Name: warehouse-init
Rating: 77.60000000000001 (1 reviews)
Author: astronomer

warehouse-init

Initialize warehouse schema discovery. Generates .astro/warehouse.md with all table metadata for instant lookups. Run once per project, refresh when schema changes. Use when user says "/astronomer-data:warehouse-init" or asks to set up data discovery.

1.60x

Quality

—

Does it follow best practices?

Impact

96%

1.60x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Quality

Content

50%

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

A well-structured, mostly actionable multi-step discovery skill with clear sequencing and real SQL/CLI examples, but it is a long monolithic file with some pseudocode-style orchestration and no validation feedback loops or progressive disclosure into separate reference files.

Suggestions

Add an explicit validation checkpoint after parallel discovery (e.g., verify warehouse.md was written and that each database returned non-empty schemas before declaring success) to support a validate-fix-retry loop.

Move the output-format template, refresh/cache-staleness details, and the 'Example Session' into separate reference files under references/ and link to them from the main body to enable progressive disclosure.

Replace the Step 4 pseudocode query ('FROM table', 'column_name') and the 'For each database ... Task()' pseudo-syntax with concrete, runnable examples or clearly mark the placeholders as intentional parameterization.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concepts-Claude-already-knows padding, but the long illustrative 'Example Session' and repeated 'Scripts are relative to ../analyzing-data/' reminders across several steps could be tightened.	2 / 3
Actionability	Real SQL queries and CLI commands are present, but core orchestration is given as templated pseudo-syntax (the Task() blocks and Step 4's 'FROM table' / 'column_name' placeholders) that is not copy-paste executable, fitting the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	Steps 1-8 are clearly sequenced, but there are no explicit validation checkpoints or validate-fix-retry feedback loops for this batch parallel-discovery operation, which caps the score at 2.	2 / 3
Progressive Disclosure	Well-organized with clear headings (not a wall of text), but it is a single ~340-line monolithic file with no local bundle references; content like the output-format template, refresh/cache details, and example session could be split into separate reference files.	2 / 3
	Total	8 / 12 Passed

Description

85%

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, third-person description that states concrete capabilities and gives explicit 'Use when' triggers tied to a specific command. Trigger-term breadth is the only real weakness, as it leans on the slash command and a couple of phrases rather than covering the natural range of ways a user might request this.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Initialize warehouse schema discovery', 'Generates .astro/warehouse.md with all table metadata for instant lookups') with a specific artifact, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers what ('Generates .astro/warehouse.md with all table metadata') and when ('Use when user says ... or asks to set up data discovery', 'Run once per project, refresh when schema changes'), with explicit triggers.	3 / 3
Trigger Term Quality	Includes the explicit '/astronomer-data:warehouse-init' command and 'set up data discovery' / 'warehouse schema discovery', but the set of natural phrasings is narrow and missing common variations like 'data warehouse' or 'table metadata'.	2 / 3
Distinctiveness Conflict Risk	A clear niche (warehouse schema discovery producing .astro/warehouse.md) with a distinct slash-command trigger, making conflict with unrelated skills unlikely.	3 / 3
	Total	11 / 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
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	15 / 16 Passed

Repository: astronomer/agents
Commit: 8827e93

Reviewed: 8 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.