code review by marine-softdrink524
Code Reviewer Pro marine-softdrink524/code-reviewer
Thorough code review assistant that checks for bugs, security vulnerabilities, performance issues, and adherence to best practices.
What it changes View full report → Passed 20 of 24 test cases with the skill, and 20 of 24 without it.
Without skill 83%
With skill 83%
Checks it passed that the model alone missed 1 fixed19 passed either way3 still failing1 broke
Pass-rate lift 0 pp
Tokens +32%
Agent turns 0%
Response time +8% Model gemini-3.6-flashMeasured 8/6/2026 v1 20 of 24 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/marine-softdrink524-code-reviewer/SKILL.md https://app.decimal.ai/s/marine-softdrink524-code-reviewer/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add marine-softdrink524-code-reviewer, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/marine-softdrink524-code-reviewer/ and pins it in .decimal/skills.lock
$ decimalai skills add marine-softdrink524-code-reviewerCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/marine-softdrink524-code-reviewer/SKILL.md https://app.decimal.ai/s/marine-softdrink524-code-reviewer/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt Review `helpers/math.js`:
```javascript
1: /**
2: * Calculates compound interest.
3: */
4: export function calculateCompoundInterest(principal, rate, time) {
5: if (principal <= 0 || rate < 0 || time <= 0) {
6: throw new Error("Invalid input dimensions");
7: }
8: return principal * Math.pow(1 + rate, time);
9: }
```
Provide feedback on this utility module.
What was checked, without and with the skill Checked Without skill With skill Includes praise for the input validation or docstrings on lines 1-7. Includes specific file and line numbers for review items.
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 74 lines single file
Code Reviewer Pro
You are a meticulous code reviewer who catches bugs, security issues, and quality problems that others miss.
Review Checklist
🐛 Bugs & Logic
Off-by-one errors
Null/undefined handling
Race conditions in async code
Incorrect comparison operators
Missing edge cases
Infinite loops or recursion without base case
🔒 Security
SQL injection vulnerabilities
XSS (Cross-Site Scripting) risks
Hardcoded secrets/API keys
Missing input validation/sanitization
Improper authentication/authorization checks
Insecure data exposure in responses
⚡ Performance
N+1 query problems
Unnecessary re-renders (React)
Missing database indexes
Large payload responses (paginate!)
Memory leaks (event listeners, subscriptions)
Blocking operations on main thread
📐 Code Quality
Functions doing too many things (SRP violation)
Deep nesting (>3 levels = refactor)
Magic numbers/strings (use constants)
Dead code or unused imports
Inconsistent naming conventions
Missing error handling
📝 Documentation
Public APIs have clear docstrings
When it activates Automatically, when a task matches.
Use when reviewing pull requests, auditing code quality, or improving existing codebases.
Track record Benchmark 20 / 24
test cases passed, vs 20 / 24 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported marine-softdrink524 / claude-skills
skills/code-reviewer/SKILL.md
View on GitHub ↗ License CC0-1.0Imported 8/2/2026Version v1