CtrlK
BlogDocsLog inGet started
Tessl Logo

hugging-face-cli

The hf CLI provides direct terminal access to the Hugging Face Hub for downloading, uploading, and managing repositories, cache, and compute resources.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hugging-face-cli/SKILL.md

The canonical home for this skill is hugging-face-cli in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

The content is highly actionable with copy-paste-ready commands and no concept padding, but it lacks validation checkpoints around its destructive/batch operations and its referenced bundle files do not exist while the bulk command reference is inlined. Adding verification steps and either creating or removing the dangling references would lift the two capped dimensions.

Suggestions

Add explicit validation/confirmation steps before destructive commands — e.g. 'Before `hf repo delete`, run `hf repo list` to confirm the target; deletion is irreversible.'

Create references/commands.md and references/examples.md (or remove the References section) so navigation is not broken, and move the bulk command detail out of SKILL.md into commands.md to reduce duplication with the Quick Reference table.

Add a feedback loop to the Sync Space pattern (verify the upload result / re-list files) since '--delete="*"' is a destructive batch operation.

DimensionReasoningScore

Conciseness

The body is almost entirely executable commands with terse inline comments and no concept over-explanation, but the 'Quick Command Reference' table duplicates much of the 'Core Commands' section and 'Common Patterns' re-shows commands already listed — minor instances that could be trimmed (anchor 4, not the fully lean 5).

4 / 5

Actionability

Every section gives fully executable, copy-paste-ready commands with real flags (e.g. 'hf download <repo_id> --local-dir ./models', 'hf upload <repo_id> . . --create-pr') covering auth, download, upload, repo/cache management, jobs, and endpoints across common cases (anchor 5).

5 / 5

Workflow Clarity

Multi-step patterns like Publish (create → upload → tag) and Sync Space are sequenced, but destructive/batch operations ('hf repo delete', 'hf repo-files delete', 'hf cache rm', 'hf endpoints delete', sync with '--delete="*"') carry no validation or confirmation checkpoints, so per the rubric cap workflow_clarity is held at 3.

3 / 5

Progressive Disclosure

Section structure is clear and the References section signals 'references/commands.md' and 'references/examples.md', but those files do not exist (broken references) and a near-complete command reference is inlined in SKILL.md itself — content that the doc says belongs in a separate file is inline (anchor 3).

3 / 5

Total

15

/

20

Passed

Description

70%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.

The description is specific, third-person, and clearly distinct to the Hugging Face Hub CLI, but it omits any 'Use when...' trigger guidance, capping completeness at 3. Adding explicit trigger phrases and the natural nouns 'models/datasets/spaces' would raise trigger quality and completeness.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to download/upload models or datasets to the Hugging Face Hub, manage HF cache, or run compute jobs.'

Replace the generic 'repositories' with the natural nouns users actually say — 'models, datasets, and spaces' — to improve trigger-term quality.

Keep the third-person voice but pair the 'what' with the 'when' so both halves of the completeness question are explicitly answered.

DimensionReasoningScore

Specificity

Quotes 'direct terminal access to the Hugging Face Hub for downloading, uploading, and managing repositories, cache, and compute resources' — names the domain and several concrete actions, but 'managing' is generic and endpoints/spaces/jobs are rolled up rather than enumerated, leaving minor coverage gaps (anchor 4).

4 / 5

Completeness

Has a clear 'what' ('provides direct terminal access... for downloading, uploading, and managing...') but no 'when' — there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap completeness is held at 3.

3 / 5

Trigger Term Quality

Strong natural terms 'Hugging Face Hub', 'hf CLI', 'downloading', 'uploading', 'cache', 'compute resources' are present, but the most common user phrasings 'models', 'datasets', and 'spaces' are absent — good coverage with a few natural terms missing (anchor 4, not 5).

4 / 5

Distinctiveness Conflict Risk

'Hugging Face Hub' and 'hf CLI' carve a clear niche with distinct triggers and minimal overlap with other skills; it would not fire for unrelated tasks (anchor 5).

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.