/a-evolve
Best practices for multi-step Python tasks including data analysis, HuggingFace datasets, token counting, and any task requiring state across multiple python() calls.
Explores Hugging Face datasets through the read-only Dataset Viewer API: list splits, preview and page through rows, search, filter, and fetch parquet links and statistics.
Install Hugging Face Dataset Viewer
$ npx skills add huggingface/skills --skill huggingface-datasets -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install huggingface/skills huggingface-datasets --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/huggingface-datasets .claude/skills/huggingface-datasets && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "huggingface-datasets" agent skill from https://github.com/huggingface/skills/tree/main/skills/huggingface-datasets into .claude/skills/huggingface-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-datasets", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/huggingface/skills/tree/main/skills/huggingface-datasetsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add huggingface/skills --skill huggingface-datasets -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install huggingface/skills huggingface-datasets --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/huggingface-datasets .agents/skills/huggingface-datasets && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "huggingface-datasets" agent skill from https://github.com/huggingface/skills/tree/main/skills/huggingface-datasets into .agents/skills/huggingface-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-datasets", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add huggingface/skills --skill huggingface-datasets -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install huggingface/skills huggingface-datasets --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/huggingface-datasets .cursor/skills/huggingface-datasets && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "huggingface-datasets" agent skill from https://github.com/huggingface/skills/tree/main/skills/huggingface-datasets into .cursor/skills/huggingface-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-datasets", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/huggingface/skills.git --path skills/huggingface-datasets--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add huggingface/skills --skill huggingface-datasets -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install huggingface/skills huggingface-datasets --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/huggingface-datasets .gemini/skills/huggingface-datasets && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "huggingface-datasets" agent skill from https://github.com/huggingface/skills/tree/main/skills/huggingface-datasets into .gemini/skills/huggingface-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-datasets", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install huggingface/skills huggingface-datasetsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add huggingface/skills --skill huggingface-datasets -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/huggingface-datasets .github/skills/huggingface-datasets && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "huggingface-datasets" agent skill from https://github.com/huggingface/skills/tree/main/skills/huggingface-datasets into .github/skills/huggingface-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-datasets", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add huggingface/skills --skill huggingface-datasets -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install huggingface/skills huggingface-datasets --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/huggingface-datasets .opencode/skills/huggingface-datasets && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "huggingface-datasets" agent skill from https://github.com/huggingface/skills/tree/main/skills/huggingface-datasets into .opencode/skills/huggingface-datasets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-datasets", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
huggingface-datasets- GitHub stars
- 11k
- Used in
- 3 other repos
- Token cost
- ~1.1k tokens
- SKILL.md length
- 394 words
- Files
- 1
- Skills in repo
- 25
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Explores Hugging Face datasets through the read-only Dataset Viewer API: list splits, preview and page through rows, search, filter, and fetch parquet links and statistics.
- Works in 6 steps: Optionally validate dataset availability… → Resolve config + split with /splits. → Preview with /first-rows. → …
- Previewing a dataset's splits and first rows before downloading anything
- SKILL.md covers Core workflow, Defaults, Dataset Viewer and Creating and Uploading Datasets, plus 1 more section
- Calls hf, curl and npx; reaches datasets-server.huggingface.co and huggingface.co; needs HF_TOKEN
What it does
The skill sends read-only GET calls to the Dataset Viewer API at datasets-server.huggingface.co. A typical run checks that the dataset is valid, resolves its config and split, previews the first rows, and then pages through the content with offset and length, where length tops out at 100 for row-style endpoints.
Beyond browsing, it covers text search over string columns, filtering with a where predicate and optional orderby, parquet shard links, size totals, per-column statistics and Croissant metadata when the dataset has it. For partial pages it follows response fields such as num_rows_total and partial. Gated or private datasets need a bearer token taken from HF_TOKEN.
When your agent uses it
- Previewing a dataset's splits and first rows before downloading anything
- Searching text columns or filtering rows in a hosted dataset
- Getting parquet URLs and size statistics for a Hugging Face dataset
Example prompts
- “List the configs and splits for stanfordnlp/imdb and show me the first rows.”
- “Search the train split of that dataset for rows mentioning refunds.”
- “Give me the parquet links and column statistics for this dataset.”
Requirements
- Network access to datasets-server.huggingface.co
- An HF_TOKEN for gated or private datasets
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Optionally validate dataset availability with /is-valid.
- Resolve config + split with /splits.
- Preview with /first-rows.
- Paginate content with /rows using offset and length (max 100).
- Use /search for text matching and /filter for row predicates.
- Retrieve parquet links via /parquet and totals/metadata via /size and /statistics.
What it can do on your machine
Read from SKILL.md and the folder at commit ca0325b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
hfcurlnpx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
datasets-server.huggingface.cohuggingface.co
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
HF_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Hugging Face Dataset Viewer loads about 1.1k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 394 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from huggingface/skills at commit ca0325b, republished under its Apache-2.0 licence (© huggingface). 394 words, ~1,141 tokens.
Download SKILL.mdSave it as
.claude/skills/huggingface-datasets/SKILL.md (or your agent's skills folder).- name
- huggingface-datasets
- description
- Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
Hugging Face Dataset Viewer
Use this skill to execute read-only Dataset Viewer API calls for dataset exploration and extraction.
Core workflow
- Optionally validate dataset availability with
/is-valid. - Resolve
config+splitwith/splits. - Preview with
/first-rows. - Paginate content with
/rowsusingoffsetandlength(max 100). - Use
/searchfor text matching and/filterfor row predicates. - Retrieve parquet links via
/parquetand totals/metadata via/sizeand/statistics.
Defaults
- Base URL:
https://datasets-server.huggingface.co - Default API method:
GET - Query params should be URL-encoded.
offsetis 0-based.lengthmax is usually100for row-like endpoints.- Gated/private datasets require
Authorization: Bearer <HF_TOKEN>.
Dataset Viewer
Validate dataset:/is-valid?dataset=<namespace/repo>List subsets and splits:/splits?dataset=<namespace/repo>Preview first rows:/first-rows?dataset=<namespace/repo>&config=<config>&split=<split>Paginate rows:/rows?dataset=<namespace/repo>&config=<config>&split=<split>&offset=<int>&length=<int>Search text:/search?dataset=<namespace/repo>&config=<config>&split=<split>&query=<text>&offset=<int>&length=<int>Filter with predicates:/filter?dataset=<namespace/repo>&config=<config>&split=<split>&where=<predicate>&orderby=<sort>&offset=<int>&length=<int>List parquet shards:/parquet?dataset=<namespace/repo>Get size totals:/size?dataset=<namespace/repo>Get column statistics:/statistics?dataset=<namespace/repo>&config=<config>&split=<split>Get Croissant metadata (if available):/croissant?dataset=<namespace/repo>
Pagination pattern:
curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=0&length=100"
curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=100&length=100"When pagination is partial, use response fields such as num_rows_total, num_rows_per_page, and partial to drive continuation logic.
Search/filter notes:
/searchmatches string columns (full-text style behavior is internal to the API)./filterrequires predicate syntax inwhereand optional sort inorderby.- Keep filtering and searches read-only and side-effect free.
For CLI-based parquet URL discovery or SQL, use the hf-cli skill with hf datasets parquet and hf datasets sql.
Show full SKILL.md (179 more words)Show less
Creating and Uploading Datasets
Use one of these flows depending on dependency constraints.
Zero local dependencies (Hub UI):
- Create dataset repo in browser:
https://huggingface.co/new-dataset - Upload parquet files in the repo "Files and versions" page.
- Verify shards appear in Dataset Viewer:
curl -s "https://datasets-server.huggingface.co/parquet?dataset=<namespace>/<repo>"Low dependency CLI flow (npx @huggingface/hub / hfjs):
- Set auth token:
export HF_TOKEN=<your_hf_token>- Upload parquet folder to a dataset repo (auto-creates repo if missing):
npx -y @huggingface/hub upload datasets/<namespace>/<repo> ./local/parquet-folder data- Upload as private repo on creation:
npx -y @huggingface/hub upload datasets/<namespace>/<repo> ./local/parquet-folder data --privateAfter upload, call /parquet to discover <config>/<split>/<shard> values for querying with @~parquet.
Agent Traces
The Hub supports raw agent session traces from Claude Code, Codex, and Pi Agent. Upload them to Hugging Face Datasets as original JSONL files and the Hub can auto-detect the trace format, tag the dataset as Traces, and enable the trace viewer for browsing sessions, turns, tool calls, and model responses. Common local session directories:
- Claude Code:
~/.claude/projects - Codex:
~/.codex/sessions - Pi:
~/.pi/agent/sessions
Default to private dataset repos because traces can contain prompts, file paths, tool outputs, secrets, or PII. Preserve the raw .jsonl files and nest them by project/cwd instead of uploading every session at the dataset root.
hf repos create <namespace>/<repo> --type dataset --private --exist-ok
hf upload <namespace>/<repo> ~/.codex/sessions codex/<project-or-cwd> --type dataset© huggingface, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/huggingface-datasets of huggingface/skills.
Open the folder on GitHubat commit ca0325b
Used in 3 other repositories
We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in huggingface/skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Hugging Face Dataset Viewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hugging Face Dataset Viewer this skillhuggingface/skills | 11k | 3 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Python Data AnalysisA-EVO-Lab/a-evolve | 805 | — | ~476 | Automated safety check: Pass | None | |
| Veomni New ModelByteDance-Seed/VeOmni | 2.2k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Dataset FinderLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.4k | Automated safety check: Pass | Proprietary | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Upload Post Imagehuggingface/blog | 3.5k | — | ~1.1k | Automated safety check: Pass | None |
Similar skills
Veomni New Model
ByteDance-Seed/VeOmni
A skill your agent uses when adding support for a new model to VeOmni.
Dataset Finder
LeoYeAI/openclaw-master-skills
A skill your agent uses when users need to search for datasets, download data files, or explore data repositories.
LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
- Official
Upload Post Image
huggingface/blog
A skill your agent uses when adding or migrating non-thumbnail images for a Hugging Face Blog post.
Esmfold2
JimLiu/science-skills
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.
More from huggingface/skills
All 25 skills in this repo- Official
SageMaker IAM Role Preflight
huggingface/skills
Finds or validates a usable SageMaker execution role before deploying or training, so scripts do not try to create IAM roles they lack permission to create.
- Official
SageMaker Serving Image Selection
huggingface/skills
Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.
- Official
Hugging Face LLM Trainer
huggingface/skills
Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.
- Official
Sentence-Transformers Training Router
huggingface/skills
Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.
- Official
Python Environment Setup for SageMaker
huggingface/skills
Sets up an isolated Python environment with a supported interpreter and current boto3 before any SageMaker deployment, training or AWS automation code runs.
- Official
Hugging Face Local Model Evals
huggingface/skills
Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.
Related
Works with
Categories
Questions about Hugging Face Dataset Viewer
What does Hugging Face Dataset Viewer do?
Explores Hugging Face datasets through the read-only Dataset Viewer API: list splits, preview and page through rows, search, filter, and fetch parquet links and statistics. co. A typical run checks that the dataset is valid, resolves its config and split, previews the first rows, and then pages through the content with offset and length, where length tops out at 100 for row-style endpoints.
When should I use Hugging Face Dataset Viewer?
Hugging Face Dataset Viewer fits situations like: previewing a dataset's splits and first rows before downloading anything; searching text columns or filtering rows in a hosted dataset; getting parquet URLs and size statistics for a Hugging Face dataset.
How do I install Hugging Face Dataset Viewer in Claude Code?
Run `npx skills add huggingface/skills --skill huggingface-datasets -a claude-code`. Or copy the skill folder (skills/huggingface-datasets in huggingface/skills) into .claude/skills/huggingface-datasets in your project. Claude Code loads it when a task matches its description.
How do I install Hugging Face Dataset Viewer in Codex?
Run `npx skills add huggingface/skills --skill huggingface-datasets -a codex`. Or copy the skill folder (skills/huggingface-datasets in huggingface/skills) into .agents/skills/huggingface-datasets in your project. Codex loads it when a task matches its description.
Can I use Hugging Face Dataset Viewer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huggingface/skills --skill huggingface-datasets -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huggingface-datasets, .gemini/skills/huggingface-datasets, .github/skills/huggingface-datasets and .opencode/skills/huggingface-datasets in your project.
What does Hugging Face Dataset Viewer need to run?
Going by SKILL.md and its folder, Hugging Face Dataset Viewer needs the command-line tools its instructions call (hf, curl and npx) and credentials named HF_TOKEN. Our summary lists: Network access to datasets-server.huggingface.co; An HF_TOKEN for gated or private datasets.
Does Hugging Face Dataset Viewer access the network?
SKILL.md names 2 domains. In commands or code: datasets-server.huggingface.co and huggingface.co; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Hugging Face Dataset Viewer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Hugging Face Dataset Viewer use?
Hugging Face Dataset Viewer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Hugging Face Dataset Viewer use?
About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Hugging Face Dataset Viewer?
Skills that share tags, products or a category with Hugging Face Dataset Viewer: Python Data Analysis (A-EVO-Lab/a-evolve, 805 stars), Veomni New Model (ByteDance-Seed/VeOmni, 2.2k stars), Dataset Finder (LeoYeAI/openclaw-master-skills, 2.2k stars) and LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hugging Face Dataset Viewer?
huggingface (a GitHub organization, an official publisher) maintains it in huggingface/skills, which has 11,142 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 1, 2026.
Source: huggingface/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.