ryoitabashi/shelly/code-review-checklist

Claude Code and agent skill by ryoitabashi/shelly

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Review a diff systematically for correctness, safety, and test coverage before approving it, instead of skimming for obvious typos.

Install

npx vskill@latest install ryoitabashi/shelly/code-review-checklist

SKILL.md

Before approving or merging a change (yours or another agent's), work through the diff in this order rather than reading it top-to-bottom once:

  1. Understand the stated intent first. Read the commit message/PR

description/plan before the diff itself — you can't judge whether a change is correct without knowing what it's supposed to accomplish.

  1. Check correctness on the actual change, not just style. Does the

logic do what it claims? Are edge cases (empty input, zero, null/undefined, the boundary of a range) handled or at least considered? Trace through one concrete example by hand rather than trusting that it "looks right."

  1. Look for scope creep. A diff that bundles an unrelated refactor,

formatting-only churn, or a second unrelated fix makes the real change harder to review and harder to revert independently — flag it to be split, don't just wave it through.

  1. Check what tests changed (or didn't). A behavior change with no test

change is a red flag: either a test should have changed and didn't (regression risk) or no test covers this path at all (coverage gap) — both are worth calling out explicitly rather than assuming it's fine.

  1. Check for the safety-sensitive patterns specifically: destructive

shell commands, credentials/secrets touched, widened permission scope, a changed validation/sanitization rule — these deserve slower, more skeptical reading than a typical logic change.

  1. Give actionable feedback, not just a verdict. If you'd block it,

say exactly what would need to change to unblock it; if you'd approve with reservations, say what to watch for after merge rather than silently accepting residual risk.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
65
Repository forks
10
7-day trend score
26

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ryoitabashi/shelly/code-review-checklist/badge)](https://verified-skill.com/skills/ryoitabashi/shelly/code-review-checklist)

Something wrong with this skill or its page? Tell us.