CtrlK
BlogDocsLog inGet started
Tessl Logo

hugging-face-cli

Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is highly actionable and well-structured with clean progressive disclosure to real reference files, but it loses points on conciseness from a duplicated quick-reference table and on workflow clarity due to missing validation checkpoints for destructive operations.

Suggestions

Remove or shrink the 'Quick Command Reference' table since its entries are repeated verbatim in the 'Core Commands' sections, keeping only the most-used few to reduce token duplication.

Add explicit verification steps before destructive/batch commands (e.g. run 'hf models info' / 'hf cache ls' to confirm the target before 'hf repo delete' or 'hf cache rm', and confirm before 'hf upload --delete="*"').

Add a brief confirmation/--yes guidance note for 'hf endpoints delete --yes' and 'hf repo delete' so batch destructive flows include a checkpoint.

DimensionReasoningScore

Conciseness

The body is mostly efficient with command tables and commented code rather than conceptual filler, but the 'Quick Command Reference' table largely duplicates the detailed 'Core Commands' sections, so it could be tightened; it is not the level-3 'every token earns its place' case.

2 / 3

Actionability

Commands are fully executable and copy-paste ready with concrete flags and realistic repo ids (e.g. 'hf download meta-llama/Llama-3.2-1B-Instruct --local-dir ./model'), matching the 'fully executable code/commands' anchor rather than the pseudocode level.

3 / 3

Workflow Clarity

Operations are organized by command group with a few sequenced patterns (Publish, Sync), but destructive/batch operations such as 'hf repo delete', 'hf cache rm', 'hf upload --delete', and 'hf endpoints delete' lack explicit validation checkpoints, which caps workflow clarity at 2 per the rubric.

2 / 3

Progressive Disclosure

SKILL.md is a clear overview with well-signaled, one-level-deep references to real bundle files ('references/commands.md', 'references/examples.md'), matching the 'clear overview with well-signaled one-level-deep references' anchor; it is not the level-2 case of inline content that should be separate.

3 / 3

Total

10

/

12

Passed

Description

100%

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: it specifies concrete capabilities, includes an explicit 'Use when' trigger clause, and occupies a distinct niche unlikely to conflict with other skills. It fully satisfies all four dimensions at the top of the scale.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs' — matching the 'lists multiple specific concrete actions' anchor; it is not the level-2 case of naming only a domain and some actions.

3 / 3

Completeness

It explicitly answers both 'what' ('Execute Hugging Face Hub operations using the `hf` CLI') and 'when' via an explicit 'Use when the user needs to...' clause, matching the anchor for clearly answering both with explicit triggers.

3 / 3

Trigger Term Quality

It includes natural terms users would actually say — 'download models/datasets/spaces', 'upload files', 'create repos', 'run compute jobs' — giving good coverage rather than just 'some relevant keywords'.

3 / 3

Distinctiveness Conflict Risk

The Hugging Face Hub CLI niche is distinct with specific triggers ('Hub repositories', 'compute jobs on HF infrastructure'), making it unlikely to trigger for unrelated skills; it is not the level-2 case of possible overlap with similar skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
synthetic-sciences/openscience
Reviewed

Table of Contents

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.