data-validation-first

Use this skill before any data analysis, transformation, or modeling. Always inspect and validate the data before drawing conclusions or writing transformations.

Quality

72%

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 ./memory_data/skills/data-validation-first/SKILL.md

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean and highly actionable with executable pandas checks and a concrete anti-pattern, and it is appropriately organized for a simple single-purpose skill. The main gap is workflow clarity: the key questions act as checks but lack explicit validation feedback loops or recovery steps.

Suggestions

Add a short feedback loop, e.g. 'If a check fails: diagnose with df[df.key.isnull()], fix (fillna/drop/astype), then re-run the check before proceeding.'

Number the inspection and validation steps to make the before-analysis sequence explicit.

Briefly state the expected outcome of each key question so Claude knows when validation passes.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of concepts Claude already knows; terse inline comments and a focused key-questions list mean every token earns its place.	3 / 3
Actionability	It provides fully executable, copy-paste-ready pandas commands (df.shape, df.dtypes, df.isnull().sum(), df.describe(), df.head()) plus concrete checks and a named anti-pattern.	3 / 3
Workflow Clarity	An inspection checklist and key questions are present, but the questions raise issues without sequencing explicit recovery actions or a validate-then-fix feedback loop, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	The skill is under 50 lines, single-purpose, needs no external references, and is organized into a code block, key questions, and an anti-pattern section.	3 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 answers both what and when with an explicit trigger clause, but its actions are generic and the second-person voice ('Use this skill') incurs a specificity penalty. Trigger terms cover the basics but miss common variations, and the niche overlaps with general data-analysis skills.

Suggestions

Rewrite in third person ('Inspects and validates data before analysis') to avoid the second-person voice penalty on specificity.

List concrete actions instead of generic verbs, e.g. 'check dtypes, nulls, duplicates, and row counts before transforming or modeling data'.

Add common trigger variations users would say, such as 'EDA', 'data cleaning', or 'data prep'.

Dimension	Reasoning	Score
Specificity	Names the data-analysis domain and a few actions ('inspect and validate the data', 'writing transformations') but they are generic rather than multiple concrete actions; the second-person imperative 'Use this skill' triggers the voice penalty, reducing the base 2 to 1.	1 / 3
Completeness	It explicitly states both what ('inspect and validate the data before drawing conclusions or writing transformations') and when ('Use this skill before any data analysis, transformation, or modeling'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	'data analysis, transformation, or modeling' are natural user terms, but common variations like 'EDA', 'data cleaning', or 'data prep' are missing, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The 'before any data analysis' prerequisite framing is a recognizable niche, but the underlying inspect/validate capability overlaps broadly with general data-analysis skills, so it could still trigger for the wrong skill.	2 / 3
	Total	8 / 12 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: aiming-lab/MetaClaw
Path: memory_data/skills/data-validation-first/SKILL.md
Commit: 922caf3

Reviewed: 9 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.