data-wizard

Data processing expert - ETL, transformation, visualization

Quality

66%

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 ./skills/data-wizard/SKILL.md

Quality

Content

68%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, code-first overview with good sectioning and mostly executable examples, but it presents a batch/destructive ETL workflow without integrating validation checkpoints or feedback loops. Tightening the workflow guidance is the main improvement area.

Suggestions

Add an explicit pipeline workflow with validation checkpoints: extract → validate → transform → re-validate → load, including a fix-and-retry loop on validation failure.

Make the data-quality validation actionable in the workflow (raise/stop on threshold breaches instead of only printing warnings) before destructive loads like if_exists='replace'.

Remove the redundant 'Expertise' bullet list and the closing motivational quote to trim tokens, or fold the expertise items into the description.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code with minimal prose and assumes Claude's competence; only the redundant 'Expertise' bullet list and the closing 'Data is the new oil' quote are padding that could be trimmed.	4 / 5
Actionability	Concrete, runnable Python is provided for extract/transform/load, validation, and dashboarding with a usage example, but hardcoded column names and 'SELECT * FROM table' leave minor gaps preventing fully copy-paste-ready generality.	4 / 5
Workflow Clarity	The extract→transform→load sequence is shown, but the ETL workflow performs destructive/batch operations (if_exists='replace', file writes) with no integrated validation checkpoints or fix→retry feedback loop, so workflow clarity is capped at 3 per the rubric guideline.	3 / 5
Progressive Disclosure	Content is organized into clear, well-labeled sections with no nested references; it is a self-contained overview that does not need external files, though everything is inlined with no navigation to deeper material.	4 / 5
	Total	15 / 20 Passed

Description

50%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 concise and names the right domain, but it reads as a capability label rather than a triggering sentence: it lacks concrete actions and any explicit 'when to use' guidance. It sits at the midpoint across all dimensions.

Suggestions

Rewrite as a triggering sentence with concrete verbs, e.g. 'Builds and runs ETL pipelines, transforms and cleans datasets, and generates data visualizations.'

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user needs to build data pipelines, clean or transform datasets, or create charts and dashboards.'

Include common synonyms and file extensions (CSV, JSON, Parquet, pandas) to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Data processing expert') plus three capability areas ('ETL, transformation, visualization'), but these are generic categories rather than the concrete actions (e.g. extract/fill/convert) the higher anchors require.	3 / 5
Completeness	It states clearly what the skill does, but provides no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Terms like 'ETL', 'transformation', and 'visualization' are reasonably natural, but common variations users might say ('clean my data', 'build a pipeline', 'make charts') and any file extensions or synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	'Data processing' is broad and ETL/visualization overlap with general data-engineering and analytics skills, so it could still trigger for the wrong related skill.	3 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TurnaboutHero/oh-my-antigravity
Path: skills/data-wizard/SKILL.md
Commit: f73e1ff

Reviewed: 15 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.