Name: warehouse-init
Rating: 79.2 (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

70%

Does it follow best practices?

Impact

96%

1.60x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/warehouse-init/SKILL.md

Quality

Content

63%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 well-sequenced, largely actionable process with genuinely non-obvious domain detail, but it is a monolithic ~340-line document with notable padding and no progressive disclosure into reference files. Validation checkpoints for the risky refresh/regeneration path are the biggest gap.

Suggestions

Move the output-format template, 'Cache Staleness & Schema Drift' guidance, and Example Session into reference files (e.g. references/output-format.md, references/cache.md) and link them from SKILL.md to cut the main body roughly in half.

Add validation checkpoints: after Step 5 verify each subagent returned a structured summary before merging, and after '--refresh' confirm user HTML comments and Quick Reference entries were preserved before overwriting warehouse.md.

Delete the duplicated 'If yes: Append the Quick Reference section…' line (SKILL.md:239) and the empty 'Relationships' placeholder section, and standardize CLI paths (use 'scripts/cli.py' consistently as in Step 3).

Dimension	Reasoning	Score
Conciseness	Mostly operational detail Claude would not know (dbt/gusty patterns, layer hierarchy, refresh preservation), but there is real padding: Step 8's instructions are duplicated ('If yes: Append the Quick Reference section' restates the numbered instructions), the 'Relationships' section is an empty placeholder, and the Cache Staleness/Stale Cache sections plus the full Example Session restate earlier content. Fits 'mostly efficient but could be tightened', not the 'minor trims' of level 4.	3 / 5
Actionability	Concrete, mostly executable guidance: real INFORMATION_SCHEMA SQL, specific CLI commands, subagent prompts, and output paths. Minor gaps — command paths are inconsistent ('scripts/cli.py' in Steps 3/7 but bare 'cli.py' at line 101 and 203) and Step 4's SQL is a placeholder template. Not 5 because these aren't fully copy-paste ready.	4 / 5
Workflow Clarity	Eight clearly sequenced steps with explicit parallelization instructions and refresh-preservation rules, but no validation checkpoints — nothing verifies subagent results were merged, the file was written, or user edits survived '--refresh' (a regeneration that could clobber user content). Fits 'clear sequence with most checkpoints; minor validation gaps'.	4 / 5
Progressive Disclosure	No bundle files exist; everything is inlined in one ~340-line SKILL.md. Section structure is good, but content that clearly belongs in separate reference files — the full output-format template, cache staleness/drift guidance, codebase-pattern table, and example session — is inline. Fits 'some structure but could be better organized'.	3 / 5
	Total	14 / 20 Passed

Description

76%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: concrete capabilities, explicit run-frequency guidance, and a clear 'Use when' clause with both a slash-command and a natural-language trigger. Main weakness is limited natural-keyword coverage beyond the command name.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Generates .astro/warehouse.md with all table metadata', 'Run once per project, refresh when schema changes' — with minor coverage gaps (no mention of codebase enrichment or categorical value discovery). Not a 5 because the action list is not comprehensive.	4 / 5
Completeness	Explicitly answers both what ('Initialize warehouse schema discovery. Generates .astro/warehouse.md with all table metadata') and when ('Use when user says "/astronomer-data:warehouse-init" or asks to set up data discovery') with concrete trigger phrases. Matches the top anchor.	5 / 5
Trigger Term Quality	Relevant keywords exist ('warehouse', 'schema', 'discovery', the slash command) but common natural variations users would say — 'warehouse setup', 'table metadata', 'schema docs' — are missing. Above 2 because the present terms are domain-relevant, not generic.	3 / 5
Distinctiveness Conflict Risk	Clear niche (warehouse schema initialization for the astronomer-data suite) with a distinct slash-command trigger, but the generic 'set up data discovery' phrase creates minor overlap risk with closely related data skills. Not 5 because of that overlap.	4 / 5
	Total	16 / 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
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	15 / 16 Passed

Repository: astronomer/agents
Path: skills/warehouse-init/SKILL.md
Commit: 1ec1a1f

Reviewed: 2 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.