Pm Verification Protocols logo

Pm Verification Protocols

Community
bobmatnyc
pm-verification-protocols

QA verification gate and evidence requirements

Overview

Publisherbobmatnyc
Repositoryclaude-mpm
Skill namepm-verification-protocols
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 Verification Protocols 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-verification-protocols .claude/skills/pm-verification-protocols
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pm Verification Protocols 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 Verification Protocols 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 Verification Protocols 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.

QA Verification Gate Protocol

🔴 MANDATORY QA VERIFICATION GATE

CRITICAL: PM MUST delegate to QA BEFORE claiming work complete. NO completion claim without QA verification evidence.

When QA Gate Applies

ALL implementation work:

  • UI features
  • Local server UI
  • API endpoints
  • Bug fixes
  • Full-stack features
  • Test modifications

QA Gate Enforcement

BLOCKING: PM CANNOT claim "done/complete/ready/working/fixed" without QA evidence

CORRECT SEQUENCE:

Implementation
  → PM delegates to QA
  → PM WAITS for evidence
  → PM reports WITH QA verification

Verification Requirements by Work Type

Work TypeQA AgentRequired EvidenceForbidden Claim
Local Server UIweb-qaChrome DevTools MCP (navigate, snapshot, screenshot, console)"Page loads correctly"
Deployed Web UIweb-qaPlaywright/Chrome DevTools (screenshots + console logs)"UI works"
API/Serverapi-qaHTTP responses + logs"API deployed"
Databasedata-engineerSchema queries + data samples"DB ready"
Local Backendlocal-opslsof + curl + pm2 status"Running on localhost"
CLI ToolsEngineer/OpsCommand output + exit codes"Tool installed"

Forbidden Phrases (CIRCUIT BREAKER VIOLATION)

❌ NEVER say these without QA evidence:

  • "production-ready"
  • "page loads correctly"
  • "UI is working"
  • "should work"
  • "looks good"
  • "seems fine"
  • "it works"
  • "all set"
  • "ready for users"
  • "deployment successful"

✅ ALWAYS say this instead:

"[Agent] verified with [tool/method]: [specific evidence]"

Evidence Quality Standards

Good Evidence

Specific details:

  • File paths and line numbers
  • URLs and endpoints tested
  • HTTP status codes
  • Test counts and pass/fail results
  • Console log excerpts
  • Screenshots with annotations

Measurable outcomes:

  • "12 tests passed, 0 failed"
  • "HTTP 200 OK response"
  • "Server listening on port 3000"
  • "No console errors found"

Agent attribution:

  • "web-qa verified with Playwright"
  • "api-qa tested endpoints"
  • "local-ops confirmed process running"

Reproducible steps:

Insufficient Evidence (VIOLATIONS)

Vague claims:

  • "works"
  • "looks good"
  • "should be fine"

No measurements:

  • "deployed successfully" (without health check)
  • "UI updated" (without verification)

PM assessment:

  • PM saying "I checked and it works"
  • PM making claims without delegation

Not reproducible:

  • "tested it" (no steps)
  • "verified" (no method)

Required Evidence by Claim Type

Claim TypeRequired EvidenceExample
Implementation Complete• Engineer confirmation• Files changed (paths)• Git commit (hash/branch)• SummaryEngineer: Added OAuth2 auth. Files: src/auth/oauth2.js (new, 245 lines), src/routes/auth.js (+87). Commit: abc123.
Deployed Successfully• Ops confirmation• Live URL• Health check (HTTP status)• Deployment logs• Process statusOps: Deployed to https://app.example.com. Health: HTTP 200. Logs: Server listening on :3000. Process: lsof shows node listening.
Bug Fixed• QA bug reproduction (before)• Engineer fix (files changed)• QA verification (after)• Regression testsQA: Bug reproduced (HTTP 401). Engineer: Fixed session.js (+12-8). QA: Now HTTP 200, 24 tests passed.

Browser State Verification (MANDATORY)

CRITICAL RULE: PM MUST NOT assert browser/UI state without Chrome DevTools MCP evidence.

When verifying local server UI or browser state, PM MUST:

  1. Delegate to web-qa agent
  2. web-qa MUST use Chrome DevTools MCP tools (NOT assumptions)
  3. Collect actual evidence (snapshots, screenshots, console logs)

Chrome DevTools MCP Tools (via web-qa only)

Available tools:

  • mcp__chrome-devtools__navigate_page - Navigate to URL
  • mcp__chrome-devtools__take_snapshot - Get page content/DOM state
  • mcp__chrome-devtools__take_screenshot - Visual verification
  • mcp__chrome-devtools__list_console_messages - Check for errors
  • mcp__chrome-devtools__list_network_requests - Verify API calls

Required Evidence for UI Verification

CORRECT: web-qa verified with Chrome DevTools:

- navigate_page: http://localhost:3000 → HTTP 200
- take_snapshot: Page shows login form with email/password fields
- take_screenshot: [screenshot shows rendered UI]
- list_console_messages: No errors found
- list_network_requests: GET /api/config → 200 OK

WRONG: "The page loads correctly at localhost:3000" (No Chrome DevTools evidence - CIRCUIT BREAKER VIOLATION)

Local Server UI Verification Template

Task:
  agent: "web-qa"
  task: "Verify local server UI at http://localhost:3000"
  acceptance_criteria:
    - Navigate to page (mcp__chrome-devtools__navigate_page)
    - Take page snapshot (mcp__chrome-devtools__take_snapshot)
    - Take screenshot (mcp__chrome-devtools__take_screenshot)
    - Check console for errors (mcp__chrome-devtools__list_console_messages)
    - Verify network requests (mcp__chrome-devtools__list_network_requests)

Example Good Report

Work complete: User authentication feature implemented

Implementation: Engineer added OAuth2 authentication using Auth0.
Changed files: src/auth.js, src/routes/auth.js, src/middleware/session.js
Commit: abc123

Deployment: Ops deployed to https://app.example.com
Health check: HTTP 200 OK, Server logs show successful startup

Testing: QA verified end-to-end authentication flow
- Login with email/password: PASSED
- OAuth2 token management: PASSED
- Session persistence: PASSED
- Logout functionality: PASSED

All acceptance criteria met. Feature is ready for users.

Circuit Breaker Enforcement

Circuit Breaker #8: QA Verification Gate

  • Trigger: PM claims completion without QA delegation
  • Action: BLOCK - Delegate to QA now
  • Enforcement Levels:
    • Violation #1: ⚠️ WARNING - Must delegate immediately
    • Violation #2: 🚨 ESCALATION - Session flagged for review
    • Violation #3: ❌ FAILURE - Session non-compliant

Frequently asked questions

What does the Pm Verification Protocols AI skill do?

QA verification gate and evidence requirements

Why use Pm Verification Protocols on TypingMind?

Because you install it once and use it with any model. Pm Verification Protocols 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 Verification Protocols in TypingMind?

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

Which AI models can use Pm Verification Protocols?

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 Verification Protocols?

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

Is the Pm Verification Protocols 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 👇