CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

1.60x
Quality

56%

Does it follow best practices?

Impact

96%

1.60x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/warehouse-init/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

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-structured description that clearly communicates what the skill does (generates warehouse metadata files) and when to use it (specific slash command or data discovery setup requests). Its main weakness is that the trigger terms could be broader to capture more natural user phrasings beyond the slash command, such as 'explore tables', 'database schema', or 'what data is available'.

Suggestions

Add more natural trigger terms like 'explore tables', 'database schema', 'list my tables', 'what data is available' to improve discoverability beyond the slash command.

DimensionReasoningScore

Specificity

Lists specific concrete actions: 'Initialize warehouse schema discovery', 'Generates .astro/warehouse.md with all table metadata for instant lookups'. Also specifies when to run ('once per project, refresh when schema changes').

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'), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Includes the slash command trigger '/astronomer-data:warehouse-init' and terms like 'schema discovery', 'data discovery', 'warehouse', and 'table metadata'. However, it misses natural user phrases like 'explore my database', 'list tables', 'what tables do I have', or 'schema' alone.

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

27%

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

This skill covers a complex multi-step warehouse discovery process comprehensively but suffers from significant verbosity — the full output template, example session, and cache management sections bloat the file well beyond what's needed. Actionability is moderate since core commands exist but subagent orchestration is pseudocode-like, and the lack of validation checkpoints in a multi-step process involving external warehouse queries is a notable gap. The content would benefit greatly from splitting into a concise overview with references to detailed sub-files.

Suggestions

Split the output format template, example session, cache management, and codebase patterns into separate reference files (e.g., OUTPUT_FORMAT.md, CACHE.md) and link from the main skill with one-line descriptions.

Add explicit validation checkpoints after Steps 3 and 6: verify SQL queries returned results, verify warehouse.md was written and contains expected sections.

Remove the 'Signs of Stale Cache' list and 'Codebase Patterns Recognized' table — these are reference material that Claude can infer or that belong in a separate file.

Make the subagent Task() calls more concrete by specifying exact tool invocation syntax or linking to a subagent usage reference, rather than illustrative pseudocode.

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~250+ lines. It includes extensive output format templates, a full example session transcript, detailed explanations of cache staleness signs, and sections like 'Codebase Patterns Recognized' that could be much more compact. Many sections explain things Claude can infer (e.g., 'Signs of Stale Cache' listing obvious indicators like 'queries fail with table not found errors').

1 / 3

Actionability

The skill provides concrete bash commands and SQL queries, but relies heavily on pseudocode-like Task() subagent calls that aren't directly executable. The CLI commands reference relative paths that require context switching ('cd to ../analyzing-data/'), and the subagent prompts are illustrative rather than copy-paste ready. Some steps like 'Merge Results' are described abstractly rather than with concrete commands.

2 / 3

Workflow Clarity

The 8-step process is clearly sequenced and logically ordered, with parallel execution noted. However, there are no explicit validation checkpoints — no step verifies that warehouse.md was generated correctly, no validation that SQL queries succeeded, and no error handling for common failures like connection issues or permission errors. The refresh behavior section describes preservation logic but lacks a verify step.

2 / 3

Progressive Disclosure

The entire skill is a monolithic wall of content with no references to external files despite being very long. The output format template, example session, cache management details, refresh behavior, and codebase patterns could all be split into separate reference files. No bundle files are provided, and no external references are used, resulting in everything being inlined in one massive document.

1 / 3

Total

6

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
astronomer/agents
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.