validate-data

QA an analysis before sharing -- methodology, accuracy, and bias checks. Use when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually supported by the data.

Quality

86%

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

77%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.

Highly actionable and clearly sequenced, with concrete checks, examples, and a well-defined output format. The main weaknesses are over-explanation of well-known analytical concepts and a monolithic single-file structure that inlines reference material instead of splitting it into bundle files.

Suggestions

Move the Common Data Analysis Pitfalls catalog and Documentation Standards (analysis template, code docstring example, version control notes) into references/ files (e.g., references/pitfalls.md, references/documentation.md), keeping only the pitfall names and a one-line pointer in SKILL.md.

Trim the pitfall entries to name + detection/prevention check — drop 'The problem' explanations and worked arithmetic for concepts Claude already knows like survivorship bias, timezone mismatches, and average of averages.

Fix or remove the dangling [CONNECTORS.md](../../CONNECTORS.md) link, which does not resolve from the skill's location.

Dimension	Reasoning	Score
Conciseness	The workflow and checklists are tight, but the pitfall catalog spends prose explaining concepts Claude already knows (survivorship bias, timezone mismatches, average-of-averages arithmetic) and ~70 lines of documentation templates/docstring examples pad the file.	3 / 5
Actionability	Fully concrete throughout: runnable SQL for join-explosion detection, a worked weighted-average example, a sanity-check table, specific red flags (e.g., rates at exactly 0% or 100%), and a copy-paste output format template.	5 / 5
Workflow Clarity	Eight clearly sequenced steps with an explicit pre-delivery checklist, a defined 3-level confidence gate, and a stated feedback loop ('If the validation finds issues, fix them and re-validate').	5 / 5
Progressive Disclosure	No bundle files exist, yet ~380 lines inlines reference-grade material (the pitfall catalog, documentation standards/templates) that belongs in separate files, and the CONNECTORS.md link does not resolve. Section organization itself is good.	3 / 5
	Total	16 / 20 Passed

Description

92%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.

A strong description that states concrete capabilities and gives an explicit, multi-scenario 'Use when' clause. It is specific, complete, and clearly distinct from sibling skills; the only gap is a few missing natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — QA an analysis, methodology/accuracy/bias checks, spot-checking calculations and aggregation logic, verifying SQL query results, assessing whether conclusions are supported — with comprehensive coverage of the validation domain.	5 / 5
Completeness	Explicitly answers both 'what' (QA an analysis: methodology, accuracy, and bias checks) and 'when' via a concrete 'Use when...' clause with four distinct trigger scenarios.	5 / 5
Trigger Term Quality	Natural user phrases like 'reviewing an analysis before a stakeholder presentation', 'spot-checking calculations', and 'SQL query's results look right' are present, but common variations such as 'sanity check my numbers', 'double-check my results', or 'validate before sending' are missing.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — pre-delivery validation of data analyses — with distinct triggers (stakeholder presentation, SQL result verification) that minimally overlap with general data-analysis or charting skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: anthropics/knowledge-work-plugins
Path: data/skills/validate-data/SKILL.md
Commit: 8444efc

Reviewed: 6 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.