Hire an AI bug repair and pull request reviewer

Everything it can hand back

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

• The cause of the bug, shown with evidence and agreed by you
• The smallest fix, checked by re-running the failing test
• A list of behaviours the fix touches that no test checks, and the tests to add
• A review of the fix against your standards and the issue
• A pull request showing the failing run before and the passing run after

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 bug keeps coming back after being fixed.

• Cause and fix. The reproduction, where it goes wrong, the proven cause for your yes, the smallest fix and the rerun.
• Missing tests. A table of what the fix changes, which parts no test covers, and the tests to add.
• Review. Findings against your standards and the issue, with a verdict.
• Pull request. A summary with the failing run before and the passing run after, plus what could go wrong on merge.
• Hand-back summary. Each step's file and one list of everything marked MISSING.

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. Step 3 used the tests you added, not step 2's report.
• The cause was shown with evidence and you said yes before any code was edited.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• 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

• Prove the cause, then fix. Reproduces the bug, narrows it down with temporary debug lines, states the cause for your yes, then makes the smallest fix and re-runs the failing test.
• Find the missing tests. Reads the fix and lists what it changes. Marks each change covered or not and proposes a test that would have caught the bug.
• Add the tests (your turn). You add the proposed tests, with one that fails on the old code, and run them.
• Review the fix. Compares the fix and its tests with your written standards and with the issue, and reports both side by side.
• Write the pull request. Describes the cause and the fix in a small picture, with the failing run before and the passing run after.

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 fix-a-bug-with-proof-and-a-clear-pull-request 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/fix-a-bug-with-proof-and-a-clear-pull-request/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

• What is broken, how to trigger it and the exact error if you have it
• Access to your project code
• Your written coding standards or the original issue (optional)

Tools and access

• Claude Code: It can run git, read the standards files and run the two reviews as separate helpers.
• Claude, ChatGPT or Gemini in a plain chat: Works if you paste the diff, the ticket and the standards. Reviews then run one after the other.

Functions and deliverables

• Bug repair and pull request reviewer: Reproduce a bug, verify its cause, make a focused fix and review the tests before writing the pull request.
  • The cause of the bug, shown with evidence and agreed by you
  • The smallest fix, checked by re-running the failing test
  • A list of behaviours the fix touches that no test checks, and the tests to add
  • A review of the fix against your standards and the issue
  • A pull request showing the failing run before and the passing run after
• Bug root cause finder: Use failing tests and code to investigate a bug, then review its cause before fixes.
  • The exact error captured
  • A narrowed-down location
  • A root cause for your approval
  • A minimal fix after you agree
  • Proof that tests pass
  Source: sickn33.
• Code change test coverage reviewer: Find what a code change does that no test checks. Give it your diff and tests. Get each behaviour marked covered or not, plus test cases for gaps.
  • A list of new behaviours
  • A covered, not covered or unknown label for each
  • Evidence for each label
  • Proposed test cases for the gaps
  Source: Pro Skill Packs.
• Code change reviewer: Share a set of changes. Get a review against your coding standards and your spec, side by side.
  • A standards review, with each finding tied to the rule it breaks
  • A spec review, listing missing, extra and wrong behaviour
  • A one-line count of findings for each review
  • A note if no spec could be found
  Source: Matt Pocock.
• Pull request writer: Turn your code changes into a pull request description with a picture, proof it works, and a merge risk note that reviewers can scan fast.
  • Pull request body in a set template
  • A diagram, tree or code sketch of the change
  • Before and after evidence section
  • Merge risk rating
  Source: Matt Pocock.
• 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 bug keeps coming back after being fixed.
• Your AI keeps changing the wrong code and the error just moves.
• You need a fix a teammate can review without redoing the investigation.

Limits to check before starting

• You only have a vague report and no code access yet: use Bug fix evidence reviewer.
• A build in your CI is failing: use the GitHub check failure fixer.
• You only want an error message explained: use the Error and log debugger.

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 plus one skill file for each step.
• Open your project in Claude Code, give it the folder and say "Follow HANDOFF.md".
• Give it the steps that trigger the bug. When it states the cause, read it and say yes or no. It will not edit until you do.
• After the missing-test step, add the tests it proposes and run them. Make sure one fails on the old code.
• Read the review, then use the pull request text as it is or trim it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/fix-a-bug-with-proof-and-a-clear-pull-request 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.