Name: hugging-face-datasets
Rating: 57.599999999999994 (1 reviews)
Author: administrakt0r

hugging-face-datasets

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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-datasets/SKILL.md

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

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.

The body is highly actionable with extensive executable examples, but it is verbose with redundant sections, lacks validation checkpoints in its batch/push workflows, and inlines material that should live in separate reference files. Trimming redundancy and adding verification steps would lift the weaker dimensions.

Suggestions

De-duplicate command listings: keep one authoritative Commands Reference and have Quick Start / Combined Examples point to it instead of repeating full invocations.

Add explicit validation/verification checkpoints to batch and --push-to workflows (e.g. verify row count or schema after add_rows, confirm pushed dataset is readable before declaring success).

Move the bulk DuckDB SQL function reference, template JSON schemas, and example sets into separate reference files and link to them one level deep from SKILL.md, ensuring the referenced scripts/ and examples/ files actually ship in the bundle.

Dimension	Reasoning	Score
Conciseness	Mostly useful reference content, but ~540 lines with notable redundancy — the same sql_manager commands recur across Quick Start, Common Operations, and Combined Workflow Examples, and dataset_manager commands recur across Recommended Workflow and Commands Reference.	3 / 5
Actionability	Abundant copy-paste ready CLI commands, executable SQL snippets, JSON templates, and a Python API example that cover the common cases comprehensively.	5 / 5
Workflow Clarity	Sequenced workflows exist (Recommended Workflow, numbered Combined Examples), but batch/destructive operations like add_rows and --push-to lack explicit validation checkpoints, capping workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Good section structure, but the bulk reference material (DuckDB SQL functions, all templates, full command reference) is inlined in SKILL.md rather than split into separate files, and the referenced scripts/examples do not exist in the bundle.	3 / 5
	Total	14 / 20 Passed

Description

71%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 and action-oriented with a clear niche, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness and limits its trigger-term quality. Adding concrete trigger phrases would round it out.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when creating, editing, or running SQL queries on Hugging Face datasets, or when the user mentions HF Hub datasets or dataset training data').

Include natural synonyms users say such as 'HF', 'HuggingFace', and 'Hub datasets' to broaden trigger coverage.

Keep the concrete action list but pair it with the trigger clause so both 'what' and 'when' are answered explicitly.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'initializing repos', 'defining configs/system prompts', 'streaming row updates', 'SQL-based dataset querying/transformation' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' trigger clause; the phrase 'Designed to work alongside HF MCP server' only weakly implies when, so per the rubric cap completeness stays at 3.	3 / 5
Trigger Term Quality	Good keyword coverage with 'datasets', 'Hugging Face Hub', and 'SQL-based dataset querying', but missing common natural synonyms users would say like 'HF', 'HuggingFace', or 'Hub datasets'.	4 / 5
Distinctiveness Conflict Risk	The HF Hub dataset niche is mostly distinct, and it explicitly carves a complementary role vs the HF MCP server, with only minor overlap risk against a generic HF MCP skill.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (545 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 44 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/hugging-face-datasets/SKILL.md
Commit: 57c135b

Reviewed: 4 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.