Hugging Face Hub
Apps & AutomationHugging Face Hub is an Agent Skill for apps & automation published in the agentic-in/elephant-agent repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Guides model, dataset, and space workflows around Hugging Face Hub with explicit auth, artifact, and cache assumptions.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/agentic-in/elephant-agent/blob/HEAD/packages/skills/builtin_packages/mlops/huggingface-hub/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/hugging-face-hub, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Hugging Face Hub
Use this built-in skill when the user is working with model repos, datasets, cards, or publishing flows on Hugging Face Hub.
Core rules
- Confirm the exact repo id, artifact type, and auth posture before acting.
- Distinguish local cache state from remote hub state.
- Inspect model cards, licenses, and file sizes before large pulls or pushes.
- Keep publish steps explicit and reversible.
Default workflow
- Verify the target repo or dataset identifier.
- Check auth, access level, and local storage implications.
- Inspect metadata, artifact layout, and intended use.
- Pull, publish, or mirror only the artifacts the task actually needs.
Guardrails
- Do not assume a repo is public, local, or already cached without verification.
- Do not hide large downloads or publishes behind vague progress language.
- Do not ignore license or model-card constraints.