agentleFS
pgplexpgplex/pgschema/.claude/skills/review_comments/SKILL.md

review_comments

Skill1.1k starsChanged 9 months agoApache-2.0View on GitHub

Verdict PR review comments pragmatically - address valid ones, dismiss over-engineered or incorrect ones, and respond to each. Use this skill when handling PR review feedback, code review comments, or when asked to address reviewer suggestions.

1 other project uses a version of this.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 2 mentionsApr 2026: 2 mentionsMay 2026: 0 mentionsJun 2026: 1 mentionJul 2026: 0 mentionsAug 2026: 2 mentionsSep 2026: 3 mentionsOct 2026: 8 mentionsNov 2026: 4 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the pgplex/pgschema repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about pgplex/pgschema

The biggest 5 of 22 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 22

Talked about on GitHub (22 times).

On GitHub · 22

17 more on GitHub
  • Other versions1 project uses a version of this.

    Word for word · 1

    1. pgschema/pgschema★ 1.1k100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the actual code being reviewed to understand context

    line 19
  2. Very specific:

    Use gh to reply to each comment:

    line 65
  3. Distinctive:

    YAGNI: - Don't build for requirements that don't exist yet

    line 74
  4. Distinctive:

    Minimal diff: - Every line changed is a line that could break.

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review Comments

Pragmatically triage PR review comments: fix what matters, push back on what doesn't.

Phase 1: Fetch Comments

  1. Get the PR number from context or user input
  2. Fetch all review comments:
    gh pr view <number> --json reviews,comments
    gh api repos/{owner}/{repo}/pulls/<number>/comments
    gh api repos/{owner}/{repo}/pulls/<number>/reviews
  3. Read the actual code being reviewed to understand context

Phase 2: Verdict Each Comment

For each comment, classify it into one of:

ADDRESS - The comment is correct and actionable

  • Genuine bugs or logic errors
  • Missing edge cases that could actually happen
  • Security issues
  • Correctness issues backed by evidence

DISMISS - The comment is over-engineered, stylistic, or wrong

  • Adding abstractions for hypothetical future needs
  • Suggesting error handling for impossible scenarios
  • Style preferences with no functional impact
  • Refactoring suggestions unrelated to the PR's purpose
  • Incorrect assumptions about how the code works
  • "What if..." scenarios that won't happen given the codebase constraints
  • Suggesting tests for trivial code paths
  • Adding comments/docs to self-evident code

ACKNOWLEDGE - Minor valid point, not worth changing

  • Technically correct but the cost of change outweighs the benefit
  • Valid style point but not a blocker
  • Good idea for a follow-up, not this PR

Phase 3: Act on Each Comment

For ADDRESS comments

  1. Make the code change
  2. Reply explaining what was fixed

For DISMISS comments

Reply with a concise, respectful explanation of why you're not making the change. Be direct, not defensive. Examples:

  • Over-engineering: "This is a single-use path - I'd rather keep it simple and extract if/when we need reuse."
  • Impossible scenario: "This can't happen because [X guarantees Y]. Adding a guard here would suggest the invariant isn't trustworthy."
  • Style preference: "Both approaches work - I'll keep the current style for consistency with the surrounding code."
  • Wrong assumption: "Actually, [correct explanation]. The current code handles this because [reason]."

For ACKNOWLEDGE comments

Reply acknowledging the point briefly: "Good point - I'll keep this in mind for follow-up" or "Fair, though I think the current approach is fine for now given [reason]."

Phase 4: Respond

Use gh to reply to each comment:

gh api repos/{owner}/{repo}/pulls/<number>/comments/<comment_id>/replies \
  -f body="<response>"

Decision Principles

  1. Ship over perfection - The goal is a working, correct change, not a perfect one
  2. YAGNI - Don't build for requirements that don't exist yet
  3. Minimal diff - Every line changed is a line that could break; keep changes focused
  4. Trust the codebase - Internal code doesn't need defensive programming against itself
  5. Reviewer != oracle - Reviewers can be wrong, overly cautious, or applying rules from different contexts
  6. Evidence over authority - "This could break" needs a scenario; "best practice says" needs a reason
  7. Be respectful, be direct - Dismissing a comment isn't personal; explain your reasoning clearly

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.