CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

72%

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 ./skills/hugging-face-cli/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

A highly actionable, well-sectioned command reference whose main weaknesses are the Quick Reference/Core Commands duplication, missing validation guidance around destructive repo/cache/endpoint operations, and two clearly signaled reference files that are absent from the bundle.

Suggestions

Remove the duplication between the 'Quick Command Reference' table and 'Core Commands' (or drop the table and keep the annotated command blocks) to reclaim tokens.

Add a short validation note for destructive/batch operations, e.g. run `hf repo-files list` or `hf cache ls` before `delete`/`rm`, and confirm `hf auth whoami` before uploads.

Ship the referenced bundle files (references/commands.md, references/examples.md) or remove the References section, and move the exhaustive command/GPU-flavor listings into them.

DimensionReasoningScore

Conciseness

Mostly efficient — the body is dense command lists with no concept explanations Claude already knows — but the ~20-row 'Quick Command Reference' table duplicates the 'Core Commands' section almost entirely, and 'Check Cache Usage' repeats `hf cache ls`/`hf cache rm` already shown. This matches anchor 3 ('could be tightened'); not 2, since there is no padded prose or unnecessary explanation, just structural duplication.

3 / 5

Actionability

Every section gives fully executable, copy-paste-ready commands with realistic flag combinations (`hf download <repo_id> --local-dir ./models`, `hf upload <repo_id> . . --create-pr`, the fully-specified `hf endpoints deploy` with region/vendor/instance flags), and 'Common Patterns' covers the common cases. Matches anchor 5; placeholders like `<repo_id>` are standard CLI notation, not pseudocode.

5 / 5

Workflow Clarity

Multi-step patterns are present (publish: `repo create` → `upload` → `tag create`), but the skill documents destructive and batch operations — `hf repo delete`, `hf repo-files delete "*.txt"`, `hf cache rm`, `hf endpoints delete --yes` — with no verification or feedback-loop steps (e.g., confirm what a delete will remove, or verify an upload landed), which caps workflow clarity at 3 per the judging guidelines. Not 2: sequences that exist are correct and clearly shown.

3 / 5

Progressive Disclosure

Section structure is good and two references are clearly signaled ('Complete command reference: See references/commands.md'), but no references/ directory exists in the bundle — both pointers are dangling — and the inline 'Core Commands' material overlaps what the missing commands.md would presumably hold. This fits anchor 3 (structure present, but reference placement/content split is not verifiable or appropriately divided); not 4, because scored against the actual bundle structure the references do not resolve.

3 / 5

Total

14

/

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.

A clear, third-person description with concrete actions and a distinct Hugging Face niche, weakened only by its missing 'Use when...' trigger clause and the absence of common keywords like 'models', 'datasets', and 'spaces'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to download or upload models, datasets, or Spaces to/from the Hugging Face Hub, manage Hub repos or local HF cache, or run jobs on HF compute.'

Include the natural nouns users actually say — 'models', 'datasets', 'Spaces', 'HF_TOKEN/login' — to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('hf CLI', 'Hugging Face Hub') and several concrete actions — 'downloading, uploading, and managing repositories, cache, and compute resources' — matching the anchor for several specific actions with minor gaps. Not 5: coverage is not comprehensive (authentication, browsing/searching models, and endpoints are absent); not 3: it lists more than 1-2 actions.

4 / 5

Completeness

The 'what' is clear and concrete (terminal access to the Hub for download/upload/management), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. Not 4: the 'when' is only weakly implied by the action list, not stated.

3 / 5

Trigger Term Quality

Natural user terms are present: 'terminal', 'Hugging Face Hub', 'downloading', 'uploading', 'repositories', 'cache'. A few common natural terms are missing — users routinely say 'models', 'datasets', 'spaces', or 'hf' when they need this skill, so it falls just short of the comprehensive-synonyms anchor 5 but clearly above anchor 3.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche — the 'hf CLI' and 'Hugging Face Hub' — with distinct triggers (downloading/uploading Hub repositories, Hub cache, HF compute) and minimal overlap with other skills. It matches anchor 5; no broader anchor fits since the domain is explicitly and uniquely named.

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.

Validation — 14 / 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

Path

skills/hugging-face-cli/SKILL.md

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.