portaljs-check-data-quality

Audit a local or remote tabular file (CSV/TSV) for common data quality issues — schema, nulls, types, duplicates. Read-only. Use when a dataset needs a quality check before publishing, or a showcase renders wrong (blank cells, garbled numbers, an unsortable date column) and the cause needs isolating.

Quality

87%

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

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, mostly lean skill body with a clear sequenced workflow, validation checkpoint, and concrete examples. Gaps are minor: a non-bundled script reference in Example 3, the executable workflow living externally, and mild repetition of the read-only guarantee.

Suggestions

Remove the dangling 'scripts/check-data-quality.sh' reference in Example 3 (the scripts/ directory is not bundled) or add the script to the bundle.

State the read-only guarantee once (in the Overview or step 7) instead of repeating it across the description, Overview, and Instructions.

Inline or mirror the essential snippet of the canonical workflow so the skill remains executable when the external GitHub command file is unreachable.

Dimension	Reasoning	Score
Conciseness	Lean and task-focused with useful tables and examples, but the read-only guarantee is restated three times (description, Overview, step 7) — minor padding that could be trimmed.	4 / 5
Actionability	Provides concrete CLI invocations, a report JSON example, and error shapes; however the embedded audit script lives in an external GitHub file and Example 3 references 'scripts/check-data-quality.sh' which is not in the bundle.	4 / 5
Workflow Clarity	Seven clearly sequenced steps with an explicit validation/stop checkpoint in step 3 ('stop and surface the error JSON as-is — do not guess a fix'); the read-only nature avoids the destructive-cap, though full feedback loops live in the external canonical file.	4 / 5
Progressive Disclosure	Clear overview with a real one-level-deep reference (references/reference.md) and well-signaled sections; the dangling 'scripts/check-data-quality.sh' reference in Example 3 is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: concrete actions, explicit 'Use when' triggers with real symptom phrases, file extensions, and third-person voice. It answers what and when unambiguously with no fluff.

Dimension	Reasoning	Score
Specificity	Names the domain (tabular CSV/TSV audit) and lists four concrete checks — 'schema, nulls, types, duplicates' — matching the comprehensive multi-action anchor.	5 / 5
Completeness	Explicitly states what it does ('Audit ... for common data quality issues') and when to use it ('Use when a dataset needs a quality check before publishing, or a showcase renders wrong ...'), both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes file extensions (CSV/TSV), natural synonyms ('data quality', 'dataset', 'quality check'), and concrete symptom phrases ('blank cells, garbled numbers, an unsortable date column') users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (read-only tabular quality audit for PortalJS) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	20 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: datopian/portaljs
Path: skills/portaljs-check-data-quality/SKILL.md
Commit: ebfd391

Reviewed: 7 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.