Agent skill

PR Review Navigator

by commercetools in commercetools/ui-kit

Generate AI-assisted navigation aids to help humans start reviewing a pull request more efficiently.

MITAuto-check: notesDevelopment

Install PR Review Navigator

skills CLI
$ npx skills add commercetools/ui-kit --skill pr-review-navigator -a claude-code

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

GitHub CLI
$ gh skill install commercetools/ui-kit pr-review-navigator --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/commercetools/ui-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pr-review-navigator .claude/skills/pr-review-navigator && 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
pr-review-navigator
GitHub stars
154
Token cost
~1.3k tokens
SKILL.md length
435 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Generate AI-assisted navigation aids to help humans start reviewing a pull request more efficiently.

  • Works in 8 steps: Fetch PR Information → Fetch the Diff → Analyze Dependencies → …
  • Starting a PR review to get oriented on large
  • SKILL.md covers Arguments, Process, Output Format and Guidelines
  • Calls gh and git; reaches github.com

What it does

PR Review Navigator is an agent skill from commercetools/ui-kit. Generate AI-assisted navigation aids to help humans start reviewing a pull request more efficiently. Use when starting a PR review to get oriented on large or unfamiliar changes.

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 licence is MIT.

When your agent uses it

  • Starting a PR review to get oriented on large
  • Unfamiliar changes

Example prompts

  • “/pr-review-navigator”

Requirements

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

Workflow steps

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

  1. Fetch PR Information
  2. Fetch the Diff
  3. Analyze Dependencies
  4. Determine Review Order
  5. Generate Mermaid Diagram
  6. Create Review Table
  7. Construct File Links
  8. Output the Result

What it can do on your machine

Read from SKILL.md and the folder at commit 62ca335. 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
    • Grep
    • Glob
    • Read

    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

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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

PR Review Navigator loads about 1.3k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 435 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
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: notes

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

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Grep, Glob, Read

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 commercetools/ui-kit at commit 62ca335, republished under its MIT licence (© commercetools). 435 words, ~1,307 tokens.

Download SKILL.mdSave it as .claude/skills/pr-review-navigator/SKILL.md (or your agent's skills folder).
name
pr-review-navigator
description
Generate AI-assisted navigation aids to help humans start reviewing a pull request more efficiently. Use when starting a PR review to get oriented on large or unfamiliar changes.
allowed-tools
Bash, Grep, Glob, Read
disable-model-invocation
false
argument-hint
[pr-number] [--comment]
scope
github, review

PR Review Navigator

Generate navigation aids to help humans review pull requests more efficiently. Provides orientation and structure, not pre-review or judgment.

Important constraints:

  • No interpretation of business intent or purpose, only factual descriptions of what changed

Arguments

  • pr-number (required): The PR number to review
  • --comment (optional): Post the navigator output as a PR comment. If omitted, write to a local markdown file.

Process

1. Fetch PR Information
bash
gh pr view $ARGUMENTS --json title,body,files,additions,deletions,url

Extract: changed files, additions/deletions count, PR URL for link construction.

For commits/branches without a PR, use git show --name-status and git diff.

2. Fetch the Diff
bash
gh pr diff <pr-number>

Understand file contents and relationships from the diff.

3. Analyze Dependencies

Read imports/references in the diff to determine which files depend on which.

4. Determine Review Order

Based on dependency flow, use outside-in ordering:

  1. API endpoints, HTTP routes, GraphQL resolvers
  2. Service/business logic layer
  3. Repository/persistence layer
  4. Data models/entities
  5. Wiring/configuration
  6. Unit tests (after the implementation files they test)
  7. Cornichon/integration tests last (they test the full stack from outside)
5. Generate Mermaid Diagram

Create a flowchart TB showing:

  • All changed files as nodes with circled numbers: ①, ②, ③, etc.
  • Dependency relationships (arrows showing "depends on" or "uses")
  • Test files connected to implementation files they test
  • Subgraphs grouped by architectural layer
  • Color coding: unit tests green (fill:#e8f5e9), integration tests blue (fill:#e3f2fd, dashed border)

Node format: ["① filename.ext<br/><i>one-liner</i>"]

Cornichon test styling:

mermaid
subgraph "🧪 Integration Tests (Cornichon)"
    style IntegrationTests fill:#e3f2fd,stroke:#1976d2,stroke-width:2px,stroke-dasharray: 5 5
    ...
end
6. Create Review Table

A numbered table with columns:

  • # - Review order number
  • File - Filename (short, without full path)
  • What it does - One factual sentence about what the file contains/does
  • Link - Anchor link to the file in the PR
Show full SKILL.md (169 more words)Show less

GitHub uses SHA256 hashes of file paths for PR file anchors:

bash
hash=$(echo -n "<filepath>" | shasum -a 256 | cut -d' ' -f1)
# Link: https://github.com/{owner}/{repo}/pull/{number}/files#diff-{hash}

Use the file path exactly as returned by gh pr view --json files. Compute the hash for each file.

For commits/branches without a PR, omit the Link column.

8. Output the Result

If --comment flag is provided, post as a PR comment:

bash
gh pr comment <pr-number> --body "<content>"

If --comment is NOT provided, write to pr-review-navigator.md in the workspace root and inform the user of the file path.

Output Format

The output (whether file or comment) should be valid markdown structured as:

markdown
## AI Review Navigator

**Summary:** <one factual sentence about what was added/changed/removed>

---

### File Relationships & Review Order

\`\`\`mermaid
flowchart TB
subgraph "1️⃣ API Layer"
A["① FeatureXController.scala<br/><i>HTTP endpoints</i>"]
end

    subgraph "2️⃣ Service Layer"
        B["② FeatureXService.scala<br/><i>Business logic</i>"]
    end

    subgraph "3️⃣ Unit Tests"
        C["③ FeatureXServiceSpec.scala"]
    end

    subgraph IntegrationTests ["🧪 Integration Tests (Cornichon)"]
        D["④ FeatureXFeature.scala"]
    end

    A --> B
    B -.->|tested by| C
    A -.->|tested by| D

    style C fill:#e8f5e9
    style IntegrationTests fill:#e3f2fd,stroke:#1976d2,stroke-width:2px,stroke-dasharray: 5 5

\`\`\`

---

### Suggested Review Order

| #   | File                        | What it does                 | Link         |
| --- | --------------------------- | ---------------------------- | ------------ |
| 1   | `FeatureXController.scala`  | HTTP endpoints for FeatureX  | [View](link) |
| 2   | `FeatureXService.scala`     | Business logic               | [View](link) |
| 3   | `FeatureXServiceSpec.scala` | Unit tests for service layer | [View](link) |
| 4   | `FeatureXFeature.scala`     | Cornichon integration tests  | [View](link) |

Summary rules:

  • State only facts about what changed
  • Do NOT interpret purpose, intent, or business value
  • Do NOT use phrases like "optimized for", "designed to", "intended for"

Guidelines

  • This skill assists with review orientation only. The human reviewer makes all judgments about code quality, correctness, and approval.
  • If the PR is too large (>30 files), suggest reviewing in logical chunks.
  • Wrap the mermaid diagram in triple backticks with mermaid language identifier so GitHub renders it as a diagram.

© commercetools, 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/pr-review-navigator of commercetools/ui-kit.

Open the folder on GitHubat commit 62ca335

Compare with similar skills

PR Review Navigator 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.

PR Review Navigator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR Review Navigator this skillcommercetools/ui-kit154—~1.3kAutomated safety check: NotesMIT
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/OpenHands90k—~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…

    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
  • 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 commercetools/ui-kit

All 11 skills in this repo
  • Agent Restore Context

    commercetools/ui-kit

    Manage restore context files so skills can survive /clear and /compact.

    154 GitHub stars~944 tokensUpdated 6 days ago
    Auto-check: notes
  • Agent Restore Context Setup

    commercetools/ui-kit

    Set up the restore-context hook so skills can resume workflows after /clear and /compact.

    154 GitHub stars~1.4k tokensUpdated 6 days ago
    Auto-check: notes
  • Remember

    commercetools/ui-kit

    Persist guidelines, conventions, and architectural decisions into the repository's knowledge base.

    154 GitHub stars~2k tokensUpdated 6 days ago
    Auto-check: notes
  • Renovate Review

    commercetools/ui-kit

    Review Renovate dependency upgrade PRs to assess safety and effort.

    154 GitHub stars~907 tokensUpdated 6 days ago
    Auto-check: notes
  • Repo Healthcheck Node

    commercetools/ui-kit

    Verify a Node.js/TypeScript repo's development environment is correctly set up.

    154 GitHub stars~1.6k tokensUpdated 6 days ago
    Auto-check: notes
  • Repo Maintenance Node

    commercetools/ui-kit

    Perform a broad Node/TypeScript repository health sweep — formatting, linting, type errors, dead code, dependency hygiene, and open Renovate PRs.

    154 GitHub stars~3k tokensUpdated 6 days ago
    Auto-check: notes

Categories

Questions about PR Review Navigator

What does PR Review Navigator do?

Generate AI-assisted navigation aids to help humans start reviewing a pull request more efficiently. PR Review Navigator is an agent skill from commercetools/ui-kit. Generate AI-assisted navigation aids to help humans start reviewing a pull request more efficiently.

When should I use PR Review Navigator?

PR Review Navigator fits situations like: starting a PR review to get oriented on large; unfamiliar changes.

How do I install PR Review Navigator in Claude Code?

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

How do I install PR Review Navigator in Codex?

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

Can I use PR Review Navigator 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 commercetools/ui-kit --skill pr-review-navigator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-review-navigator, .gemini/skills/pr-review-navigator, .github/skills/pr-review-navigator and .opencode/skills/pr-review-navigator in your project.

What does PR Review Navigator need to run?

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

Does PR Review Navigator access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is PR Review Navigator safe to install?

Our automated static check of SKILL.md found notes only (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 PR Review Navigator use?

PR Review Navigator 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 PR Review Navigator use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 PR Review Navigator?

Skills that share tags, products or a category with PR Review Navigator: 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, 90k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Review Navigator?

commercetools (a GitHub organization) maintains it in commercetools/ui-kit, which has 154 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 3, 2026.

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