Ready to supercharge your AI agents?

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

Code Review · jamestorrevillas | DecimalAI

code reviewby jamestorrevillas

Code Review

jamestorrevillas/code-review

Source jamestorrevillas/dev-skills ↗License MIT

Use this skill when performing code reviews, security audits, architecture reviews, vulnerability analysis, or evaluating code quality. Trigger on keywords: code review, review, audit, security, vulnerability, OWASP, SQL injection, XSS, architecture review, refactor suggestion, quality check, static analysis.

SkillScore87Maintained

Automatic

Coding pack

Last verified 8/3/2026

What it changes

Passed 20 of 23 test cases with the skill, and 9 of 23 without it.

Without skill39%

With skill87%

Checks it passed that the model alone missed

Labels the hardcoded API key with the BLOCKER tag.
States that PRAISE has a fix requirement status of N/A.
Specifies 40 lines as the function length limit guideline.

and 8 more in the full report

11 fixed9 passed either way3 still failing0 broke

Pass-rate lift: +48 pp
Tokens: +38%
Agent turns: 0%
Response time: -23%

Model gemini-3.6-flashMeasured 8/3/2026v120 of 23 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/jamestorrevillas-code-review/SKILL.md https://app.decimal.ai/s/jamestorrevillas-code-review/SKILL.md

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

decimalai skills add jamestorrevillas-code-review

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

During a pull request code review, a developer rewrote a complex algorithm to be significantly cleaner and well-tested. What specific tag should be used to acknowledge this good work, and what is its fix requirement status?

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies PRAISE as the feedback tag for good work.	Passed	Passed
States that PRAISE has a fix requirement status of N/A.	Missed	Passed

case-18 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md138 linessingle file

Code Review

Review Philosophy

Review the code, not the person. The goal is to ship better software, not to win arguments. Every comment should make the codebase better or help the author learn — preferably both.

Feedback Categories

Always tag review comments to set expectations:

Tag	Meaning	Must Fix?
`BLOCKER`	Breaks functionality, security risk, violates standards	Yes
`WARNING`	Technical debt, potential issue, should be addressed	Recommended
`SUGGESTION`	Optional improvement, alternative approach	No
`QUESTION`	Asking for clarification or understanding	No
`NITPICK`	Minor style or preference	Author decides
`PRAISE`	Acknowledge good work	N/A

Code Quality Checklist

Correctness

Does the code do what the ticket/story requires?
Are edge cases handled? (null, empty, boundary values)
Is error handling present and meaningful?
Are async operations awaited properly?
Are there any obvious race conditions?

Readability

Are variable and function names descriptive?
Is the code self-documenting (minimal need for comments)?
Are complex sections commented with the "why"?
Is there dead code or commented-out code that should be removed?
Is function length reasonable (< 40 lines as a guideline)?

Architecture

Track record

Benchmark

20 / 23

test cases passed, vs 9 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

jamestorrevillas / dev-skills

.github/skills/code-review/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version 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

Review Philosophy

Feedback Categories

Code Quality Checklist

Correctness

Readability

Architecture

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills