post-review-comments
Post line-level review comments and an overall review comment on a PR in English with a natural, concise writing style
Best use case
post-review-comments is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Post line-level review comments and an overall review comment on a PR in English with a natural, concise writing style
Teams using post-review-comments should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/post-review-comments/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How post-review-comments Compares
| Feature / Agent | post-review-comments | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Post line-level review comments and an overall review comment on a PR in English with a natural, concise writing style
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
target_pr = $ARGUMENTS
If target_pr is not provided, use the PR of the current branch.
## Step 1: Understand the PR
Read the PR diff and description to understand:
- What changed and why
- The scope and impact of the changes
## Step 2: Prepare Line-Level Comments
Identify specific lines in the diff that deserve feedback — bugs, potential issues, style concerns, suggestions for improvement, or questions about intent.
For each comment, note:
- The file path
- The line number (in the new version of the file)
- Your comment text
## Step 3: Prepare an Overall Review Comment
Write a brief overall assessment of the PR. This is a summary-level comment, not a repeat of line-level feedback.
## Step 4: Post the Review
Use a single `gh api` call to submit both line-level comments and the overall comment together as one review:
```bash
gh api repos/{owner}/{repo}/pulls/{pr_number}/reviews \
--method POST \
-f event="COMMENT" \
-f body="<overall comment>" \
-f 'comments[]={...}' ...
```
Each line comment requires: `path`, `line` (line number in the diff's new file), and `body`.
If you have no line-level comments, fall back to:
```bash
gh pr review <pr_number> --comment --body "<overall comment>"
```
## Writing Style
Write in **English only**.
Style guidelines — write like a human teammate, not a bot:
- Use plain paragraphs. Avoid headings (`##`), horizontal rules (`---`), and excessive bullet lists.
- Keep it conversational and direct. Say what matters, skip the filler.
- Do not use phrases like "Great work!" or "LGTM!" unless you genuinely mean it and have nothing else to add.
- Be honest. If something looks off, say so clearly but respectfully.
- Short is fine. A two-sentence comment is better than a five-paragraph essay with no substance.
## Step 5: Report
Output the PR number, a count of line-level comments posted, and a brief summary of the overall comment.Related Skills
review-pr
Review a pull request for code quality and security issues. Use when the user wants to review a PR, check PR code changes, or audit a pull request. Triggers on: "review PR", "review pull request", "check this PR", "/review-pr".
review-and-comments
Review a PR for code quality and security issues, then post review comments on it. Runs review-pr followed by post-review-comments sequentially.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
security-scan-diff
Scan for malicious code in git diff between a tag/commit and HEAD
release-dry-run
Dry run for release: summarize changes since last release and suggest version bump.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
git-worktree-runner
Manages git worktrees using git-worktree-runner (gtr). Use when the user needs to create, list, remove, or navigate worktrees with `git gtr` commands, open editors or AI tools in worktrees, manage parallel development branches, or check out GitHub PRs (including from forks) into worktrees.
draft-release
Draft a new release of the project.
create-scrap-issue
Create a GitHub issue that consolidates passed content into a single scrap issue with background context and solution details, labeled as maintainer-scrap. Use when the user wants to create a scrap issue, jot down notes as a GitHub issue, or save findings for later.
create-issue
Create a GitHub issue with detailed description, purpose, and appropriate labels
rebase-latest-main
Fetch latest origin/main and rebase it onto the current branch, resolving conflicts if necessary. Use when the user wants to rebase on main, update their branch with latest main, or sync with upstream.