# huggingface/skills

Give your agents the power of the Hugging Face ecosystem

Repository: https://github.com/huggingface/skills
Canonical: https://ross.abutalabs.com/products/huggingface-skills
Homepage: https://huggingface.co
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T20:03:43+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 20
- inputs: {"age_days": 282, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10964, forks 737 (observed 2026-08-28T04:10:44.861484+00:00)

## What it is
A collection of Agent Skills (SKILL.md folders) that teach AI coding agents how to use the Hugging Face ecosystem, including the hf-cli skill for Hub operations like searching models, managing datasets, and launching Spaces. Skills install via plugin marketplaces for Claude Code, Codex, Gemini CLI, and Cursor, or through the hf CLI.

## Use cases
- give my coding agent access to the hugging face hub
- let an ai agent search and download models from hugging face
- have claude code manage hugging face datasets and spaces
- install hf skills into codex or gemini cli
- teach my agent to train and evaluate models on the hub
- bootstrap hf cli usage in an mcp-compatible client

## When to choose
- you use Claude Code, Codex, Gemini CLI, or Cursor and want agent access to Hugging Face Hub operations
- you want standardized Agent Skills format instructions for ML workflows like dataset creation and model training
- you need an agent to run hf commands such as searching models, managing buckets, or launching jobs

## When to avoid
- your agent does not support skills, MCP, or AGENTS.md-style instruction files
- you need a runtime library for programmatically calling the Hub API rather than agent instructions
- you work outside the Hugging Face ecosystem entirely

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, mcp, cli, developer-tools, machine-learning
- domain: large-language-models, machine-learning, developer-tools
- platform: cli, cross-platform, python
- tags: agent-skills, hugging-face-hub, hf-cli, claude-code, codex, gemini-cli, cursor, skill-marketplace, agentsmd, ai-agents, automation

## Member repositories
- huggingface/skills (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:44.861484+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:17:17.081849+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/skills (fetched 2026-08-28T04:10:44.861484+00:00, sha b2cd95b97685)
  - homepage: https://huggingface.co (fetched 2026-08-29T08:16:03.645641+00:00, sha 3a1a5a51705d)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T08:16:03.654805+00:00, sha bdec26667b98)
  - site_page: https://huggingface.co/docs/transformers (fetched 2026-08-29T08:16:03.660519+00:00, sha 15a63894ac07)
  - site_page: https://huggingface.co/docs/diffusers (fetched 2026-08-29T08:16:03.662176+00:00, sha 595ce0157b00)
  - site_page: https://huggingface.co/docs/safetensors (fetched 2026-08-29T08:16:03.663689+00:00, sha 7fa2c18b9c26)
  - site_page: https://huggingface.co/docs/huggingface_hub (fetched 2026-08-29T08:16:03.665205+00:00, sha 4bba662fb619)
  - site_page: https://huggingface.co/docs/tokenizers (fetched 2026-08-29T08:16:03.666808+00:00, sha a89855921333)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T08:16:03.656681+00:00, sha de6b7a178be5)
  - site_page: https://huggingface.co/zai-org/GLM-5.3 (fetched 2026-08-29T08:16:03.658593+00:00, sha 4242fcde7d0e)
- Data as of 2026-08-30T08:39:29.467469+00:00.