Name: hf-cli
Rating: 76 (1 reviews)
Author: huggingface

hf-cli

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

2.27x

Quality

66%

Does it follow best practices?

Impact

100%

2.27x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./projects/pre-training/.agents/skills/hf-cli/SKILL.md

Quality

Content

50%

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

This skill serves as a comprehensive CLI reference card for the `hf` command, with well-organized command groupings and clear syntax. Its main weaknesses are the lack of concrete worked examples showing common workflows (download a model, upload a dataset, authenticate and verify) and the monolithic listing of all subcommands inline rather than focusing on the most common operations with pointers to `--help` for the rest.

Suggestions

Add 2-3 concrete, copy-paste-ready workflow examples for common tasks (e.g., authenticate then download a model, upload a folder to a dataset repo) to improve actionability.

Trim the command listing to the most commonly used commands and add a note like 'Run `hf --help` for the full command list' to improve conciseness.

Add a brief workflow for destructive operations like `hf repos delete` that includes a verification step (e.g., `hf repos info` before deleting) to improve workflow clarity.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient as a CLI reference, but includes some unnecessary lines like the version/regeneration note and the install command that could be trimmed. The comprehensive command listing is useful but borders on verbose for a skill file—some subcommands could be deferred to `--help`.	2 / 3
Actionability	The skill provides concrete command syntax with argument placeholders, which is helpful. However, it lacks executable examples showing real-world usage (e.g., downloading a specific model, uploading with specific flags). It's essentially a reference card rather than actionable guidance with worked examples.	2 / 3
Workflow Clarity	There are no multi-step workflows demonstrated (e.g., authenticate → download → verify). The tips section hints at useful patterns but doesn't sequence them. For operations like `hf repos delete` (irreversible), there's no validation or confirmation step mentioned.	2 / 3
Progressive Disclosure	The content is organized with clear section headers and grouped subcommands, which aids navigation. However, the entire command reference is inlined in a single file rather than providing a concise overview with references to detailed docs. The tips at the end suggesting `--help` partially compensates, but the file is quite long for a SKILL.md.	2 / 3
	Total	8 / 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.

The description is strong in specificity and distinctiveness, clearly identifying the tool, platform, and concrete actions. It includes excellent natural trigger terms that users would actually say. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about downloading models from Hugging Face, uploading datasets to the Hub, managing HF repositories, or using the hf CLI.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'downloading, uploading, and managing repositories, models, datasets, and Spaces.' Also specifies the tool ('hf' CLI) and notes it replaces the deprecated 'huggingface-cli' command.	3 / 3
Completeness	Clearly answers 'what does this do' (downloading, uploading, managing HF resources via CLI), but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the capabilities listed.	2 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'Hugging Face', 'Hub', 'hf', 'downloading', 'uploading', 'repositories', 'models', 'datasets', 'Spaces', and 'huggingface-cli'. Good coverage of terms a user working with Hugging Face would naturally use.	3 / 3
Distinctiveness Conflict Risk	Very distinct niche — Hugging Face Hub CLI operations are unlikely to conflict with other skills. The mention of specific tool name ('hf'), platform ('Hugging Face Hub'), and resource types (models, datasets, Spaces) creates clear boundaries.	3 / 3
	Total	11 / 12 Passed

Validation

72%

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 — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	8 / 11 Passed

Repository: huggingface/context-course
Commit: 0448a7c

Reviewed: 26 days 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.