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

64%

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 ./backend/cli/skills/data-engineering/hugging-face-datasets/SKILL.md

Quality

Content

57%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 skill is highly actionable with excellent executable examples, but it is overly verbose and inlines substantial reference material that belongs in separate files. Destructive/batch workflows also lack explicit validation checkpoints.

Suggestions

Move the template JSON schemas, the full 'Useful DuckDB SQL Functions' reference, and the complete Python API examples into separate reference files (e.g., references/templates.md, references/sql_reference.md), keeping SKILL.md a concise overview.

Add explicit validation checkpoints to destructive/batch workflows—e.g., after add_rows or --push-to, verify stats/row counts before proceeding ('Verify: `... stats --repo_id ...`; confirm row count before pushing further batches').

Cut redundancy: collapse the repeated command listings across Quick Start, Common Operations, and Commands Reference into a single reference, and remove the restated version number and general DuckDB function explanations Claude already knows.

Dimension	Reasoning	Score
Conciseness	The ~550-line body is noticeably verbose: the version is restated, command sequences are repeated across Quick Start, Common Operations, and Commands Reference, and the 'Useful DuckDB SQL Functions' section explains general DuckDB behavior Claude already knows.	2 / 5
Actionability	Provides fully executable, copy-paste-ready `uv run` commands and a complete Python API section, with concrete examples covering the common query, transform, export, and push cases.	5 / 5
Workflow Clarity	Multi-step workflows (Recommended Workflow, Combined Workflow Examples) are sequenced, but batch/destructive operations like add_rows and --push-to lack explicit validate-then-proceed checkpoints, capping clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Scripts are clearly signaled one level deep (scripts/sql_manager.py, scripts/dataset_manager.py, both real bundle files), but large reference material—template JSON schemas, full SQL function reference, and complete API examples—is inlined rather than split into separate reference files.	3 / 5
	Total	13 / 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 domain niche, but it omits an explicit "Use when..." trigger clause, which caps completeness. Adding concrete trigger phrases would push it into the top tier.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when creating, editing, or querying Hugging Face datasets, or when the user mentions HF Hub, dataset repos, or SQL-based dataset analysis').

Include natural synonyms and shorthand users actually say (HF, HuggingFace, Hub dataset) to broaden trigger coverage.

Sharpen the boundary with the HF MCP server by framing it as a trigger distinction ('Use this skill for X; use HF MCP for Y') rather than a feature note.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—"initializing repos", "defining configs/system prompts", "streaming row updates", and "SQL-based dataset querying/transformation"—giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Has a clear "what" with concrete capabilities, but lacks any explicit "Use when..." trigger clause—the only trigger guidance is the feature statement "Designed to work alongside HF MCP server", which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes natural terms like "Hugging Face Hub", "datasets", and "SQL", but omits common variations/synonyms users might say such as "HF", "HuggingFace", or file-format cues.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (dataset creation/editing + SQL querying) and disambiguates from the HF MCP server, though the boundary is described as a feature rather than via distinct trigger phrases.	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 (561 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: 2 missing	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/data-engineering/hugging-face-datasets/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.