smithery.ai

prioritize-review-comments

Decide which automated review comments to fix vs skip. Use after receiving feedback from hooks, GitHub bots, or review agents.

First seen Mar 30, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,951 B
  • docs SUMMARY.md 160 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Prioritize Review Comments

After receiving automated review feedback, apply this framework to decide what to fix.

What to Fix

TL;DR: Valid problems that are in-scope.

For example:

  • A bug in the implementation: fix
  • Created code duplication: fix
  • Touched (called / edited) duplicated code: fix the DRY
  • A mistaken bug (the reviewer didn't understand the code): skip
  • A valid problem that doesn't happen in practice: If this problem could happen if the code around would change (e.g creating a component that could be called in a way that creates a bug but nobody calls it this way now): fix

- For example, an API that would break if called in some way but it isn't called in that way: we want our APIs to be robust

  • A pre-existing problem that wasn't touched by this code, e.g noticing a problem in an unrelated util: skip (don't scope creep)
  • A valid in-scope problem that is tiny and takes seconds to fix: fix

- if it takes a long time to fix: still fix. (the amount of work is not a factor, we want to keep the code we touched clean)

  • No SSOT (doesn't cause a bug) : this is a design problem, fix
  • There is another idea for a feature that might be good: probably out of scope, consider suggesting it to the user, perhaps as a follow-up
  • Changed a variable from containing only the user meetings to containing all meetings: is changing the variable name or tests about it in scope? yes, otherwise the incorrect name is a problem caused by this PR, definitely in scope

Show Your Decisions

Consider showing the user your decisions. For each review comment:

  1. Is it a valid problem?
  2. Is it in code that was touched?
  3. (If you want: how big is the fix. Though this shouldn't affect whether we do it.)
  4. Fix / Skip / Open follow-up issue