analysis-artifacts

Generate reproducible analysis artifacts — SQL queries, Python visualizations, and summary tables — as you work through a BigQuery data analysis. Use when asked to conduct a deep dive, exploratory analysis, or investigation that goes beyond a simple data lookup.

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 ./.agents/skills/analysis-artifacts/SKILL.md

Quality

Content

61%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 skill lays out a clear, well-organized analysis workflow with concrete artifact conventions, but it lacks executable code templates/examples and explicit validation loops for its batch and overwrite operations, which cap actionability and workflow clarity.

Suggestions

Add a short example SQL artifact (with the required purpose comment block) and a minimal Python viz script snippet so the artifact conventions are copy-paste ready.

Insert an explicit validation checkpoint after generating artifacts — e.g., re-run the query to confirm reproducibility and verify the image/CSV rendered correctly before finalizing, with a fix-and-retry loop.

Provide a brief README skeleton showing the required section order (Problem Statement, TL;DR, Cohorts Definition, step sections, Key Takeaways) so the summarization step is fully actionable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of BigQuery or visualization basics), but the Cohorts Definition bullets are somewhat dense and could be tightened, so 4 not 5.	4 / 5
Actionability	Guidance is concrete on file locations and formats ('.sql file in /assets/queries/', 'save both the script and the output image'), but it provides no example SQL comment-block template, viz script, or README skeleton, leaving key execution details missing.	3 / 5
Workflow Clarity	The six-step sequence is clear and includes a plan-approval checkpoint, but batch artifact creation and the destructive overwrite step (step 5) lack an explicit validate→fix→retry loop, so the destructive/batch cap of 3 applies.	3 / 5
Progressive Disclosure	A single self-contained SKILL.md with clean section headers and a directory-tree example; no nested or buried references, but it is over 50 lines with all content inline, so 4 rather than 5.	4 / 5
	Total	14 / 20 Passed

Description

83%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, well-structured description that clearly states both capability and trigger conditions with concrete artifact types. It sits just below the top anchor on specificity and trigger breadth due to a slightly limited action list and missing synonyms.

Dimension	Reasoning	Score
Specificity	Lists three concrete artifact types ('SQL queries, Python visualizations, and summary tables') for the BigQuery domain — several specific actions, but one short of the comprehensive five-anchor count, so 4 not 5.	4 / 5
Completeness	Explicitly answers both 'what' (generate reproducible SQL/viz/table artifacts during a BigQuery analysis) and 'when' ('Use when asked to conduct a deep dive, exploratory analysis, or investigation that goes beyond a simple data lookup') with concrete triggers, matching the 5-anchor.	5 / 5
Trigger Term Quality	Natural phrases users say appear ('deep dive', 'exploratory analysis', 'investigation'), but common synonyms and an explicit BigQuery/data-warehouse trigger term are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	The BigQuery + reproducible-artifacts framing carves a clear niche, but the broad 'deep dive'/'analysis' triggers could overlap with general analysis skills, so minor overlap risk rather than minimal.	4 / 5
	Total	17 / 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: warpdotdev/oz-skills
Path: .agents/skills/analysis-artifacts/SKILL.md
Commit: 6c08c49

Reviewed: 3 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.