Hire an AI bug fix evidence reviewer

Everything it can hand back

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

• Reproduction brief
• Coverage gaps
• Verified, partial or blocked bug receipt

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 report is vague and you cannot make the bug happen on your machine.

• Reproduction brief. Expected and actual behavior, the environment, the smallest failing case and what happened on repeat runs.
• Coverage gaps. Missing, weak and stale tests, ranked from P0 to P3, each with a suggested test.
• Bug receipt. One block marked VERIFIED, PARTIAL or BLOCKED, with problem, root cause, change, proof and gaps.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• 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

• Bug reproduction evidence writer. Share an unclear bug report. Get repeatable steps, a minimal case and the evidence still needed.
• Test coverage gap investigator. Share your repo or change. Get missing, weak and stale tests ranked by the behavior at risk.
• Bug fix evidence recorder. Share a fix and its checks. Get a dated record of what is verified, partial or blocked.

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 turn-a-bug-report-into-proof 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/turn-a-bug-report-into-proof/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 bug report, as you received it
• Your repo, or the part of the code the bug touches
• Error messages or logs, with secrets removed (optional)
• The fix and the checks you ran on it, for the last step (optional)

Functions and deliverables

• Bug fix evidence reviewer: Share a bug report, code and fix evidence. Get a repeatable case, ranked test gaps and a record of verified or blocked checks.
  • Reproduction brief
  • Coverage gaps
  • Verified, partial or blocked bug receipt
• Bug reproduction evidence writer: Turn a vague bug report into a bug reproduction brief: exact steps, a minimal failing case, and the evidence you still need. No fix is made.
  • A short brief with expected and actual behaviour side by side
  • The smallest steps and data that still show the bug
  • A clear answer on whether it repeats: yes, no or intermittent
  • The commands and outputs that back it up
  • A list of what is still unknown
  Source: GitHub Copilot community.
• Software test gap finder: Share your repo or change. Get missing, weak and stale tests ranked by the behavior at risk.
  • A list of test gaps ranked from P0 (most serious) to P3.
  • For each gap, the code and test locations as path:line.
  • A specific test to add for each gap, with the scenario to check.
  • A short plan that says which tests to write first.
  • A list of checks that ran and checks that were skipped.
  Source: GitHub Copilot community.
• Bug fix evidence recorder: Close a bug fix with a bug fix evidence recorder. Give it the defect and your checks. You get a receipt marked verified, partial or blocked.
  • A seven-line receipt: problem, baseline, root cause, change, proof, gaps and source
  • A status of verified, partial or blocked
  • The single next step needed if proof is missing
  • A note on whether each check was run now or supplied by you
  • A JSON version of the receipt for CI (optional, needs code running)
  Source: GitHub Copilot community.
• 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 report is vague and you cannot make the bug happen on your machine.
• You have a fix and need proof that it works, not a claim.
• You want to know which tests would have caught the bug.

Limits to check before starting

• You want the bug fixed and a pull request written: use Bug repair and pull request reviewer.
• You can already repeat the bug and only need its cause: use Bug root cause finder.
• You only need a clear ticket for a developer: use Bug report writer.

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.

• Add the complete skill pack to an AI that can read your repo and run commands, such as Claude Code.
• Share the bug report and the repo. Take secrets out of any logs first.
• Ask it to follow the steps and mark any missing facts.
• Read the repeatable case before step 2. If the AI cannot repeat the bug, the receipt will say blocked.
• Review the result before approving external actions.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/turn-a-bug-report-into-proof 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.