sql-queries

Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations.

Quality

83%

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

65%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.

Highly actionable reference material with executable, dialect-specific snippets and useful debugging guidance, but it is monolithic and padded with SQL knowledge Claude already has. Splitting per-dialect references into bundle files and adding a validated translation/optimization workflow would lift both conciseness and progressive disclosure.

Suggestions

Move the per-dialect reference blocks (PostgreSQL, Snowflake, BigQuery, Redshift, Databricks) into separate reference files (e.g., references/postgresql.md, references/snowflake.md) and keep SKILL.md as an overview with clearly signaled links, improving progressive disclosure and token efficiency.

Trim or remove content Claude already knows — generic window-function syntax, the tutorial-style CTE example, and basic date-part extraction — and keep only dialect quirks and gotchas (e.g., DOW=0 vs DAYOFWEEK=1, no ILIKE in BigQuery, clustering keys vs indexes).

Add a short sequenced workflow for the headline tasks (e.g., dialect translation: identify source/target dialect -> check date/string/JSON mapping in the reference -> run EXPLAIN/dry-run to validate -> compare outputs), with an explicit validation checkpoint before delivering the query.

Dimension	Reasoning	Score
Conciseness	Snippets are prose-lean, but a large share duplicates knowledge Claude already has — generic window-function syntax (ROW_NUMBER/RANK, running totals), a full tutorial-style CTE example, and per-dialect basics like EXTRACT(YEAR FROM created_at); the Snowflake section even repeats VARIANT access twice. Matches 'mostly efficient but includes some unnecessary explanation or could be tightened'; not 4 because the padding is more than minor.	3 / 5
Actionability	Code is executable and copy-paste ready — concrete dialect syntax (DATEADD(day, 7, date_column), DATE_DIFF(end_date, start_date, DAY)), complete cohort/funnel/dedup CTEs, and concrete debugging fixes like NULLIF(denominator, 0). Covers the common cases fully, matching the 5 anchor.	5 / 5
Workflow Clarity	The Error Handling section provides an ordered debugging loop, but there is no sequenced workflow with validation checkpoints for the headline tasks (writing, optimizing, or translating between dialects), and pre-run validation (EXPLAIN/dry-run) appears only as scattered tips. Since database operations are a context where missing feedback loops cap the score, 3 fits; not 4 because checkpoints are absent rather than minor.	3 / 5
Progressive Disclosure	No bundle files exist and ~400 lines of per-dialect API reference are inlined in SKILL.md where per-dialect reference files clearly belong. Section headers are well-organized (better than anchor 2's 'no section headers'), matching anchor 3's 'content that should be separate is inline'; not 4 because nothing is split out and no references exist at all.	3 / 5
	Total	14 / 20 Passed

Description

92%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: third-person, concrete, and specific about both capabilities and trigger conditions, with named dialects giving it a clear niche. The only gap is a few missing natural trigger variations (e.g., 'SQL tuning', 'debugging queries').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Write correct, performant SQL', 'optimizing slow SQL', 'translating between dialects', 'building complex analytical queries with CTEs, window functions, or aggregations' — with comprehensive coverage of the domain, matching the top anchor. It is not 4 because there are no meaningful coverage gaps; it is above the 4 anchor's 'minor gaps in coverage'.	5 / 5
Completeness	Explicitly answers both: the 'what' ('Write correct, performant SQL across all major data warehouse dialects') and a concrete 'Use when...' clause with specific trigger conditions. Matches the 5 anchor; not 4 because the 'when' is explicit and specific rather than 'could be more explicit'.	5 / 5
Trigger Term Quality	Good natural keyword coverage — 'writing queries', 'optimizing slow SQL', 'translating between dialects', 'CTEs', 'window functions' — but misses common variations users would say such as 'SQL tuning', 'migrate queries', or 'debugging a query'. Falls between the 4 and 5 anchors: strong coverage but not comprehensive synonyms.	4 / 5
Distinctiveness Conflict Risk	Clear niche — SQL dialect work — with named dialects (Snowflake, BigQuery, Databricks, PostgreSQL) and trigger terms (CTEs, window functions, optimizing SQL) that are unlikely to fire for unrelated skills. Matches the 5 anchor's 'clear niche with distinct triggers; minimal conflict risk'.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/knowledge-work-plugins
Path: data/skills/sql-queries/SKILL.md
Commit: 8444efc

Reviewed: 6 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.