Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

SQL Review · archive228 | DecimalAI

code reviewby archive228

SQL Review

archive228/sql-review

Source archive228/loopkit ↗License MIT

Review SQL and ORM queries for correctness, safety, and performance before they ship.

SkillScore100Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 22 of 22 test cases with the skill, and 21 of 22 without it.

Without skill95%

With skill100%

Checks it passed that the model alone missed

Includes EXPLAIN analysis for table/index scan overhead

1 fixed21 passed either way0 still failing0 broke

Pass-rate lift: +5 pp
Tokens: -3%
Agent turns: 0%
Response time: -9%

Model gemini-3.6-flashMeasured 8/16/2026v122 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/archive228-sql-review/SKILL.md https://app.decimal.ai/s/archive228-sql-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add archive228-sql-review, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/archive228-sql-review/ and pins it in .decimal/skills.lock

decimalai skills add archive228-sql-review

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/archive228-sql-review/SKILL.md https://app.decimal.ai/s/archive228-sql-review/SKILL.md

Raw file: /s/archive228-sql-review/SKILL.md ↗ · machine-readable summary at /s/archive228-sql-review.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

Review this offset-based query on a billion-row table: `SELECT * FROM transaction_history ORDER BY id LIMIT 100 OFFSET 5000000;`. Analyze performance issues and rewrites.

What was checked, without and with the skill
Checked	Without skill	With skill
Replaces high OFFSET pagination with keyset/cursor-based pagination	Passed	Passed
Includes EXPLAIN analysis for table/index scan overhead	Missed	Passed

case-19 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md8 linessingle file

SQL Review

Injection — parameterized, always. No string interpolation into SQL.
N+1 — a query inside a loop? Replace with a join or a batched IN.
Missing index — does the WHERE/JOIN/ORDER BY hit an indexed column? If not, the table scan will surface at scale.
Unbounded — SELECT with no LIMIT on a growing table; a JOIN that fans out rows.
Transactions — multi-write operations wrapped so a partial failure can't corrupt state.
Migrations — reversible (up AND down), and safe on a live table (no blocking lock on a hot table at peak). Output: each issue with the line and the rewrite. Show the EXPLAIN if performance is the concern.

Track record

Benchmark

22 / 22

test cases passed, vs 21 / 22 without

Adoption

Users: 16
Times used: 305

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

archive228 / loopkit

skills/sql-review/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

SQL Review

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills