huggingface-hub

HuggingFace hf CLI: search/download/upload models, datasets.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, actionable CLI reference that respects token budget and needs no external bundle files. The main gap is the absence of validation/verification guidance around destructive commands, which limits workflow clarity.

Suggestions

Add a brief warning and verification step for destructive commands (e.g. confirm `hf repos delete` target with `hf repos info` first, or recommend `--dry-run` where available).

Consider a short worked example showing a complete flow (auth → download → upload) with a checkpoint between steps to model safe sequencing.

Dimension	Reasoning	Score
Conciseness	The body is a lean command reference grouped by category; it avoids explaining concepts Claude already knows and the brief intro/deprecation notes earn their tokens.	3 / 3
Actionability	Commands are concrete, executable templates with arguments (e.g. `hf download REPO_ID`, `hf datasets sql SQL`, `hf upload-large-folder REPO_ID LOCAL_PATH`) that are copy-paste ready.	3 / 3
Workflow Clarity	Commands are well-organized by category with a Quick Start, but destructive operations (delete, delete-files, rm, move) appear without any validation or verification guidance, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and none are needed; the self-contained reference is cleanly sectioned (Quick Start, Core Commands, Specialized Interactions, Advanced Usage), giving easy navigation without nested references.	3 / 3
	Total	11 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, specific description that names concrete actions and uses natural trigger terms within a clearly distinct niche. Its main weakness is the absence of an explicit "Use when..." trigger clause, which leaves the "when to use" half of completeness implied rather than stated.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when downloading, searching, or uploading Hugging Face models and datasets, or when the user mentions the hf CLI or Hub."

Include a couple of natural variation terms (e.g. "Hub", "Spaces", "checkpoints") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"search/download/upload models, datasets" lists three concrete actions on a named domain, matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but lacks any "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2.	2 / 3
Trigger Term Quality	"HuggingFace", "hf", "models", "datasets", "search/download/upload" are exactly the natural terms a user would say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	"HuggingFace hf CLI" carves out a clear niche with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/mlops/huggingface-hub/SKILL.md
Commit: b7a05b6

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.