Review
Run a structured code-review pass — correctness, style, and risk flags before merge.
by AgentVoltv1.0.0Published 1y ago1 install
Free to sign up · every skill included with AgentVolt Pro
Before & after
Same prompt, same agent — the only difference is the skill.
Prompt“Review this PR before I merge it.”
Beforegeneric AI agent
I'd be happy to review your PR. A good code review typically checks: - Correctness: does the logic do what it should - Edge cases: are they handled - Readability: is the code clear - Style: does it match conventions - Tests: is there adequate coverage - Security: any vulnerabilities Share the diff and I'll give you specific feedback. Generally it helps to review in passes — correctness first, then style, then nitpicks. What does the PR change?
Afterwith Review
Structured review pass — findings grouped by what they'd actually do to
you, most severe first. Coverage over politeness: I report it, you
decide.
CORRECTNESS (blocks merge)
▸ src/api.ts:44 — the error path returns undefined, and the caller at
:81 does .length on it. Null-input crash. This is the merge-blocker.
▸ src/parse.ts:23 — off-by-one: loop runs to <= length, reads one past
the array. Silent on happy path, wrong on the boundary.
RISK FLAGS (should-fix before merge)
▸ auth/token.ts:12 — token compared with ===, not a constant-time
compare. Timing-attack surface on an auth path.
▸ No test covers the error branch above — which is exactly why it
shipped.
STYLE / CONSISTENCY (non-blocking)
▸ Mixed async styles in one file (.then and await). Pick one.
▸ src/util.ts:30 — magic number 86400, name it SECONDS_PER_DAY.
WHAT'S GOOD
The refactor consolidates three duplicated fetch calls into one — right
call, and it makes the correctness fix above a one-line change instead
of three.
VERDICT
Block on the two correctness items. The security and test gaps I'd fix
in the same PR since the files are already open; style can follow.
Paste the diff and I'll run the real pass line by line.About this skill
name: review description: Use when -
Review
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the review skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Review; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
SKILL.md
---
name: review
description: Use this skill when running a structured code-review pass before merge, checking correctness, style, and risk.
version: 1.0.0
category: Development / Engineering
author: AgentVolt
license: proprietary
tags:
- development
- engineering
---
# Review
Runs a structured review pass over a diff or pull request, surfacing correctness bugs, style deviations, and risk flags before merge.
## When to use
… (sign up to view the full skill)Sign up to view, copy, and install the full skill
More development skills
View all Development skills →Generate
Scaffold code, tests, and boilerplate from a short spec.
Development
Performance Profiler
Systematic performance profiling for Node.js, Python, and Go applications.
Development
Threat Detection
Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.
Development
Agent Harness
Turns a domain folder of skills into a bounded agentic loop: compile a goal into a task plan, execute with the domain's tools, verify every task, retry within a budget.
Development