Workflow code review

Skill subhansh-dev/agent-maxxing/examples/workflow-code-review

95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.

Install

npx -y skills add subhansh-dev/agent-maxxing --skill workflow-code-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

28 days oldThe repository was created 28 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Run an 8-angle code review with security audit before merging.

SKILL.md

2.4 KB, as published. Nobody here has run it

Multi-Agent Workflow: Deep Code Review

Run an 8-angle code review with security audit before merging.

Skills Used

Skill	Role
Deep Code Review	8-angle correctness review
Security Review	Security vulnerability audit
Code Simplify	Cleanup and optimization
Runtime Verify	Run the app and observe behavior
Code Review Checklist	Final checklist pass

Workflow

Phase 1: Gather Context

git diff @{upstream}...HEAD  # Get the diff
git log --oneline -10        # Recent commits

Phase 2: Deep Review (Parallel)

Launch 3 parallel reviews:

Review 1 — Correctness (8 angles):

Load Deep Code Review skill.
Run all 8 angles: line-by-line, removed-behavior, cross-file, reuse, simplification, efficiency, altitude, conventions.
Return: up to 10 findings ranked by severity.

Review 2 — Security:

Load Security Review skill.
Examine: input validation, auth, crypto, injection, data exposure.
Return: HIGH/MEDIUM findings only with confidence scores.

Review 3 — Cleanup:

Load Code Simplify skill.
Run 4 cleanup angles: reuse, simplification, efficiency, altitude.
Return: actionable fixes.

Phase 3: Runtime Verification

Load Runtime Verify skill.
Build the app, run it, drive the changed code paths.
Capture: stdout, screenshots, error messages.
Push on it: try edge cases, wrong inputs, rapid actions.
Verdict: PASS / FAIL / BLOCKED / SKIP

Phase 4: Final Checklist

Load Code Review Checklist.
Check: works? readable? safe? performant? maintainable?
Frontend: accessible? responsive? loading states? no CLS?
Backend: migrations reversible? rate limiting? logging?

Phase 5: Report

## Review Summary

**Correctness:** 3 findings (1 HIGH, 2 MEDIUM)
**Security:** 1 finding (1 MEDIUM)
**Cleanup:** 2 suggestions
**Runtime:** PASS — all paths verified

### Critical Findings
1. [HIGH] SQL injection in user search — line 42
2. [MEDIUM] Missing error handler in API route — line 87

### Recommendations
- Add input validation before line 42
- Wrap API handler in try/catch
- Consider adding rate limiting

Gives 0 of the 12 instructions most automation workflows skills give

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-06

write conventional commit messagesin 36 of 745, across 35 files
delete branches after mergein 30 of 745, across 21 files
make atomic commitsin 25 of 745, across 15 files
write minimal code to pass testsin 22 of 745, across 10 files
run tests before committingin 21 of 745, across 13 files
re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
use try-catch for error handlingin 20 of 745, across 6 files
write tests before implementationin 20 of 745, across 8 files
configure branch protection rulesin 19 of 745, across 5 files
explain the why in commit messagesin 19 of 745, across 9 files
refactor code while tests remain greenin 19 of 745, across 6 files
Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

Run an 8-angle code review before merging
Launch 3 parallel reviews
Run all 8 correctness angles
Examine input validation, auth, crypto, injection, data exposure
Return HIGH or MEDIUM security findings with confidence scores
Run 4 cleanup angles

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.