review-sql
Skill730 starsChanged 2 months agoMITView on GitHub
Review a T-SQL file against Erik Darling's coding style guide
2 other projects use a version of this.
Adopted by
Most recently taken up by
- nesnilnehc/ai-cortextheir own version, first seen Oct 25, 2026
- atsushi-green/ds-ai-coding-skillstheir own version, first seen Sep 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- atsushi-green/ds-ai-coding-skills★ 86same name
- nesnilnehc/ai-cortex★ 8same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- darlingdata-releaseSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Read the file at $ARGUMENTS and check for violations of every rule below.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
T-SQL Style Review
Review a T-SQL file against the coding conventions defined in CLAUDE.md. This is a read-only analysis -- do not modify files.
Read the file at $ARGUMENTS and check for violations of every rule below.
Checklist
Keywords & Functions
- All SQL keywords UPPERCASE (SELECT, FROM, WHERE, JOIN, EXECUTE, TRANSACTION, PROCEDURE)
- All SQL functions UPPERCASE (CONVERT, ISNULL, OBJECT_ID, DATEADD, COUNT_BIG)
- Never abbreviated keywords (EXECUTE not EXEC, TRANSACTION not TRAN, PROCEDURE not PROC)
- TOP always has parentheses:
TOP (100)notTOP 100
Data Types
- All data types lowercase (varchar, nvarchar, datetime2, bigint, integer)
- Never abbreviated data types (integer not int)
- Length specs lowercase: nvarchar(max) not nvarchar(MAX)
- sysname used for SQL Server object names, not nvarchar(128)
Formatting
- 4 spaces for indentation, no tabs
- Trailing commas on multi-line column lists
- Column aliases use
column_name = expressionpattern (notexpression AS column_name) - Statements terminated with semicolons
- Block comments
/* */used, not double dash-- - Single quotes for strings, N-prefix for Unicode (N'string')
Query Structure
- Tables always have aliases, using AS keyword:
FROM dbo.table AS t - Columns always qualified with table alias
- Schema prefix on all objects except temp tables
- WHERE conditions with AND aligned:
AND(with spacing) - EXISTS uses
SELECT 1/0pattern - JOINs use ANSI syntax with ON conditions indented
- Subqueries never one-liners
Best Practices
- COUNT_BIG() used instead of COUNT()
- ROWCOUNT_BIG() used instead of @@ROWCOUNT
- CONVERT used instead of CAST (except TRY_CAST)
- IS NULL / IS NOT NULL for null comparisons, never = NULL
- No MERGE statements (unless absolutely necessary)
- Cursor variables instead of normal cursors
- Temp tables preferred over table variables for relational use
- Temp tables not explicitly dropped at end of procedures
- Date literals in yyyymmdd format
- TABLOCK hint on temp table inserts
Procedure Structure (if applicable)
- SET NOCOUNT, XACT_ABORT ON at the top
- Parameter validation before main logic
- Help section for @help = 1
- BEGIN TRY / BEGIN CATCH with proper ROLLBACK pattern
- No additional dependency objects (all logic self-contained)
Output Format
Present findings as:
- Summary: Overall compliance rating (e.g., "12 issues found across 3 categories")
- Issues: List each violation with:
- Line number(s)
- What's wrong
- What it should be
- Good Practices: Note anything done particularly well
Group issues by category (Keywords, Data Types, Formatting, Structure, Best Practices). Order by severity within each group.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

