CtrlK
BlogDocsLog inGet started
Tessl Logo

hugging-face-dataset-viewer

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

65

Quality

79%

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-dataset-viewer/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, actionable reference with concrete commands and a clear core workflow. It is held back from the top band by placeholder-laden examples, the absence of explicit error-recovery feedback loops, and a small amount of redundancy and generic filler.

Suggestions

Replace remaining placeholders in the upload and parquetlens query commands with a fully worked real example so every command is copy-paste executable.

Add an explicit validate-fix-retry loop for the upload flow (e.g. re-check /parquet after upload, surface errors, retry) to raise workflow clarity.

Remove the generic 'When to Use' boilerplate line and de-duplicate the endpoint list against the Core workflow summary to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is mostly lean endpoint lists and executable curl/npx examples with no padding about what Hugging Face is, but the endpoint catalogue duplicates the Core workflow summary and the generic 'When to Use' line is mild fluff that could be trimmed.

4 / 5

Actionability

Provides concrete, mostly copy-paste-ready curl and npx commands with a real dataset (stanfordnlp/imdb) and jq derivation, but several upload/query commands retain unsubstituted placeholders, leaving minor gaps.

4 / 5

Workflow Clarity

A clear numbered Core workflow with an optional /is-valid validation step and a 'verify shards appear in Dataset Viewer' checkpoint for uploads; not a 5 because pagination continuation and upload error recovery lack explicit validate-fix-retry feedback loops.

4 / 5

Progressive Disclosure

Single self-contained file with well-organized section headers (Core workflow, Defaults, Dataset Viewer, Querying, Creating/Uploading); the inlined endpoint reference and SQL/export sections are reasonable for a skill of this size, with only minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

83%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 specific, action-enumerating description tied to a well-defined niche, with strong capability coverage and low conflict risk. The main gap is the absence of sharper, user-facing trigger phrasing for the 'when' clause.

Suggestions

Add an explicit 'Use when the user mentions Hugging Face datasets, dataset rows, parquet exports, or dataset statistics' clause to lift completeness and trigger_term_quality.

Include natural synonyms and extensions (e.g. 'datasets, .parquet, hf://') so trigger terms match how users actually phrase requests.

DimensionReasoningScore

Specificity

Lists six concrete actions ('fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics'), giving comprehensive coverage of the API's capability surface.

5 / 5

Completeness

The 'what' is explicit via the enumerated actions and 'Use this skill for ... workflows' provides equivalent trigger guidance, but the 'when' is not sharpened with concrete user-mention triggers, so it stops short of a 5.

4 / 5

Trigger Term Quality

Domain terms like 'Hugging Face Dataset Viewer', 'paginate rows', 'parquet', 'filters' are natural for this audience, but common synonyms and concrete file/extension triggers (e.g. '.parquet', 'hf://') are missing, so it is not a 5.

4 / 5

Distinctiveness Conflict Risk

Scoped to the Hugging Face Dataset Viewer API, a clear niche with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

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
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.