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.
68
60%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/warehouse-init/SKILL.mdQuality
Discovery
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.
This is a well-crafted description that clearly communicates what the skill does (generates warehouse metadata files), when to use it (slash command or data discovery setup), and its lifecycle (run once, refresh on schema changes). The main weakness is limited natural language trigger terms—users asking about exploring database schemas or listing tables might not trigger this skill.
Suggestions
Add more natural trigger terms users might say, such as 'explore database schema', 'list tables', 'catalog tables', or 'discover data warehouse structure'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Initialize warehouse schema discovery', 'Generates .astro/warehouse.md with all table metadata for instant lookups'. Describes what is produced and its purpose clearly. | 3 / 3 |
Completeness | Clearly answers both what ('Generates .astro/warehouse.md with all table metadata for instant lookups') and when ('Use when user says "/astronomer-data:warehouse-init" or asks to set up data discovery', plus 'Run once per project, refresh when schema changes'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'warehouse', 'schema', 'data discovery', and the slash command trigger '/astronomer-data:warehouse-init'. However, it misses natural variations users might say like 'database tables', 'catalog', 'explore schema', or 'list tables'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a specific slash command trigger, a unique output artifact (.astro/warehouse.md), and a clear niche around warehouse schema discovery. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive warehouse schema discovery workflow with clear steps and useful output templates, but suffers significantly from verbosity. At its current length, it consumes excessive context window space with explanatory content, repeated information, and sections that could be externalized. The workflow would benefit from validation checkpoints and tighter prose that trusts Claude's ability to fill in gaps.
Suggestions
Cut content by ~50%: remove the 'Cache Staleness & Schema Drift' signs/indicators section, 'Codebase Patterns Recognized' table, and the lengthy example session — Claude can generate appropriate user-facing output without a full transcript example.
Move the output format template and refresh behavior details into a separate reference file (e.g., WAREHOUSE_FORMAT.md) and link to it from the main skill.
Add explicit validation checkpoints: after Step 3 verify all databases returned results, after Step 6 verify the file was written and is parseable, and include error recovery guidance for common failures (e.g., permission denied, empty database).
Consolidate the repeated script path reminders ('Scripts are relative to ../analyzing-data/') into a single note at the top rather than repeating in multiple steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It over-explains concepts Claude can infer (e.g., what schema discovery does, signs of stale cache, what dbt models are), includes lengthy output format templates, and repeats information (e.g., script paths mentioned multiple times, the example session largely restates the process). The 'Cache Staleness & Schema Drift' and 'Codebase Patterns Recognized' sections add significant bulk with limited actionable value. | 1 / 3 |
Actionability | The skill provides concrete CLI commands and SQL queries, but much of the guidance is pseudocode-like (e.g., the Task() subagent calls are illustrative rather than executable, the merge step is described abstractly). The output format template is helpful but the actual execution steps mix concrete commands with vague instructions like 'Combine warehouse metadata + codebase context'. | 2 / 3 |
Workflow Clarity | The 8-step process is clearly sequenced and logically ordered, but lacks explicit validation checkpoints. There's no verification that warehouse.md was generated correctly, no error handling for failed SQL queries or inaccessible databases, and no feedback loop if discovery fails partway through. The refresh behavior section describes preservation logic but doesn't include validation steps. | 2 / 3 |
Progressive Disclosure | The skill references external scripts in `../analyzing-data/scripts/` appropriately, but the main file itself is monolithic with too much inline content. The output format template, example session, cache staleness section, and codebase patterns table could all be split into separate reference files. There are no clear links to supplementary documents for advanced topics. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- astronomer/agents
- Commit
166c98a
- Reviewed
Table of Contents
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.