Pm Delegation Patterns

Community

bobmatnyc

pm-delegation-patterns

Common delegation patterns for PM agent

Overview

Publisher	bobmatnyc
Repository	`claude-mpm`
Skill name	`pm-delegation-patterns`
Stars	152
Forks	34
Bundled files	Instructions only
Links	Skill source Repository

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 Delegation Patterns AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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-delegation-patterns .claude/skills/pm-delegation-patterns

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pm Delegation Patterns 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 Delegation Patterns 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 Delegation Patterns 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.

Common Delegation Patterns

Full Stack Feature

Workflow: Research → Analyzer → react-engineer + Engineer → Ops (deploy) → Ops (VERIFY) → api-qa + web-qa → Docs

When: Complete feature requiring frontend, backend, and deployment

Example:


User: "Add user dashboard with analytics"
PM delegates:
  1. Research: Investigate dashboard frameworks and analytics libraries
  2. Code Analyzer: Review solution approach
  3. react-engineer: Build dashboard UI components
  4. Engineer: Implement analytics API endpoints
  5. Ops: Deploy to staging
  6. Ops: Verify deployment (health checks, logs)
  7. api-qa: Test API endpoints
  8. web-qa: Test dashboard UI
  9. Documentation: Update API docs and user guide

API Development

Workflow: Research → Analyzer → Engineer → Deploy (if needed) → Ops (VERIFY) → web-qa (fetch tests) → Docs

When: Backend API implementation without frontend

Example:


User: "Create REST API for user management"
PM delegates:
  1. Research: API design patterns, authentication
  2. Code Analyzer: Review API design
  3. Engineer: Implement API endpoints
  4. Ops: Deploy API to staging (if needed)
  5. Ops: Verify deployment
  6. web-qa: Run fetch tests on endpoints
  7. Documentation: Generate API documentation

Web UI

Workflow: Research → Analyzer → web-ui/react-engineer → Ops (deploy) → Ops (VERIFY with Playwright) → web-qa → Docs

When: Frontend-only changes

Example:


User: "Redesign landing page"
PM delegates:
  1. Research: UI/UX best practices, component libraries
  2. Code Analyzer: Review design approach
  3. react-engineer: Implement new landing page
  4. Ops: Deploy to staging
  5. Ops: Verify deployment with Playwright
  6. web-qa: Visual regression testing
  7. Documentation: Update component documentation

Local Development

Workflow: Research → Analyzer → Engineer → local-ops (PM2/Docker) → local-ops (VERIFY logs+fetch) → QA → Docs

When: Working with localhost, PM2, Docker, or local processes

Example:


User: "Set up local development server"
PM delegates:
  1. Research: Local development setup best practices
  2. Code Analyzer: Review setup approach
  3. Engineer: Configure development environment
  4. local-ops: Start server with PM2/Docker
  5. local-ops: Verify server running (lsof, curl, logs)
  6. QA: Test local endpoints
  7. Documentation: Update setup guide

Bug Fix

Workflow: Research → Analyzer → Engineer → Deploy → Ops (VERIFY) → web-qa (regression) → version-control

When: Fixing reported bugs

Example:


User: "Fix login error on Safari"
PM delegates:
  1. Research: Investigate Safari-specific issues
  2. Code Analyzer: Review fix approach
  3. Engineer: Implement fix
  4. Ops: Deploy fix to staging
  5. Ops: Verify deployment
  6. web-qa: Run regression tests, verify Safari fix
  7. version-control: Create PR with fix

Vercel Site

Workflow: Research → Analyzer → Engineer → vercel-ops (deploy) → vercel-ops (VERIFY) → web-qa → Docs

When: Vercel-hosted applications

Example:


User: "Deploy blog to Vercel"
PM delegates:
  1. Research: Vercel deployment best practices
  2. Code Analyzer: Review deployment config
  3. Engineer: Configure Vercel settings
  4. vercel-ops: Deploy to Vercel
  5. vercel-ops: Verify deployment (health check)
  6. web-qa: Test deployed site
  7. Documentation: Update deployment guide

Railway App

Workflow: Research → Analyzer → Engineer → railway-ops (deploy) → railway-ops (VERIFY) → api-qa → Docs

When: Railway-hosted applications

Example:


User: "Deploy API to Railway"
PM delegates:
  1. Research: Railway deployment patterns
  2. Code Analyzer: Review Railway config
  3. Engineer: Configure Railway settings
  4. railway-ops: Deploy to Railway
  5. railway-ops: Verify deployment
  6. api-qa: Test API endpoints
  7. Documentation: Update deployment docs

Agent Selection by Trigger Keywords

Keywords	Agent	Use Case
localhost, PM2, docker-compose, port, process	local-ops	Local development
vercel, edge function, serverless	vercel-ops	Vercel platform
railway, nixpacks	railway-ops	Railway platform
gcp, google cloud, IAM, OAuth consent	gcp-ops	Google Cloud
clerk, auth middleware, OAuth provider	clerk-ops	Clerk authentication
browser, screenshot, click, navigate, DOM	web-qa	Browser testing
ticket, issue, PROJ-123, #123	ticketing	Ticket operations
skill, stack, framework	mpm-skills-manager	Skill management

Delegation Best Practices

Provide Context: Include relevant background for agent
Clear Acceptance Criteria: Define completion criteria
Wait for Completion: Don't interrupt agent work
Collect Evidence: Get specific artifacts from agents
Immediate File Tracking: Track files right after agent creates them
Chain Verification: QA verification after implementation

Frequently asked questions

What does the Pm Delegation Patterns AI skill do?

Common delegation patterns for PM agent

Why use Pm Delegation Patterns on TypingMind?

Because you install it once and use it with any model. Pm Delegation Patterns 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 Delegation Patterns in TypingMind?

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

Which AI models can use Pm Delegation Patterns?

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 Delegation Patterns?

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

Is the Pm Delegation Patterns 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

Next Cache Components Optimizer

vercel

OrganizationPopular

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal…

Next Partial Prefetching Adoption

vercel

OrganizationPopular

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the `partialPrefetching` flag, opt routes…

Next Partial Prefetching Optimizer

vercel

OrganizationPopular

Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected…

Ponytail Gain

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger:…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Common Delegation Patterns

Full Stack Feature

API Development

Web UI

Local Development

Bug Fix

Vercel Site

Railway App

Agent Selection by Trigger Keywords

Delegation Best Practices

Frequently asked questions

Related AI Skills

Set up your own AI workspace now