Hire an AI pull request repair and approval reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A ranked list of risks, from security and breaking changes to slow queries and missing tests
• Fixes in the code for the comments you choose
• A one-page review with your notes sorted into blockers and small points
• A sign-off record that names the reviewer and what was checked

How it does the job well

• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: A pull request is open and a quick glance would not be enough.

• Step 1 file: risks. Findings ranked by severity, what the change could break, missing tests and what to fix first.
• Step 2 file: comment fixes. Numbered comments, what each one needs, which ones were fixed and the code that changed.
• Step 3 file: sign-off review. A one-page review with blockers, small points, the reviewer name and whether it is closed.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Rank the risks. Reads the diff and the pull request details, traces what the change could break and ranks the findings by severity.
• Post the findings (your turn). You choose the findings that matter and post them as comments on the pull request.
• Fix the comments. Reads every comment and thread, numbers them with what each fix needs, and applies the ones you pick.
• Sign off. Builds a one-page review of the fixed change, collects your notes and will not close while a blocker is open or no reviewer is named.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id review-a-pull-request-fix-the-comments-and-sign-off only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/review-a-pull-request-fix-the-comments-and-sign-off/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The open pull request, as a link or branch name
• Access to the project code
• Your name, or the person who signs off

Tools and access

• Claude Code, Codex or another AI coding tool: It can run the GitHub command line and the fetch script, and edit files in your repo.
• GitHub command line (gh): The fetch script uses it to read the pull request and its comments.

Functions and deliverables

• Pull request repair and approval reviewer: Share the pull request, review comments and code access. Get ranked risks, scoped fixes and a signoff record after a named reviewer approves.
  • A ranked list of risks, from security and breaking changes to slow queries and missing tests
  • Fixes in the code for the comments you choose
  • A one-page review with your notes sorted into blockers and small points
  • A sign-off record that names the reviewer and what was checked
• Pull request risk reviewer: Review a pull request for risk. Get issues ranked by severity, security findings and review comments you can post before you merge.
  • Findings ranked by severity
  • Security notes
  • Breaking change warnings
  • Test coverage gap
  • Ready-to-post review comments
  Source: Alireza Rezvani.
• Pull request comment repairer: Turn the review comments on your open GitHub pull request into a numbered list. Pick which to fix and your AI changes only those.
  • A numbered list of comments, reviews and review threads
  • The file, the request and a short fix note for each
  • Resolved and outdated threads marked
  • Code changes for the numbers you pick
  • A report of what changed, what was skipped, and the test result if tests ran
  Source: OpenAI.
• Human approval review planner: Get a human review gate for AI work: a one-page review, saved feedback, and a sign-off record before anything counts as done.
  • A one-page review view with anchored comments
  • Feedback saved as a countable file
  • A pass or fail gate status
  • A record that the review took place
  Source: Alireza Rezvani.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.

Tasks you can use it for

• A pull request is open and a quick glance would not be enough.
• You have review comments waiting and no time to work through them.
• You need a record that a person looked before the change went in.

Limits to check before starting

• You have a tiny change that a quick read covers: read it yourself and skip this workflow.
• Your pull request has no comments yet and you only want the risks: run the first step, the pull request risk reviewer, on its own.
• You want to plan ad tests or read campaign results: this workflow only covers code changes, so use a person or tool built for that.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Open your project in Claude Code, give it the folder and say "Follow HANDOFF.md". Claude Code may need a paid plan or an API key.
• Make sure the AI can read the pull request comments, for example through a signed-in GitHub command line. If it cannot, paste the comments in. Never paste a token into the chat.
• Give it the pull request. Read the ranked risks and post the ones you agree with as comments on the pull request.
• Tell it which numbered comments to fix. Check the changes.
• Open the review page, mark your notes as blockers or small points, then close it under your name.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/review-a-pull-request-fix-the-comments-and-sign-off for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.