Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

product-manager-prompts Skill

Repository ↗

by deanpeters★ 1,2021 skills

Install

What it does

A repository of Generative AI prompts for product managers using agents such as ChatGPT, Claude, & Gemini

  • Connects Instruction files the AI reads
  • Account or key No key found in README or SKILL.md
  • Category Automation and agents
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/deanpeters-product-manager-prompts.svg)](https://mcp.popnx.com/en/skills/deanpeters-product-manager-prompts)

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
product-manager-prompts
skillsnacosanatomyleon
Makerdeanpetersvercel-labsalibabawheresryan22leon-ai
Skills11111
GitHub stars1,20240,01433,53328,16217,692
Last code changeAug 10, 2026Nov 17, 2026Nov 19, 2026Oct 19, 2026Nov 13, 2026
License–MITApache-2.0MITMIT

1 skills (instruction sets) by deanpeters that an AI reads and follows · not an MCP server

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

Claude CodeClaude (เว็บ/แอป)GitHub Copilot

From the maker’s README and the folders in the repo

Install

Is it safe?

  • Who made it

    GitHub account deanpeters (person), 16 years old

  • Use and upkeep

    ★ 1,202 stars · code last changed Aug 10, 2026

  • Any scripts?

    No, plain text files the AI reads and follows

  • Uses the internet?

    No scripts, so it does not go online by itself

  • Changes machine-wide settings?

    No hooks or writes to machine settings found

Checked automatically from the repo files at commit c3b91db (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

First: which AI do you use?

Pick your app and this page shows only how to install it there

Option 1Upload to claude.ai (web and app)

  1. Download from GitHub

    This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier

    Download from GitHub (whole repo) ↗

    Unzip it, then zip only the skills/dangerous-animals-of-pm-generator folder again. The ZIP must have a dangerous-animals-of-pm-generator folder with SKILL.md at the top level, no loose files

  2. Open Skills on claude.ai and upload

    +Create skillUpload a skillpick dangerous-animals-of-pm-generator.zip

    Open claude.ai/customize/skills ↗

  3. No Upload button? Turn on file creation first

    SettingsCapabilitiesCode execution and file creation

    Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free

Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)

Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)

Checked against official docs Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com

Option 1Let Claude Code install it

Copy this sentence and paste it into a Claude Code chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Restart Claude Code, then type /dangerous-animals-of-pm-generator or ask for a matching task and Claude picks it up

Checked against official docs Nov 12, 2026 · Source: code.claude.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.claude/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Claude Code, then type /dangerous-animals-of-pm-generator or ask for a matching task and Claude picks it up

Skills you install yourself work in the ChatGPT desktop app, Codex CLI and the Codex IDE extension · ChatGPT on the web and mobile cannot use skills you install yourself, only skills that come with a plugin from the directory

ChatGPT desktop app

The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills

Option 1Let ChatGPT install it

Open Codex in the ChatGPT desktop app and paste this sentence into the chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2Put the folder there yourself

Put the dangerous-animals-of-pm-generator folder at ~/.agents/skills/dangerous-animals-of-pm-generator

~ is your home folder ($HOME)

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

After installing

  • ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
  • To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
  • Codex picks up newly installed skills by itself; if one does not show up, restart Codex

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

ChatGPT on the web and mobile

Skills you install yourself do not work here; only skills that come with a plugin from the directory

To use this skill with ChatGPT, use the ChatGPT desktop app as above

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

Option 1Let Codex install it

Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Codex, then ask for a matching task; Codex lists the skill

Option 1Let Cursor install it

Copy this sentence and paste it into a Cursor chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

In Cursor’s Agent chat, type / and pick dangerous-animals-of-pm-generator

Checked against official docs Nov 12, 2026 · Source: cursor.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.cursor/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. In Cursor’s Agent chat, type / and pick dangerous-animals-of-pm-generator

Option 1Let the AI install it

For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.

View on GitHub ↗

Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026

View the original SKILL.md

The text below comes from the maker’s repo, not from PopNx MCP

Showing the first 8,000 characters · Open the full file on GitHub

---
name: dangerous-animals-of-pm-generator
description: Generate creature acronyms that name PM dysfunctions, blockers, or winning strategies. Use when you want to give your team shared vocabulary for the animals hiding in your product work.
license: CC-BY-NC-SA-4.0
metadata:
  intent: >-
    Guide product managers through a 5-question facilitation that maps their real jobs, pains, and frustrations onto creature acronyms — then outputs a session-starter prompt for a dedicated beast-naming exploration. Surfaces the "Dangerous Animals" (dysfunctions, anti-patterns, blockers) or "Beneficial Beasts" (strategies, behaviors, mindsets) lurking in daily PM work.
  type: interactive
  theme: creativity-reframing
  best_for:
    - "Making PM anti-patterns visible and memorable for teams and stakeholders"
    - "Building shared vocabulary for dysfunctions in retrospectives or team charters"
    - "Reframing obstacles with humor to reduce friction in sensitive conversations"
  scenarios:
    - "My team keeps building what the HiPPO wants instead of what customers need — I want to name this and the other creatures like it"
    - "I need a warm-up exercise for a retrospective about product dysfunctions"
    - "I want memorable metaphors to explain PM anti-patterns to non-PM stakeholders"
  estimated_time: "10-15 min"
---

<!--
## Description:
Runs a five-question facilitation over a product manager's real jobs,
pains, and obstacles, then names 4-9 creature acronyms that make those
hazards discussable -- the meeting that eats a day, the stakeholder who
circles, the requirement that molts overnight.

## Standalone: yes

## Usage Note:
Reach for this in a retro that has gone flat, a team offsite, or any
moment when people will describe a dysfunction as a monster long before
they will name it in a status report. Humor is the anesthetic; the
diagnosis is the point.

## When NOT to Use:
When the team is not safe enough to name dysfunctions honestly, when a
metaphor would substitute for direct feedback someone is owed, or when
the moment calls for a formal framework artifact rather than a naming
exercise.

## Instructions:
1. Ask the five questions one at a time; do not batch them.
2. Generate options 1-4 per question from what the user has already
   said -- the enumerated lists below are worked examples, not a script.
3. Let the user pick beast mode and animal category before naming
   anything.
4. Name the creatures directly. Unlike the source prompt, this skill
   does not emit a session starter for the user to run elsewhere.

## Pedagogic Notes:
- Metaphor lowers the cost of naming an uncomfortable truth, which is
  why satire belongs in a serious prompt library.
- The animal-noun-first rule teaches a general prompting lesson: bind
  the generator to a hard constraint it cannot satisfy by paraphrase,
  or it will drift to the nearest easy word.
- Building shared vocabulary for recurring hazards makes them
  discussable later without the metaphor.

## Attribution:
Created by Dean Peters (Productside.com), September 2024.

## Licensing:
CC BY-NC-SA 4.0 (see LICENSE and LICENSING.md). Commercial use requires
expressed written permission from Dean Peters.

Date: August 8, 2026
-->

## Purpose

Guide product managers through a 5-question facilitation that maps real jobs, pains, and frustrations onto creature acronyms — then outputs a session-starter prompt for a dedicated exploration. Use this to name the "Dangerous Animals" lurking in your product work (dysfunctions, anti-patterns, blockers) or the "Beneficial Beasts" worth cultivating (strategies, behaviors, mindsets).

This is not a framework document — it's a creative reframing tool. Naming a dysfunction gives your team shared vocabulary to talk about it without pointing fingers.

## Key Concepts

### The Creature Acronym Pattern

Creature names map PM realities onto animal imagery through acronyms.

**The five core Dangerous Animals.** These are canon from *The Dangerous
Animals of Product Management* and are not up for redefinition — cite them,
don't rewrite them:

| Creature | Acronym | What It Represents |
|---|---|---|
| HiPPO | Highest Paid Person's Opinion | Decisions driven by seniority, not evidence |
| RHiNO | Really High-value, New Opportunity | Shiny object that derails the roadmap |
| ZEbRA | Zero Evidence But Really Arrogant | Stakeholder with strong opinions and no data |
| WoLF | Works on Latest Fire | Reactive PM who abandons strategy for urgency |
| Seagull Manager | — | Flies in, makes noise, dumps on everything, leaves |

**Illustrations only**, used below to show the cause-and-effect shape. Generate
your own; these are not canon:

| Creature | Acronym | What It Represents |
|---|---|---|
| ORCA | Optimistic Reasoning, Catastrophic Action | Confident plan that breaks on contact |
| DODO | Demo Overpromised, Deployment Obliterated | The demo that wrote a cheque delivery couldn't cash |

### Five Acronym Rules

1. **Animal nouns only** — The acronym must spell an actual animal species noun from the chosen category. FROG, TOAD, NEWT, SALAMANDER, AXOLOTL are valid. CROAK, SLIME, LEAP, AGILE, STINKS are not. If it isn't a creature name, it isn't a creature.
2. **Short and punchy** — aim for 3–6 letters. Stretch to 8 only when the longer animal noun is unmistakably the better metaphor (AXOLOTL earns its length; PLATYPUS rarely does).
3. **One mechanism, not two traits** — the expansion has to hold together as a single idea. Two shapes work:
   - **One noun phrase**, where the behavior is *implied by the noun* rather than narrated. RHiNO — *Really High-value, New Opportunity* — never says what the salesperson does, because the noun already did it. Same with HiPPO — *Highest Paid Person's Opinion*.
   - **Cause and effect**, where the first half produces the second. ORCA — *Optimistic Reasoning, Catastrophic Action*. DODO — *Demo Overpromised, Deployment Obliterated*. Here the comma is a hinge, not a list separator.

   The failure is **coordination**: two traits that merely co-occur. MACAW — *Mentions AI Constantly, Accomplished Wrapper* — names two complaints about the same person and no mechanism joining them; being a thin wrapper doesn't cause the AI talk. **Test:** put "which is why" between the halves. If only "and also" fits, it's a list, not a beast.
4. **Every word carries freight** — intensity words are not evidence. *Escalates*, *Hemorrhages*, *Obliterated* announce that something is bad without naming what or how, and a beast built from them would fit any dysfunction at any company. A word earns its slot by being specific and checkable: "Highest Paid" is observable, "Demo Overpromised" names the exact act. The same word passes or fails depending on what it's bound to — *Deployment Obliterated* works because the deployment is the thing obliterated, while a bare *Obliterated* is melodrama. Attach it to a subject or cut it. Never add a word just to reach a letter.
5. **Emotional impact** — The name should create a vivid, memorable image. ZEbRA and WoLF work because they trigger an instant visual *and* a gut reaction.

For the reasoning behind rules 3 and 4, a worked pass/fail table, and why WoLF and ZEbRA are compliant despite being neither shape, see `acronym-craft.md`.

### Pains, Gains, and Jobs Framing

The facilitation collects three lenses before generating beasts:
- **Jobs** — What PM tasks or outcomes are you trying to achieve?
- **Pains** — What makes those jobs hard?
- **Obstacles** — What specific behaviors, personalities, or dynamics block you?

These map directly onto which creatures get created and what they represent. Specific inputs produce specific beasts.

### Two Beast Modes

- **Dangerous Animals Enumeration** — Creatures representing dysfunctions, blockers, anti-patterns. Good for retrospectives, team charters, naming what's already happening.
- **Beneficial Beasts List** — Creatures representing strategies, mindsets, behaviors worth cultivating. Good for culture-building,

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
1,202
Maker
deanpeters
License
No license stated This repo states no license. By default the author keeps all rights: ask before you share it or use it commercially.
Last code change
Aug 10, 2026
SKILL.md files in the repo (including translated copies and templates)
1
Topics
agile, chatgpt, documentation-generator, generative-ai, product-management, product-owner