Voyage Digital
    Skills· Software Development & Technical Infrastructure

    The Bug Report Protocol

    Turns a freeform bug description into a structured bug report that can be entered directly into your ticketing system, with reproducible steps, a clear separation between expected and actual behavior, environment data, and a severity estimate.

    structuringwriting

    Description

    A bug report that saves hours of follow-up questions has a fixed shape: reproducible steps, a clear separation between what should happen and what actually happens, complete environment data, and an assessment of urgency. This protocol takes an unstructured report, whether it comes from support, QA, or directly from the product team, and shapes it into exactly that pattern.

    It is built for anyone who passes bugs on to a development team without working in a ticketing system every day: customer reports, internal observations, test logs. The result can be entered directly into Jira, Linear, or GitHub Issues.

    The protocol does not judge whether a reported behavior is actually a bug, and it estimates severity only as well as the information provided allows. Where environment data or reproduction steps are missing, the assistant flags this as an open gap instead of inventing it.

    Example scenario

    A customer reports that the app keeps crashing whenever they click the button. This description is passed to the AI, along with the browser and operating system. What comes back is a structured bug report with a searchable title, five exact reproduction steps, complete environment data, and the assessment Major, functional limitation, with the workaround of temporarily using a desktop browser.

    Steps

    Every step shows who carries it out: icon, colour and label together indicate whether a person acts, whether it runs automatically, whether a result is produced, or whether an approval is required.

    01Person

    The description states what happens and what was expected instead, supplemented with the available environment data.

    02Automated

    03Automated

    04Automated

    05Result

    Key
    PersonAutomatedResultApproval

    In use

    Bug description: what happens, what should happen instead

    Required

    Steps to reproduce, rough or detailed

    Required

    Environment: browser, operating system, version, device

    Optional

    Screenshots, logs, frequency, impact

    Optional

    Output

    A nine-part bug report with title, summary, numbered reproduction steps, expected and actual behavior, environment data, severity estimate, workaround, and supplementary information.

    Skill Text

    Copy the prompt below in full into your AI tool. As a file: bugreport-protokoll.en.json

    # DESCRIPTION
You turn bug descriptions into structured, directly actionable bug reports. Focus: reproducibility, a clean separation between expected and actual behavior, complete environment information. Where information is missing, explicitly mark missing or assumed information as an assumption instead of silently filling it in.

# INPUT
- Bug description (what happens, what should happen instead)
- Steps to reproduce, rough or detailed
- Optional: screenshots or logs, environment (browser, operating system, version), frequency, impact

# OUTPUT
A structured bug report with the following sections:
1. Title: short, descriptive, easy to find
2. Summary: one sentence naming the problem
3. Steps to reproduce: numbered, exact
4. Expected behavior
5. Actual behavior
6. Environment: browser, operating system, version, device
7. Severity and priority: Critical, Major, Minor, or Trivial
8. Workaround, if one exists
9. Additional information: logs, screenshots, context

# CONTEXT
- Reproducibility is the single most important criterion for a usable bug report.
- Severity and priority are two different dimensions and are never mixed up.
- A bug report addresses exactly one issue. Do not combine multiple symptoms into one report.
- Screenshots and logs are valuable and are always included when available.

# WORKING INSTRUCTIONS
## Step 1: Understand the bug
Work out the core of the problem from the user's description and separate it from pure symptoms.

## Step 2: Formulate title and summary
Write a concise, searchable title and a one-sentence summary.

## Step 3: Build reproduction steps
Document exact, numbered steps to reproduce the bug.

## Step 4: Document expected and actual behavior
Describe both states clearly separated, without mixing them.

## Step 5: Assess severity and workaround
Estimate severity (Critical, Major, Minor, Trivial), capture environment information, and document a workaround if one is known. Where information is missing, flag this in the report as an open assumption instead of inventing it.

# DEFINITION OF DONE
[ ] Title is short, descriptive, and searchable
[ ] Reproduction steps are exact and numbered
[ ] Expected and actual behavior are clearly separated
[ ] Environment information is complete or flagged as missing
[ ] Severity is estimated
[ ] The report addresses exactly one bug

# ADDRESSING THE USER
Address the user in a professional manner throughout.

# CONVERSATION START
Which bug would you like to document? Describe the issue, what you expected, and what happened instead, and I will structure a clear bug report from it.

    Setup

    Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.

    ChatGPT

    OpenAI

    1. Copy the skill text above using the copy button.
    2. Click your profile picture and select "Skills".
    3. Click "Create skill" and paste the copied text as the instruction.
    4. Adjust inputs, outputs and format where your case requires it.
    5. Save the skill. It is available in all chats from that point on.
    Documentation

    Anthropic

    1. Copy the skill text above using the copy button.
    2. Open claude.ai and go to "Skills" in your profile.
    3. Create a new skill and paste the copied text as the instruction.
    4. The skill works in claude.ai, in Claude Code and through the API.
    5. Available on the Pro, Max, Team and Enterprise plans.
    Documentation

    Microsoft

    1. Copy the skill text above using the copy button.
    2. Open Copilot Studio and create a new agent.
    3. Paste the copied text as the instruction.
    4. Connect knowledge sources and tools where needed.
    5. Publish the agent for yourself or for your organisation.
    Documentation

    1. Copy the skill text above using the copy button.
    2. Open the sidebar and click "Add skill".
    3. Paste the copied text directly as the instruction.
    4. Connect the skill to integrations such as Gmail or Slack where needed.
    5. Save the skill and release it for yourself or your team.
    Documentation

    Implementation

    1. Copy the skill text

      The skill text is copied into the chosen AI tool, and the bug is described the way it was noticed.

    2. Add environment data

      Browser, operating system, and screenshots are added, they noticeably increase the value of the bug report.

    3. Review the result

      The finished report is reviewed and entered directly into the ticketing system, for example Jira, Linear, or GitHub Issues.

    Last reviewed:

    In the workshop this becomes your method.

    A single prompt becomes a repeatable method. We show that in the workshop From Prompt to Method.

    View workshops

    Related resources

    Browse all resources
    Skills

    The API Playbook

    The API Playbook turns a technical API specification into complete, developer-friendly documentation, from a quick start guide to a full endpoint and error reference.

    Learn more
    Assistants

    The Documentation Writer

    Creates complete, understandable technical documentation from product information, technical specifications and a defined audience, from the product overview through installation and usage to troubleshooting and glossary.

    Learn more
    Skills

    The Review Protocol

    Turns rough code review notes into structured, constructive review feedback with severity-sorted remarks, rationale, and a clear approve/request-changes/comment recommendation.

    Learn more
    Stripe Agent Skills
    Tools

    Stripe Agent Skills

    Stripe Agent Skills is Stripe's official collection of agent skills for best practices, project setup and version upgrades, giving AI coding agents current, correct patterns for building Stripe integrations.

    Learn more
    Skills

    The MCP Builder

    Guides you through research, implementation, testing and evaluation of an MCP server: typed tools, clean error handling, pagination and ten verified evaluation questions for reliable access by a language model to an external service.

    Learn more
    Assistants

    The VBA Translator

    Translates automation tasks in Excel into working VBA code based on the concrete file structure, and debugs existing macros.

    Learn more
    Supabase
    Tools

    Supabase

    Supabase is an open source backend-as-a-service platform built on Postgres, providing database, authentication, storage, and edge functions in a single tool.

    Learn more
    Vercel
    Tools

    Vercel

    Git-centered deployment and hosting platform for web applications, with a built-in AI model gateway, isolated sandboxes for agent-generated code, and a security and observability stack in one interface.

    Learn more
    Windsurf
    Tools

    Windsurf

    Windsurf is an AI native code editor built on VS Code, with an autonomous Cascade agent for multi file changes, fast context aware tab completion, and inline chat.

    Learn more
    Workflows

    The Quote Pipeline

    A workflow that automatically turns an incoming quote request into a reviewed quote draft, from requirements extraction through to sales approval.

    Learn more

    Conversation, not pitch

    Understand first, then decide. We take time for an initial conversation, without sales pressure, without obligation.

    Schedule a call