Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Pr Comments Fix

ASecurity

Fetch PR review comments, evaluate each critically, fix valid ones, reject wrong suggestions. Use when asked to check PR comments, fix review feedback, or handle PR review.

3 stars
0 votes
0 copies
0 views
Added 10/2/2026
code-qualitybashgit

Security Analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned 10/2/2026

$npx -y skills add ashugaev/spur --skill pr-comments-fix --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pr Comments Fix?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pr Comments Fix
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashugaev-pr-comments-fix/badge)](https://www.skillsdirectory.com/skills/ashugaev-pr-comments-fix)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: pr-comments-fix
description: Fetch PR review comments, evaluate each critically, fix valid ones, reject wrong suggestions. Use when asked to check PR comments, fix review feedback, or handle PR review.
---

PR COMMENTS FIX

SCRIPTS, auto-detect repo and PR from current branch

  scripts/pr-info.sh                             PR number, title, URL, branch, state
  scripts/fetch-comments.sh                      review threads: thread_id, resolved status, diff hunks
  scripts/fetch-issue-comments.sh                issue-level, non-inline comments
  scripts/reply-comment.sh <comment_id> <body>   reply to inline comment
  scripts/resolve-thread.sh <thread_id>          resolve a review thread

WORKFLOW

  1  bash .claude/skills/pr-comments-fix/scripts/pr-info.sh
     bash .claude/skills/pr-comments-fix/scripts/fetch-comments.sh

  2  Evaluate each comment, read file + surrounding code. Classify:

       Valid bug                  fix it
       Valid concern, wrong fix   fix your way, explain
       Wrong/incorrect            skip with reasoning
       Stylistic nitpick          skip unless matches project rules
       Already fixed              skip, note it
       Valid, PR already merged   never fix here; file an issue per the `github` skill, reply with its link

  3  Apply fixes. Minimal change, verify no regressions.

  4  bash .claude/skills/pr-comments-fix/scripts/reply-comment.sh COMMENT_ID "Fixed in <commit>"
     bash .claude/skills/pr-comments-fix/scripts/resolve-thread.sh THREAD_ID

  5  bash .claude/skills/pr-comments-fix/scripts/verify-replies.sh
     Must print: OK: all N threads have replies and are resolved.
     FAIL: send missing replies and resolve before finishing.

  6  Report:

       Fixed
         file:line   what was fixed
       Rejected
         file:line   why rejected

RULES

  - Never resolve a thread without replying, always explain what was done.
  - Never blindly apply suggestions, verify against codebase.
  - Bot/Copilot comments get extra scrutiny.
  - Suggestion breaks behavior -> reject it.
  - Prefer own fix over suggested one when a better approach exists.
  - Reply only inside the originating thread, never as a new top-level PR comment.
  - No follow-up, status, or summary comments on the main PR thread, no self-narration on own PRs.
  - One reply per thread; multi-item bot reviews get one reply on the originating comment covering each item.

Attribution

ashugaevashugaev
View sourceSee grades on GitHubMore from ashugaev →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman Review

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

1100021 votes

Caveman Commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

1100021 votes

Springboot Verification

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

2456590 votes

Verification Loop

一个全面的 Claude Code 会话验证系统。

2456590 votes

Django Verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

2456590 votes
View all in code-quality →