Agent skill

Review PR

by marin-community in marin-community/marin

Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations.

Apache-2.0Auto-check passedDevelopment

Install Review PR

skills CLI
$ npx skills add marin-community/marin --skill review-pr -a claude-code

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

GitHub CLI
$ gh skill install marin-community/marin 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/marin-community/marin.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
3.9k
Token cost
~1.3k tokens
SKILL.md length
565 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
Apache-2.0

At a glance

Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations.

  • Works in 10 steps: Inspect the pull request metadata, issue… → Check both issue and inline comments for → Confirm that the checked-out commit and… → …
  • Tasks that involve Pull requests
  • SKILL.md covers Review standard and Workflow
  • Calls uv

What it does

Review PR is an agent skill from marin-community/marin. Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations.

Its SKILL.md is about 1.3k 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: Open-source framework for the research and development of foundation models. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Pull requests

Example prompts

  • “/review-pr”

Requirements

  • Pre-approved tools (allowed-tools): Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*), Bash(gh api:*), Bash(git diff:*), Bash(git merge-base:*), Bash(git rev-parse:*), Bash(git show:*), Bash(rg:*), Bash(uv run infra/codehealth/log_stats.py:*), mcp__github_inline_comment__create_inline_comment

Workflow steps

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

  1. Inspect the pull request metadata, issue comments, inline comments, and
  2. Check both issue and inline comments for
  3. Confirm that the checked-out commit and the pull request's current head both
  4. Read the root instructions and every instruction file that scopes a changed
  5. Review the code against the standard above. For each finding, record its
  6. Emit one best-effort stats event before returning, including clean and
  7. Print the findings or No issues found. and list pull-request-description
  8. With --comment, post one top-level comment for all title or description
  9. If the code review is clean and step 8 did not post a description comment,
  10. Otherwise, post one inline comment per unique code finding. Begin each body

What it can do on your machine

Read from SKILL.md and the folder at commit c468793. 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:

    • Bash(gh pr comment:*)
    • Bash(gh pr diff:*)
    • Bash(gh pr view:*)
    • Bash(gh api:*)
    • Bash(git diff:*)
    • Bash(git merge-base:*)
    • Bash(git rev-parse:*)
    • Bash(git show:*)
    • Bash(rg:*)
    • Bash(uv run infra/codehealth/log_stats.py:*)

    …and 1 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, 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 1.3k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 565 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 marin-community/marin at commit c468793, republished under its Apache-2.0 licence (© marin-community). 565 words, ~1,287 tokens.

Download SKILL.mdSave it as .claude/skills/review-pr/SKILL.md (or your agent's skills folder).
name
review-pr
description
Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations.
allowed-tools
Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*), Bash(gh api:*), Bash(git diff:*), Bash(git merge-base:*), Bash(git rev-parse:*), Bash(git show:*), Bash(rg:*), Bash(uv run infra/codehealth/log_stats.py:*), mcp__github_inline_comment__create_inline_comment

Review a pull request

Review the requested pull request at the exact head named by the caller. The review is read-only except for comments posted when --comment is requested.

Review standard

A reviewable Marin pull request:

  • Implements the behavior claimed by its title and description without an introduced correctness, security, state-transition, or error-handling defect.
  • Follows the root and path-scoped AGENTS.md or CLAUDE.md instructions. If tests change, it also follows root TESTING.md and any scoped testing guide.
  • Keeps public interfaces, invariants, dependency direction, configuration, and types coherent across every changed call site. Marin does not preserve backward compatibility unless the request explicitly requires it.
  • Uses tests for behavior rather than implementation details, incidental prose, private state, tautologies, or mocks below an I/O boundary.
  • Keeps abstraction proportional to demonstrated reuse. Flag a maintainability problem only when the change creates a concrete structural obstacle, hidden assumption, or distant coupling that materially constrains nearby work.
  • Keeps documentation synchronized with behavior. The pull-request title and body must follow .agents/skills/writing-style/pull-requests.md; the body is the squash-merge commit message, not a template, file inventory, or test log.

Report only actionable defects introduced by the pull request. Validate every finding against the diff, relevant surrounding code, and applicable instructions. Do not report style preferences, speculative failures, harmless duplication in experiments/grug, or pre-existing problems. If the evidence is uncertain, omit the finding.

Workflow

  1. Inspect the pull request metadata, issue comments, inline comments, and current head. Stop without commenting when the pull request is closed, a draft, an automated dependency update, or too trivial to benefit from code review. Still review agent-generated pull requests.

  2. Check both issue and inline comments for <!-- marin-correctness-review -->. Stop when a prior automated correctness review is present unless a maintainer explicitly requested another review.

  3. Confirm that the checked-out commit and the pull request's current head both match the requested head. If either differs, report the stale review and post nothing.

  4. Read the root instructions and every instruction file that scopes a changed path. Read the root and scoped testing guides when tests change. Inspect the complete diff and enough surrounding code to validate behavior and call-site consistency.

  5. Review the code against the standard above. For each finding, record its changed file and line, category (bug, instruction-following, or maintainability), concrete impact, and the evidence that makes it certain. Separately record title or description problems.

  6. Emit one best-effort stats event before returning, including clean and non-commenting reviews. Never retry or surface a telemetry failure. Run from the repository root:

    bash
    cat <<'EOF' | uv run infra/codehealth/log_stats.py
    {
      "tool": "review-pr",
      "invocation": {
        "trigger": "local",
        "agent_cli": "codex",
        "pr_number": <PR>,
        "agent_exit_code": 0,
        "timed_out": false
      },
      "findings": [
        ["<file>", <line>, "<category>", 1.0, "<first 200 chars of issue description>"]
      ]
    }
    EOF

    Use an empty findings array when the code review is clean.

  7. Print the findings or No issues found. and list pull-request-description problems separately. Without --comment, stop here.

  8. With --comment, post one top-level comment for all title or description problems. Begin with 🤖, name each concrete problem and fix, and end with <!-- marin-correctness-review -->.

  9. If the code review is clean and step 8 did not post a description comment, post exactly this top-level comment. Otherwise stop after the description comment.

    markdown
    🤖 Code review
    
    No issues found.
    
    <!-- marin-correctness-review -->
  10. Otherwise, post one inline comment per unique code finding. Begin each body with 🤖, explain the defect and its impact, and end with <!-- marin-correctness-review -->. Include a committable suggestion only when that suggestion completely fixes a small, self-contained issue. Use a full-SHA GitHub link with surrounding context when citing repository instructions or related code.

Show full SKILL.md (19 more words)Show less

Use gh for GitHub reads and top-level comments. Post inline comments with the GitHub inline-comment tool and confirmed: true.

© marin-community, Apache-2.0. 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 .agents/skills/review-pr of marin-community/marin.

Open the folder on GitHubat commit c468793

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 skillmarin-community/marin3.9k—~1.3kAutomated safety check: PassApache-2.0
Finishing a Development Branchobra/superpowers297k5 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
PR Design DocOpenHands/OpenHands91k—~2.4kAutomated safety check: PassMIT
WooCommerce Code Reviewwoocommerce/woocommerce11k3 repos~1.1kAutomated safety check: PassCustom licence

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.

    297k 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
  • 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…

    91k 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
  • Record PR Demo

    payloadcms/payload

    A skill your agent uses when a Payload pull request needs a concise visual walkthrough for reviewers.

    45k GitHub stars~1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from marin-community/marin

All 41 skills in this repo
  • Noslop

    marin-community/marin

    Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Use Iris

    marin-community/marin

    Use Iris to submit, inspect, debug, monitor, or recover jobs and tasks; diagnose scheduling and federation; deploy controllers; or reserve dev GPUs and TPUs.

    3.9k GitHub stars~745 tokensUpdated today
    Auto-check passed
  • Launch Rl

    marin-community/marin

    Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.

    3.9k GitHub stars~894 tokensUpdated today
    Auto-check passed
  • Marina Applet

    marin-community/marin

    Build, validate, publish, update, inspect, query, roll back, or archive a dynamic Marina applet.

    3.9k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Query Finelog

    marin-community/marin

    Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Trace Pulumi Diff

    marin-community/marin

    Run a read-only preview for a specified Marin infra/pulumi stack and trace each pending resource change to merged pull requests since its latest successful update when that update records a clean…

    3.9k GitHub stars~663 tokensUpdated today
    Auto-check passed

Categories

Questions about Review PR

What does Review PR do?

Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations. Review PR is an agent skill from marin-community/marin. Review an explicitly identified Marin pull request against the repository's correctness and maintainability expectations.

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 marin-community/marin --skill review-pr -a claude-code`. Or copy the skill folder (.agents/skills/review-pr in marin-community/marin) 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 marin-community/marin --skill review-pr -a codex`. Or copy the skill folder (.agents/skills/review-pr in marin-community/marin) 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 marin-community/marin --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 (uv). Its frontmatter pre-approves these tools: Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*), Bash(gh api:*), Bash(git diff:*), Bash(git merge-base:*), Bash(git rev-parse:*), Bash(git show:*), Bash(rg:*), Bash(uv run infra/codehealth/log_stats.py:*), mcp__github_inline_comment__create_inline_comment.

Does Review PR access the network?

SKILL.md contains no URLs. Its commands use uv, 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 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 Apache-2.0 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 1.3k tokens (SKILL.md is roughly 5.1k 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, 297k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars) and PR Design Doc (OpenHands/OpenHands, 91k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review PR?

marin-community (a GitHub organization) maintains it in marin-community/marin, which has 3,921 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 10, 2026.

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