Pm Bug Reporting logo

Pm Bug Reporting

Community
bobmatnyc
pm-bug-reporting

Bug reporting protocol for PM and agents to file GitHub issues

Overview

Publisherbobmatnyc
Repositoryclaude-mpm
Skill namepm-bug-reporting
Stars
152
Forks
34
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bobmatnyc on GitHub. Read the source before you install it.

Installation

Install the Pm Bug Reporting AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git /tmp/claude-mpm
mkdir -p .claude/skills
cp -r /tmp/claude-mpm/plugin/skills/mpm-bug-reporting .claude/skills/pm-bug-reporting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pm Bug Reporting in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pm Bug Reporting on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pm Bug Reporting is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PM Bug Reporting Protocol

When to Report Bugs

Report bugs when you encounter:

  • PM instruction errors or missing guidance
  • Agent malfunction or incorrect behavior
  • Skill content errors or outdated information
  • Framework crashes or unexpected behavior
  • Missing or incorrect documentation
  • Configuration errors or invalid defaults

GitHub Repositories

Route bugs to the correct repository:

Bug TypeRepositoryOwner/Repo
Core MPM (CLI, startup, config, orchestration)claude-mpmbobmatnyc/claude-mpm
Agent bugs (wrong behavior, errors, missing capabilities)claude-mpm-agentsbobmatnyc/claude-mpm-agents
Skill bugs (wrong info, outdated, missing content)claude-mpm-skillsbobmatnyc/claude-mpm-skills

External System Bug Routing

Decision tree:

  • Bug in MPM startup/config/delegation → bobmatnyc/claude-mpm
  • Bug in agent behavior → bobmatnyc/claude-mpm-agents
  • Bug in skill content → bobmatnyc/claude-mpm-skills
  • Bug in external system (installed via setup) → That system's GitHub repo

External systems installed via claude-mpm setup:

  • kuzu-memory → File issue at kuzu-memory's GitHub
  • mcp-vector-search → File issue at mcp-vector-search's GitHub
  • slack-user-proxy → File issue at slack-user-proxy's GitHub
  • google-workspace-mpm → File issue at google-workspace-mpm's GitHub
  • Other MCP servers → Check their GitHub repos

Examples:

  • "Vector search returns no results" → mcp-vector-search repo
  • "Kuzu memory fails to persist" → kuzu-memory repo
  • "PM fails to delegate" → claude-mpm repo
  • "Research agent crashes" → claude-mpm-agents repo

Bug Report Template

When creating an issue, include:

Title

Brief, descriptive title (50 chars max)

  • ✅ "PM delegates to non-existent agent"
  • ✅ "Research skill missing web search examples"
  • ❌ "Bug in system"
  • ❌ "Fix this"

Labels

Always include:

  • bug (required)
  • agent-reported (required)
  • Additional context labels:
    • high-priority - Critical functionality broken
    • documentation - Documentation error
    • agent-error - Agent-specific issue
    • skill-error - Skill content issue

Body Structure

markdown
## What Happened
[Clear description of the bug]

## Expected Behavior
[What should have happened]

## Steps to Reproduce
1. [First step]
2. [Second step]
3. [Third step]

## Context
- Agent: [agent name if applicable]
- Skill: [skill name if applicable]
- Error Message: [full error if available]
- Version: [MPM version if known]

## Impact
[How this affects users/workflow]

🤖👥 Generated with [Claude MPM](https://github.com/bobmatnyc/claude-mpm)

Footer rule: Always append the canonical MPM footer (🤖👥 Generated with [Claude MPM](https://github.com/bobmatnyc/claude-mpm)) to the issue body. Never use Claude Code's default 🤖 Generated with [Claude Code] footer — MPM only overrides the commit trailer, so the "Generated with" footer must be set explicitly or the Claude Code default leaks into GitHub issues.

Using gh CLI

Prerequisites Check

bash
gh auth status

If not authenticated:

bash
gh auth login

Creating Issues

Delegate to ticketing agent with:

Task:
  agent: ticketing
  task: Create GitHub issue for [bug type]
  context: |
    Repository: bobmatnyc/claude-mpm[-agents|-skills]
    Title: [brief title]
    Labels: bug, agent-reported
    Body: |
      ## What Happened
      [description]

      ## Expected Behavior
      [expected]

      ## Steps to Reproduce
      1. [step 1]
      2. [step 2]

      ## Context
      - Agent: [agent name]
      - Error: [error message]

      ## Impact
      [impact description]

Examples

Core MPM Bug

Task:
  agent: ticketing
  task: Create GitHub issue for core MPM bug
  context: |
    Repository: bobmatnyc/claude-mpm
    Title: PM fails to load configuration on startup
    Labels: bug, agent-reported, high-priority
    Body: |
      ## What Happened
      PM fails to initialize when configuration.yaml contains invalid syntax.
      No clear error message shown to user.

      ## Expected Behavior
      PM should display clear YAML syntax error with line number and fix suggestion.

      ## Steps to Reproduce
      1. Add invalid YAML to .claude-mpm/configuration.yaml
      2. Run `mpm`
      3. Observe generic error without details

      ## Context
      - Component: Configuration loader
      - Error: "Failed to load configuration"
      - Version: 5.4.x

      ## Impact
      Users cannot diagnose configuration errors, requiring manual YAML validation.

Agent Bug

Task:
  agent: ticketing
  task: Create GitHub issue for agent bug
  context: |
    Repository: bobmatnyc/claude-mpm-agents
    Title: Research agent fails to search with special characters
    Labels: bug, agent-reported, agent-error
    Body: |
      ## What Happened
      Research agent throws error when search query contains quotes or special chars.

      ## Expected Behavior
      Search queries should be properly escaped and executed.

      ## Steps to Reproduce
      1. Delegate to research: "Search for 'React hooks'"
      2. Research agent attempts search
      3. Error: "Invalid search query"

      ## Context
      - Agent: research
      - Error: grep command fails with unescaped quotes

      ## Impact
      Cannot search for quoted phrases or technical terms with special characters.

Skill Bug

Task:
  agent: ticketing
  task: Create GitHub issue for skill content error
  context: |
    Repository: bobmatnyc/claude-mpm-skills
    Title: Git workflow skill contains outdated branch strategy
    Labels: bug, agent-reported, documentation, skill-error
    Body: |
      ## What Happened
      Skill recommends `git flow` branching model, which project no longer uses.
      Current standard is trunk-based development.

      ## Expected Behavior
      Skill should document current trunk-based workflow.

      ## Context
      - Skill: git-workflow.md
      - Section: "Branching Strategy"
      - Line: 45-60

      ## Impact
      Agents follow outdated branching model, creating workflow friction.

Escalation Path

When ticketing agent is unavailable or gh CLI fails:

  1. Log locally for manual reporting:

    echo "[BUG] $(date): [description]" >> .claude-mpm/logs/bugs.log
  2. Report to PM for alternative action:

    PM should create ticket in primary ticketing system (Linear/JIRA)
    with note to create GitHub issue once available
  3. User notification:

    "Bug detected: [description]. Logged for manual GitHub issue creation."

Success Criteria

Bug reporting successful when:

  • ✅ Issue created in correct repository
  • ✅ All required labels applied (bug, agent-reported)
  • ✅ Body follows template structure
  • ✅ Title is clear and concise
  • ✅ Context includes agent/skill name if applicable
  • ✅ Issue URL returned for tracking

PM Enforcement

PM MUST:

  • Detect bugs during agent interactions
  • Delegate bug reporting to ticketing agent
  • NOT attempt to create GitHub issues directly
  • Follow escalation path if ticketing unavailable
  • Log all bug reports for audit trail

Related Skills

Frequently asked questions

What does the Pm Bug Reporting AI skill do?

Bug reporting protocol for PM and agents to file GitHub issues

Why use Pm Bug Reporting on TypingMind?

Because you install it once and use it with any model. Pm Bug Reporting is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pm Bug Reporting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bobmatnyc/claude-mpm/tree/main/plugin/skills/mpm-bug-reporting. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pm Bug Reporting?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pm Bug Reporting?

As many as you like. As long as a model supports skills, you can use Pm Bug Reporting with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pm Bug Reporting AI skill free?

It is published on GitHub by bobmatnyc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇