data-quality

Quality dimensions quick reference and remediation decision tree for tabular data assessment

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skills/data-quality/SKILL.md

Quality

Content

90%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 a lean, highly actionable quick-reference card with concrete qsv commands and a well-sequenced fix-ordering workflow. Its main gap is the lack of an explicit post-fix verification feedback loop and the absence of any bundle-file references for the extensive advanced-stats material.

Suggestions

Add an explicit verification step after the Fix Ordering sequence (e.g., re-run `stats --cardinality` or `validate` and confirm the flagged issue is resolved before proceeding).

Consider moving the Advanced Stats distribution-metrics table into a separate reference file (e.g., references/advanced-stats.md) linked from the main body to improve progressive disclosure.

Clarify the handoff to /data-profile at the top with a one-line statement of when each is preferred.

Dimension	Reasoning	Score
Conciseness	Dense reference tables with no padding or over-explanation of concepts Claude already knows; every row maps a concrete check or cache column to a quality signal, so each token earns its place.	5 / 5
Actionability	Provides concrete, executable qsv commands throughout (stats, validate schema.json, fixlengths, input, safenames, sqlp with TRIM(), dedup, joinp --left-anti) with a clear problem-to-command mapping covering common cases.	5 / 5
Workflow Clarity	The Fix Ordering section gives a clear numbered sequence (input -> safenames -> fixlengths -> TRIM -> dedup -> validate) with rationale, and the decision tree's "When to Skip" columns act as pre-check checkpoints, but there is no explicit re-verify feedback loop after destructive fixes.	4 / 5
Progressive Disclosure	Well-organized into clear sections with headers and tables and no nested references, but the content is entirely inline (no bundle files present) and the lengthy Advanced Stats table could arguably live in a separate reference file.	4 / 5
	Total	18 / 20 Passed

Description

53%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 clearly states what the skill provides but omits any "Use when..." trigger guidance, which caps its completeness and trigger quality. It is specific to a clear niche with only minor overlap risk.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g., "Use when assessing data quality, diagnosing quality issues, or choosing remediation commands for tabular data."

Include natural user phrasings such as "data quality", "clean data", and "validate data" alongside the technical terms.

Mention the underlying tool (qsv) to sharpen distinctiveness from general data-skills.

Dimension	Reasoning	Score
Specificity	Names the domain concretely ("tabular data assessment") and two deliverables ("quick reference", "remediation decision tree"), but these are artifacts rather than concrete actions, and coverage is not comprehensive.	3 / 5
Completeness	The "what" is clear (quality dimensions quick reference + remediation decision tree), but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Has relevant terms like "quality dimensions", "tabular data", and "remediation", but misses common natural variations users would say such as "data quality", "clean data", or "validate data".	3 / 5
Distinctiveness Conflict Risk	The niche (tabular data quality assessment + remediation) is fairly distinct; minor overlap risk exists with the related /data-profile skill and other data skills, but triggers are reasonably specific.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dathere/qsv
Path: .claude/skills/skills/data-quality/SKILL.md
Commit: a46782a

Reviewed: about 3 hours 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.