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.

72

Quality

90%

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

87%Weight 40%Scale 1-5

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

Highly actionable and token-efficient command reference with good progressive disclosure into two bundle files. The main gap is missing validation/verification steps for destructive and batch operations, which limits workflow clarity.

Suggestions

Add verification/validation checkpoints around destructive commands (e.g., confirm target repo before `hf repo delete`, verify `--dry-run` output before `hf repo-files delete`, or check `hf cache ls` before `hf cache rm`).

For batch operations like `hf cache prune` and folder/pattern deletes, include a preview/list step before the irreversible action.

Add a short workflow sequence for the publish pattern (create -> upload -> verify -> tag) with an explicit verification step before tagging.

DimensionReasoningScore

Conciseness

Lean command tables and short commented code blocks with no padding or explanation of concepts Claude already knows; every line carries usable information.

5 / 5

Actionability

Fully executable `hf` commands with inline comments covering common cases (download, upload, repo, cache, jobs, endpoints) — copy-paste ready.

5 / 5

Workflow Clarity

Commands are well grouped, but destructive and batch operations (repo delete, repo-files delete, cache rm/prune, endpoints delete) lack validation or verification checkpoints, capping workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

SKILL.md is a concise overview with clearly signaled one-level-deep references to references/commands.md and references/examples.md, both confirmed to exist, yielding easy navigation.

5 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

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 strong, specific description with clear 'what' and 'when' clauses and concrete actions across the HF Hub surface area. It is third-person and avoids fluff; minor gains would come from adding natural synonyms and file extensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs' — covering auth, transfers, repos, cache, and cloud compute comprehensively.

5 / 5

Completeness

Explicitly answers both what ('Execute Hugging Face Hub operations using the `hf` CLI') and when ('Use when the user needs to download... or run compute jobs').

5 / 5

Trigger Term Quality

Natural phrases like 'download models', 'upload files', 'create repos' are present and would be user-spoken, but synonyms and file extensions (.safetensors, .bin) are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped to the Hugging Face Hub `hf` CLI with distinct triggers (HF repos, model/dataset downloads, HF cache, HF compute jobs), giving it a clear niche with minimal conflict risk.

5 / 5

Total

19

/

20

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.