Agent skill

Review PR

by hmislk in hmislk/hmis

Handle CodeRabbit and Codex review comments on a GitHub PR. An agent skill from hmislk/hmis.

GPL-3.0Auto-check: notesDevelopment

Install Review PR

skills CLI
$ npx skills add hmislk/hmis --skill review-pr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hmislk/hmis review-pr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hmislk/hmis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/review-pr .claude/skills/review-pr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-pr
GitHub stars
236
Token cost
~1.4k tokens
SKILL.md length
579 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
GPL-3.0

At a glance

Handle CodeRabbit and Codex review comments on a GitHub PR. An agent skill from hmislk/hmis.

  • Works in 10 steps: Fetch and Checkout → Load PR Comments → Investigate Each Comment → …
  • Tasks that involve Pull requests
  • SKILL.md covers Arguments, Steps and Reference
  • Calls gh and git

What it does

Review PR is an agent skill from hmislk/hmis. Handle CodeRabbit and Codex review comments on a GitHub PR. Fetches the PR, investigates each comment against the codebase, discusses validity with the user, batches valid fixes, and guides through push and reply steps.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: This is an Open Source Java EE based Hospital Information Management System. The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Pull requests

Example prompts

  • “/review-pr”

Requirements

  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Fetch and Checkout
  2. Load PR Comments
  3. Investigate Each Comment
  4. Present Findings to User
  5. Batch Valid Fixes
  6. Pre-Push Checklist
  7. Push
  8. Reply to Existing Reviewer Threads
  9. Re-Request Review
  10. Post-Merge Cleanup

What it can do on your machine

Read from SKILL.md and the folder at commit d261e32. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review PR loads about 1.4k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 579 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:78
    - No credentials or `.env` files staged
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Grep, Glob, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hmislk/hmis at commit d261e32, republished under its GPL-3.0 licence (© hmislk). 579 words, ~1,392 tokens.

Download SKILL.mdSave it as .claude/skills/review-pr/SKILL.md (or your agent's skills folder).
name
review-pr
description
Handle CodeRabbit and Codex review comments on a GitHub PR. Fetches the PR, investigates each comment against the codebase, discusses validity with the user, batches valid fixes, and guides through push and reply steps.
allowed-tools
Read, Grep, Glob, Bash
argument-hint
<pr-url-or-number>

PR Review Workflow

Handle review comments (CodeRabbit, Codex, human reviewers) on a GitHub pull request.

Arguments

  • $0 — GitHub PR URL or PR number (required)

Steps

1. Fetch and Checkout
bash
git fetch origin
gh pr checkout $0

Always fetch first — automated tools may have pushed fixes not yet local.

2. Load PR Comments
bash
gh pr view $0 --comments
pr_number=$(gh pr view $0 --json number --jq '.number')
gh api repos/hmislk/hmis/pulls/$pr_number/comments

List all review comments. Group them by file/topic.

3. Investigate Each Comment

For each comment:

  • Read the referenced file and line range with Read
  • Search for related patterns with Grep
  • Determine if the comment is valid, a false positive, or project-specific intent

Common false positives in this project:

  • Null checks where lazy init already handles it (e.g., getBillFinanceDetails())
  • Constructor changes — NEVER modify existing constructors (HMIS rule)
  • "Fix" for intentional typos like purcahseRate — database compatibility
  • Native SQL suggestions when JPQL works fine
  • Bootstrap CSS classes when project uses PrimeFaces
4. Present Findings to User

For each comment, report:

  • Comment summary
  • Your assessment: Valid / False positive / Discuss
  • Reasoning with file:line reference

Wait for user confirmation before making any changes.

5. Batch Valid Fixes

Apply all confirmed fixes. Group into one or a few logical commits:

text
Fix CodeRabbit review comments (#<issue>)

Closes #<issue>

Co-Authored-By: Claude <noreply@anthropic.com>
6. Pre-Push Checklist
  • persistence.xml uses ${JDBC_DATASOURCE} / ${JDBC_AUDIT_DATASOURCE} — not hardcoded JNDI names
  • No credentials or .env files staged
  • JSF-only changes do not need compilation
7. Push
bash
git push

Verify CI passes before proceeding.

8. Reply to Existing Reviewer Threads

⚠️ Cardinal rules — read before posting anything:

  1. Do NOT create new top-level inline comments on the PR. Each one becomes a thread the author must manually resolve. This is noise.

  2. Reply only after fixing (or explicitly dismissing). Bots cannot fix anything — describe action taken, not requested.

    • Valid + fixed → "Fixed in <commit-sha>: <what was changed>"
    • Dismissed → "Dismissed because: <specific reasoning>"

    ⚠️ "Please resolve" wording on a CodeRabbit thread triggers CodeRabbit Chat — it opens a NEW PR (📝 CodeRabbit Chat: Implement requested code changes, branch coderabbitai/chat/<sha>) attempting the fix against a stale snapshot. These auto-PRs often duplicate work the author has already done and have shipped unsafe diffs (e.g. deleted a params.put(...) line on PR #20979). If you accidentally trigger one: close it, delete the branch.

  3. Replies go UNDER existing reviewer threads only (/replies endpoint). Never as new top-level comments.

  4. Self-review items go in the commit message (or PR description if deferred). Never as new inline comments.

  5. ONE re-review request at the end, not per item.

Order: discuss → fix → push → reply to existing threads → one re-review request.

Show full SKILL.md (188 more words)Show less

For each existing reviewer comment, post a threaded reply under the parent. The four endpoints are easy to confuse:

WantEndpointUse?
Reply under existing reviewer comment (threaded)POST /pulls/{pr}/comments/{id}/repliesYES — this is the only legitimate reply form
New standalone inline comment on a linePOST /pulls/{pr}/commentsNO — creates a fresh thread the author must manually resolve
Bundled reviewPOST /pulls/{pr}/reviewsNO — grouping wrapper, doesn't match how bots post
General PR comment (only genuine PR-wide notes)POST /issues/{n}/commentsSparingly — only for actual PR-wide announcements

For self-review items you spot on your own PR — don't post a new inline comment. Fix in the next commit and reference the file:line in the commit message:

text
refactor(cashier): address self-review items

- PaymentSettlementController.java:117 — add comment on shallow snapshot
- settle_non_cash.xhtml:203 — use lastSettlementBill.institution.name

Find existing comment IDs to reply to:

bash
gh api "repos/hmislk/hmis/pulls/<PR>/comments" \
  --jq '.[] | "\(.id) \(.user.login) \(.path):\(.line // .original_line)"'

Post a threaded reply:

bash
gh api -X POST "repos/hmislk/hmis/pulls/<PR>/comments/<COMMENT_ID>/replies" \
  -f body="Fixed in <commit-sha>: <what was changed>."

Do NOT resolve other reviewers' conversations. CodeRabbit auto-resolves on detection.

Full API recipes and cleanup commands: see Posting PR Comments via gh CLI.

9. Re-Request Review

Click "Re-request review" on the PR page after pushing. Do not rely on reviewers noticing the new push.

10. Post-Merge Cleanup

After merge:

bash
git branch -d <branch-name>

Also confirm "Delete branch" was checked in the GitHub merge dialog.

Reference

Full workflow documentation: developer_docs/git/pr-review-workflow.md

© hmislk, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/review-pr of hmislk/hmis.

Open the folder on GitHubat commit d261e32

Compare with similar skills

Review PR next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Review PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review PR this skillhmislk/hmis236—~1.4kAutomated safety check: NotesGPL-3.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from hmislk/hmis

All 33 skills in this repo
  • API Usage

    hmislk/hmis

    Reference for calling existing HMIS REST APIs. An agent skill from hmislk/hmis.

    236 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Application configuration options reference for the HMIS project.

    236 GitHub stars~474 tokensUpdated today
    Auto-check passed
  • Caveman

    hmislk/hmis

    Ultra-compressed communication mode. An agent skill from hmislk/hmis.

    236 GitHub starsUsed in 20 repos~946 tokens
    Auto-check passed
  • Database Guide

    hmislk/hmis

    MySQL database development guide for the HMIS project. An agent skill from hmislk/hmis.

    236 GitHub stars~664 tokensUpdated today
    Auto-check passed
  • Demo Video

    hmislk/hmis

    A skill your agent uses when asked to make a demo, training, how-to or tutorial video with sound or voice-over showing an HMIS function or configuration (e.g.

    236 GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Deploy QA

    hmislk/hmis

    Sync development into QA/testing environment branches (QA1-QA4, local RH staging) via PR + merge on GitHub.

    236 GitHub stars~2.1k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Review PR

What does Review PR do?

Handle CodeRabbit and Codex review comments on a GitHub PR. An agent skill from hmislk/hmis. Review PR is an agent skill from hmislk/hmis. Handle CodeRabbit and Codex review comments on a GitHub PR.

When should I use Review PR?

Review PR fits situations like: tasks that involve Pull requests.

How do I install Review PR in Claude Code?

Run `npx skills add hmislk/hmis --skill review-pr -a claude-code`. Or copy the skill folder (.claude/skills/review-pr in hmislk/hmis) into .claude/skills/review-pr in your project. Claude Code loads it when a task matches its description.

How do I install Review PR in Codex?

Run `npx skills add hmislk/hmis --skill review-pr -a codex`. Or copy the skill folder (.claude/skills/review-pr in hmislk/hmis) into .agents/skills/review-pr in your project. Codex loads it when a task matches its description.

Can I use Review PR in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hmislk/hmis --skill review-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-pr, .gemini/skills/review-pr, .github/skills/review-pr and .opencode/skills/review-pr in your project.

What does Review PR need to run?

Going by SKILL.md and its folder, Review PR needs the command-line tools its instructions call (gh and git). Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash.

Does Review PR access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Review PR safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Review PR use?

Review PR is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review PR use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review PR?

Skills that share tags, products or a category with Review PR: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review PR?

hmislk (a GitHub organization) maintains it in hmislk/hmis, which has 236 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 9, 2026.

Source: hmislk/hmis on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.