Agent skill

Fastlane Pull Request Review

by fastlane in fastlane/fastlane

Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately.

MITAuto-check passedDevelopment

Install Fastlane Pull Request Review

skills CLI
$ npx skills add fastlane/fastlane --skill code-review -a claude-code

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

GitHub CLI
$ gh skill install fastlane/fastlane code-review --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/fastlane/fastlane.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/code-review .claude/skills/code-review && 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
code-review
GitHub stars
42k
Token cost
~550 tokens
SKILL.md length
327 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately.

  • Reviewing an incoming pull request to fastlane
  • SKILL.md covers Understand intent first, Verify before reporting, What to look for and Reporting
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Checking a change against the issue it claims to resolve

What it does

Review starts from intent. The agent reads the linked issue and its comments with the GitHub MCP server, then the description, checks the change against what the issue asked, including any request to audit or discuss other places first, and searches earlier pull requests and issues touching the same code for decisions already made. The change is held to AGENTS.md and the guides it lists for the touched files.

Every claim is verified against the code before it is raised, and unconfirmed findings are not posted. If a change introduces a vulnerability, or exposes an existing one in public, the agent does not describe or demonstrate it, and leaves one short comment asking for maintainer security review or pointing the contributor to the private reporting guide.

Blocking findings include a fix whose spec would also pass before the fix, behavior without a spec for each branch, validator and error case, a new pattern where the codebase already has one, contradictions of the design doc, changes that break existing Fastfiles, and docs that no longer match the code. Naming and simpler rewrites are non-blocking, scope is one concern per PR, and each finding cites file, line and the guide rule.

When your agent uses it

  • Reviewing an incoming pull request to fastlane
  • Checking a change against the issue it claims to resolve
  • Spotting changes that could break users' existing Fastfiles

Example prompts

  • “Review this fastlane pull request against its linked issue.”
  • “Does this PR change an action's defaults in a way that breaks existing Fastfiles?”
  • “Check whether this fix has a spec that would fail without the fix.”

Requirements

  • The GitHub MCP server
  • A checkout of the fastlane repository with its AGENTS.md and guides

What it can do on your machine

Read from SKILL.md and the folder at commit d7c3068. 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.

    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

Fastlane Pull Request Review loads about 550 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 327 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~550

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 fastlane/fastlane at commit d7c3068, republished under its MIT licence (© fastlane). 327 words, ~550 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder).
name
code-review
description
Use when reviewing a pull request to fastlane.

Reviewing a fastlane pull request

Hold the change to AGENTS.md and the guides it lists for the files the pull request touches.

Understand intent first

  • Read the issue the description links ("Resolves #N", "Fixes #N") and its comments with the GitHub MCP server, then the description. Review the change against what the issue asks, including any request to audit, discuss or check other places before changing this one. Report it when that was not done.
  • Search for earlier pull requests and issues about the same code, to find decisions already made.

Verify before reporting

  • Check every claim against the code before raising it. Do not post a finding you could not confirm.
  • If the change introduces a vulnerability, do not describe it, show how to exploit it, or suggest a fix that reveals it. Leave one short comment that the change needs a security review by a maintainer before it is merged, without details.
  • If the change exposes or fixes an existing vulnerability in public, do not describe it either. Leave one short comment pointing the contributor to SECURITY.md to report it privately.

What to look for

Blocking
  • A fix whose spec would also pass against the code before the fix.
  • New behaviour without a spec for each branch, validator and error case.
  • A new pattern where the codebase already solves the same problem. Name the existing one: for two options that can replace each other, delete_keychain (:name and :keychain_path).
  • A change that contradicts Design.md, or works around one of its known limits in a single action.
  • A bug, or a change to an action's options, defaults or outputs that breaks existing Fastfiles.
  • example_code, details or option descriptions that no longer match what the code does after the change.
Non-blocking
  • A simpler way to write the same thing.
  • Naming, comments, readability.
Scope
  • One concern per pull request: name what to split out.

Reporting

Give each finding its file and line, and the guide rule it rests on.

© fastlane, 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 .github/skills/code-review of fastlane/fastlane.

Open the folder on GitHubat commit d7c3068

Compare with similar skills

Fastlane Pull Request Review 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.

Fastlane Pull Request Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fastlane Pull Request Review this skillfastlane/fastlane42k—~550Automated safety check: PassMIT
Address PR Feedback for ruby-gitruby-git/ruby-git1.8k—~657Automated safety check: PassMIT
Pull Request Review Workflowruby-git/ruby-git1.8k—~1.6kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT

Similar skills

  • Addresses unresolved pull request review threads and suppressed (low-confidence) Copilot review comments on the current branch, folds each fix into the…

    1.8k GitHub stars~657 tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Reviews a GitHub pull request against the ruby-git project standards, shows findings first, and posts review comments with the gh CLI only after you approve.

    1.8k GitHub stars~1.6k tokensUpdated 6 days ago
    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
  • 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 yesterday
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Official

    Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.

    48k GitHub stars~767 tokensUpdated yesterday
    DevelopmentAuto-check passed

Works with

Categories

Questions about Fastlane Pull Request Review

What does Fastlane Pull Request Review do?

Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately. Review starts from intent. The agent reads the linked issue and its comments with the GitHub MCP server, then the description, checks the change against what the issue asked, including any request to audit or discuss other places first, and searches earlier pull requests and issues touching the same code for decisions already made.

When should I use Fastlane Pull Request Review?

Fastlane Pull Request Review fits situations like: reviewing an incoming pull request to fastlane; checking a change against the issue it claims to resolve; spotting changes that could break users' existing Fastfiles.

How do I install Fastlane Pull Request Review in Claude Code?

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

How do I install Fastlane Pull Request Review in Codex?

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

Can I use Fastlane Pull Request Review 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 fastlane/fastlane --skill code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.

What does Fastlane Pull Request Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Fastlane Pull Request Review is instructions for the agent only. Our summary lists: The GitHub MCP server; A checkout of the fastlane repository with its AGENTS.md and guides.

Does Fastlane Pull Request Review 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 Fastlane Pull Request Review 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 Fastlane Pull Request Review use?

Fastlane Pull Request Review 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 Fastlane Pull Request Review use?

About 550 tokens (SKILL.md is roughly 2.2k 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 Fastlane Pull Request Review?

Skills that share tags, products or a category with Fastlane Pull Request Review: Address PR Feedback for ruby-git (ruby-git/ruby-git, 1.8k stars), Pull Request Review Workflow (ruby-git/ruby-git, 1.8k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars) and GitHub Review Iteration (prisma/orm, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fastlane Pull Request Review?

fastlane (a GitHub organization) maintains it in fastlane/fastlane, which has 42,207 GitHub stars. The repository was last updated on October 7, 2026.

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