Ready to supercharge your AI agents?

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

Get Started Free →

Code Review Standards · aiskillstore | DecimalAI

code reviewby aiskillstore

Code Review Standards

aiskillstore/code-review-standards

Source aiskillstore/marketplace ↗License Not recorded

Code review framework and criteria. References security-sentinel for security checks.

SkillScore91Maintained

Automatic

Coding pack

Last verified 9/3/2026

What it changes

Passed 20 of 22 test cases with the skill, and 12 of 22 without it.

Without skill55%

With skill91%

Checks it passed that the model alone missed

Uses 🟢 LOW for the lowest severity level.
Classifies missing tests as MEDIUM severity.
Uses 🔴 CRITICAL for the highest severity level.

and 8 more in the full report

8 fixed12 passed either way2 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +111%
Agent turns: 0%
Response time: -36%

Model gemini-3.6-flashMeasured 9/3/2026v120 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/aiskillstore-code-review-standards/SKILL.md https://app.decimal.ai/s/aiskillstore-code-review-standards/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aiskillstore-code-review-standards, 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/aiskillstore-code-review-standards/ and pins it in .decimal/skills.lock

decimalai skills add aiskillstore-code-review-standards

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

curl -fsSL --create-dirs -o .claude/skills/aiskillstore-code-review-standards/SKILL.md https://app.decimal.ai/s/aiskillstore-code-review-standards/SKILL.md

Raw file: /s/aiskillstore-code-review-standards/SKILL.md ↗ · machine-readable summary at /s/aiskillstore-code-review-standards.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

A reviewer found three inline `// TODO: refactor query optimization` comments in a database service PR without any further context. What requirement must be met for a TODO comment to be acceptable in production code?

What was checked, without and with the skill
Checked	Without skill	With skill
Requires every TODO comment to reference a GitHub issue.	Missed	Passed

case-09 · gemini-3.6-flash · 9/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md421 linessingle file

Code Review Standards

When to Use

Reviewing pull requests
Performing code reviews
Defining review criteria
Establishing review process

Overview

Code review standards ensure consistent, thorough reviews that catch bugs before they reach production. This skill aggregates criteria from specialized skills.

Review Framework

4-Level Severity Classification

CRITICAL 🔴 - Must fix before merge
- Security vulnerabilities
- Data loss risks
- Authentication bypasses
- SQL injection risks
HIGH 🟠 - Should fix before merge
- TypeScript strict mode violations
- Missing error handling
- Performance issues (N+1 queries)
- Missing input validation
MEDIUM 🟡 - Fix soon (can merge with plan)
- Code quality issues
- Missing tests
- Poor naming
- Missing documentation
LOW 🟢 - Nice to have
- Style suggestions
- Optimization opportunities
- Refactoring ideas

Track record

Benchmark

20 / 22

test cases passed, vs 12 / 22 without

Adoption

Users: 5
Times used: 118

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

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

aiskillstore / marketplace

skills/barnhardt-enterprises-inc/code-review-standards/SKILL.md

View on GitHub ↗

Imported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

Code Review Standards

When to Use

Overview

Review Framework

4-Level Severity Classification

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills