Agent skill

Review PR

by bholmesdev in bholmesdev/hubble.md

Review a pull request or local branch diff for correctness, security, lifecycle, error handling, tests, and meaningful performance risks.

MITAuto-check passedDevelopment

Install Review PR

skills CLI
$ npx skills add bholmesdev/hubble.md --skill review-pr -a claude-code

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

GitHub CLI
$ gh skill install bholmesdev/hubble.md 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/bholmesdev/hubble.md.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/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
1.5k
Token cost
~800 tokens
SKILL.md length
351 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Review a pull request or local branch diff for correctness, security, lifecycle, error handling, tests, and meaningful performance risks.

  • Works in 5 steps: Use the base branch, commit, or range… → Otherwise determine the merge base with… → Include committed branch changes plus… → …
  • Asked to review PR changes
  • SKILL.md covers Establish scope, Review priorities, Finding rules and Structured JSON Output
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review PR is an agent skill from bholmesdev/hubble.md. Review a pull request or local branch diff for correctness, security, lifecycle, error handling, tests, and meaningful performance risks. Use when asked to review PR changes, a branch, a commit range, or the current working tree and return a structured review.

Its SKILL.md is about 800 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. The repository describes itself as: The best notepad for you and your agents. The licence is MIT.

When your agent uses it

  • Asked to review PR changes
  • The current working tree and return a structured review

Example prompts

  • “/review-pr”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Use the base branch, commit, or range named by the user.
  2. Otherwise determine the merge base with the repository's default branch.
  3. Include committed branch changes plus relevant staged, unstaged, and untracked files.
  4. Use available change descriptions, specifications, and review context.
  5. Focus on changed code and the unchanged call sites needed to prove or disprove a finding.

What it can do on your machine

Read from SKILL.md and the folder at commit 571a523. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

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

  • Network

    No URLs in SKILL.md.

    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 800 tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 351 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~800

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 passed

The automated check found no risky patterns in SKILL.md.

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 bholmesdev/hubble.md at commit 571a523, republished under its MIT licence (© bholmesdev). 351 words, ~800 tokens.

Download SKILL.mdSave it as .claude/skills/review-pr/SKILL.md (or your agent's skills folder).
name
review-pr
description
Review a pull request or local branch diff for correctness, security, lifecycle, error handling, tests, and meaningful performance risks. Use when asked to review PR changes, a branch, a commit range, or the current working tree and return a structured review.

Review PR

Review the requested change set and return a structured response.

If asked to use a structured JSON output specifically, follow the "Structured JSON Output" section. Otherwise, respond with your structured review as text, naturally as part of the conversation.

Establish scope

  1. Use the base branch, commit, or range named by the user.
  2. Otherwise determine the merge base with the repository's default branch.
  3. Include committed branch changes plus relevant staged, unstaged, and untracked files.
  4. Use available change descriptions, specifications, and review context.
  5. Focus on changed code and the unchanged call sites needed to prove or disprove a finding.

Review priorities

Prioritize:

  1. Correctness, data loss, security, crashes, and broken user behavior.
  2. Lifecycle, concurrency, stale state, cleanup, and error-handling problems.
  3. Material performance regressions on demonstrated hot paths.
  4. Missing or weak tests, judged by .agents/skills/writing-tests/SKILL.md.

Avoid speculative findings. Trace relevant callers, state transitions, cleanup paths, and existing tests before reporting an issue. Do not flag untouched code unless the change makes it unsafe.

Treat robustness ideas as suggestions unless they present a concrete correctness, security, or data-loss risk.

Show full SKILL.md (166 more words)Show less

Finding rules

Use these severities:

  • critical: security issue, data loss, crash, or broadly broken behavior.
  • important: concrete logic, lifecycle, edge-case, or error-handling bug.
  • suggestion: worthwhile non-blocking improvement.
  • nit: precise cleanup with a concrete replacement.

For every finding:

  • Cite a repository-relative path.
  • Cite an exact changed line when possible; otherwise use null.
  • Explain the failure mode and when it occurs.
  • Give a concrete fix direction.
  • Keep the body concise and actionable.

Return REQUEST_CHANGES only when at least one critical or important finding remains. Suggestions and nits do not block approval.

Structured JSON Output

If asked to use structured JSON as your output, follow this shape exactly to ensure your response can be parsed in contexts like CI. Do not wrap it in a Markdown fence and do not write it to disk.

json
{
  "verdict": "REQUEST_CHANGES",
  "overview": "Short description of the reviewed change and overall assessment.",
  "findings": [
    {
      "severity": "important",
      "path": "path/to/file.ts",
      "line": 42,
      "title": "Short finding title",
      "body": "Failure mode, evidence, and concrete fix direction."
    }
  ],
  "counts": {
    "critical": 0,
    "important": 1,
    "suggestion": 0,
    "nit": 0
  }
}

verdict must be exactly APPROVE or REQUEST_CHANGES. findings must be empty when no issues remain. Counts must match the findings array.

Do not modify the repository or publish the review unless the user separately asks.

© bholmesdev, MIT. 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 .agents/skills/review-pr of bholmesdev/hubble.md.

Open the folder on GitHubat commit 571a523

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 skillbholmesdev/hubble.md1.5k—~800Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything85k1 repos~1.4kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • 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
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    85k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from bholmesdev/hubble.md

All 13 skills in this repo
  • Changelog

    bholmesdev/hubble.md

    Add a user-facing entry to CHANGELOG.md for work that just landed.

    1.5k GitHub stars~564 tokensUpdated 5 days ago
    Auto-check passed
  • Triage

    bholmesdev/hubble.md

    Triage an incoming GitHub, Jira, Linear, or other issue-tracker issue against the current codebase and related issues, then return a structured decision with exactly one triage state.

    1.5k GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed
  • Simplify

    bholmesdev/hubble.md

    Use this skill automatically when you feel your code is ready for human review, and whenever writing or reviewing code comments.

    1.5k GitHub stars~886 tokensUpdated 5 days ago
    Auto-check passed
  • Write Product Spec

    bholmesdev/hubble.md

    Write a PRODUCT.md spec for a significant Hubble user-facing feature, focused only on user experience and observable behavior.

    1.5k GitHub stars~966 tokensUpdated 5 days ago
    Auto-check passed
  • Write Tech Spec

    bholmesdev/hubble.md

    Write a TECH.md spec for a significant Hubble feature after researching the monorepo architecture.

    1.5k GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check: notes
  • Taste Review

    bholmesdev/hubble.md

    Ask Claude Code to make a taste-driven call on something ambiguous — UI polish, prose phrasing, naming, formatting.

    1.5k GitHub stars~306 tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Review PR

What does Review PR do?

Review a pull request or local branch diff for correctness, security, lifecycle, error handling, tests, and meaningful performance risks. md. Review a pull request or local branch diff for correctness, security, lifecycle, error handling, tests, and meaningful performance risks.

When should I use Review PR?

Review PR fits situations like: asked to review PR changes; the current working tree and return a structured review.

How do I install Review PR in Claude Code?

Run `npx skills add bholmesdev/hubble.md --skill review-pr -a claude-code`. Or copy the skill folder (.agents/skills/review-pr in bholmesdev/hubble.md) 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 bholmesdev/hubble.md --skill review-pr -a codex`. Or copy the skill folder (.agents/skills/review-pr in bholmesdev/hubble.md) 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 bholmesdev/hubble.md --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?

SKILL.md names no scripts, command-line tools or credentials: Review PR is instructions for the agent only.

Does Review PR access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review PR safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Review PR use?

Review PR is published under the MIT 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 800 tokens (SKILL.md is roughly 3.2k 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: Finishing a Development Branch (obra/superpowers, 296k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 85k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review PR?

bholmesdev (a GitHub user) maintains it in bholmesdev/hubble.md, which has 1,483 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 1, 2026.

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