analyzing-data

Queries the data warehouse with SQL and answers business questions about data. Use when answering anything that needs warehouse data - counts, metrics, trends, aggregations, joins across tables, data lookups, or ad-hoc SQL analysis (for example "who uses X", "how many Y", "show me Z", "find customers", "what is the count").

Quality

91%

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

Quality

Content

86%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.

A tight, highly actionable CLI-oriented skill body with excellent token efficiency and a well-sequenced caching workflow. Its main defects are the two missing reference/ files the body links to, and the absence of an explicit error-recovery checkpoint in the workflow.

Suggestions

Add the missing reference/discovery-warehouse.md and reference/common-patterns.md files (or remove/inline the links) — both are cited in the workflow and References section but do not exist in the bundle.

Add an explicit error-recovery step to the workflow, e.g. 'If a query times out, re-run with exec "..." -t 600; if it errors, check the warehouse size with warehouse list before retrying'.

State when to use `table cache` in the workflow (e.g. after discovering a schema in step 3) so the table-schema cache commands in the CLI reference are anchored to a step.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense: a 6-step workflow, a kernel-functions table, and terse CLI command listings with no padding and no explanations of concepts Claude already knows (e.g. 'the kernel self-terminates after 2h idle' and fail-fast semantics of run_sql_many are genuinely non-obvious facts). Every section earns its tokens.	5 / 5
Actionability	Every instruction is a copy-paste-ready `uv run scripts/cli.py ...` command with concrete flags (-k <KEY_COL>, -t 600, --stale-only), and the kernel API is given as an executable snippet ("dfs = run_sql_many(['SELECT ...', 'SELECT ...']); print(dfs[0])"). The scripts/ bundle (cli.py, cache.py, etc.) actually exists, so the commands are real, not pseudocode.	5 / 5
Workflow Clarity	The 6-step workflow is clearly sequenced with conditional branching ('If a pattern exists, follow its strategy', 'If cache misses') and a built-in feedback loop via `pattern record <name> --success/--failure`. It falls short of a 5 because there is no explicit checkpoint for handling a failed or timed-out query (e.g. retry with a higher -t, inspect the error) — only the timeout mechanics are described, not the recovery step.	4 / 5
Progressive Disclosure	Structure is good — a References section clearly signals two one-level-deep files ('discovery-warehouse.md — Large table handling...', 'common-patterns.md — SQL templates...'), and SQL templates/discovery details are appropriately deferred. However, neither referenced file exists in the bundle (no reference/ or references/ directory), so the disclosure navigation is broken and a following agent hits dead links; this is worse than the 'minor organization gaps' of a 4.	3 / 5
	Total	17 / 20 Passed

Description

96%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 pairs a concrete capability statement with an explicit 'Use when...' trigger clause containing natural example questions. Its only weakness is mild overlap risk with general SQL/data-analysis skills on generic counting/lookup phrasings.

Dimension	Reasoning	Score
Specificity	'Queries the data warehouse with SQL and answers business questions about data' plus 'counts, metrics, trends, aggregations, joins across tables, data lookups, or ad-hoc SQL analysis' lists multiple concrete, comprehensive actions in third person; no vague filler. Not a 4 because coverage of the domain's operations is comprehensive rather than having minor gaps.	5 / 5
Completeness	Both halves are explicit: what ('Queries the data warehouse with SQL and answers business questions about data') and when ('Use when answering anything that needs warehouse data - ...') with concrete trigger phrases. This matches the 5 anchor's 'clearly and explicitly answers both what AND when with concrete trigger phrases'.	5 / 5
Trigger Term Quality	Natural user phrasings are quoted directly: '"who uses X", "how many Y", "show me Z", "find customers", "what is the count"' — exactly what a user would say — alongside domain keywords (counts, metrics, trends, aggregations, joins, data lookups). Not a 4 because common variations are explicitly covered via the example questions.	5 / 5
Distinctiveness Conflict Risk	The 'data warehouse' framing plus SQL/joins triggers give it a clear niche, but 'answers business questions about data' and examples like 'what is the count'/'show me Z' overlap with generic SQL/database or spreadsheet-analysis skills a user might invoke instead. Not a 5 because a user asking 'what's the count of X' could reasonably intend a local-data or SQL-client skill.	4 / 5
	Total	19 / 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: astronomer/agents
Path: skills/analyzing-data/SKILL.md
Commit: 1ec1a1f

Reviewed: 1 day 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.