data-wizard
Data processing expert - ETL, transformation, visualization
55
Quality
39%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/data-wizard/SKILL.mdQuality
Discovery
14%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague and buzzword-heavy to be useful for skill selection. It lacks concrete actions, explicit trigger conditions, and distinctive scope. A user asking to 'create a bar chart from my CSV' or 'clean up this JSON file' might not trigger this skill, while it might incorrectly trigger for unrelated data tasks.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios (e.g., 'Use when user needs to clean, transform, or pipeline data between formats like CSV, JSON, or databases')
Replace abstract terms with concrete actions (e.g., 'Cleans messy data, converts between CSV/JSON/Excel formats, builds data pipelines, creates charts and dashboards')
Add natural user terms like 'clean data', 'convert files', 'charts', 'graphs', 'CSV', 'spreadsheet', 'database' to improve trigger matching
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Uses vague, abstract terms like 'ETL', 'transformation', and 'visualization' without describing concrete actions. Does not specify what data formats, what transformations, or what visualizations. | 1 / 3 |
Completeness | Only vaguely addresses 'what' with buzzwords and completely lacks any 'when' guidance. No 'Use when...' clause or explicit trigger conditions. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords ('ETL', 'transformation', 'visualization', 'data processing') but 'ETL' is technical jargon and missing common user terms like 'clean data', 'convert', 'charts', 'graphs', 'CSV', 'JSON'. | 2 / 3 |
Distinctiveness Conflict Risk | Extremely generic - 'data processing' and 'visualization' could overlap with dozens of other skills (Excel analysis, charting, database work, reporting, etc.). No clear niche defined. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, executable code examples for data processing tasks with good coverage of ETL, validation, and visualization. However, it includes unnecessary persona framing, lacks explicit error handling workflows for batch operations, and could benefit from better content organization across multiple files for the detailed implementations.
Suggestions
Remove the persona introduction ('You are Data Wizard') and closing quote - these add no value for Claude
Add explicit error recovery steps to the ETL pipeline (e.g., 'If transform fails: log error, skip row or retry, continue processing')
Consider splitting detailed implementations (validation functions, visualization code) into referenced files like VALIDATION.md and VISUALIZATION.md
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing ('You are Data Wizard', the closing quote) and the code examples are comprehensive but could be tighter. The persona introduction adds no value for Claude. | 2 / 3 |
Actionability | Provides fully executable Python code with complete class implementations, concrete examples for ETL, validation, and visualization. Code is copy-paste ready with clear usage patterns. | 3 / 3 |
Workflow Clarity | The ETL pipeline shows a clear sequence (extract→transform→load) with inline validation (assert statement), but lacks explicit error recovery steps or feedback loops for handling failures in batch data operations. | 2 / 3 |
Progressive Disclosure | Content is organized into logical sections (ETL, Quality Checks, Visualization) but everything is inline in one file. For a skill of this size (~100 lines of code), the validation and visualization sections could be referenced as separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- TurnaboutHero/oh-my-antigravity
- Commit
fab464f
- 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.