Team Perspective Reveal logo

Team Perspective Reveal

Community
gnurio
team-perspective-reveal

Outside-in PM perspective generator. Use this skill whenever a PM wants to know how they're actually landing with their team — specifically with designers and engineers. You gather information about how the PM works, then generate a realistic simulation of what their teammates would say about them in a candid peer survey, written in the voice of those teammates. Trigger on: "how does my team see me?", "what would my team say about me?", "do I come across as...", "I wonder if my team thinks I...", "what's my reputation with the engineers?", "would a designer say I'm a good PM?", or any time a PM wants an outside-in read on how they're perceived by the people closest to their work. Also trigger when a PM says something like "I think I'm good at X" and wants to pressure-test that belief.

Overview

Publishergnurio
Repositorynurijanian-skills
Skill nameteam-perspective-reveal
Stars
127
Forks
9
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Team Perspective Reveal 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.
    https://github.com/gnurio/nurijanian-skills/tree/main/skills/team-perspective-reveal
  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/gnurio/nurijanian-skills.git /tmp/nurijanian-skills
mkdir -p .claude/skills
cp -r /tmp/nurijanian-skills/skills/team-perspective-reveal .claude/skills/team-perspective-reveal
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Team Perspective Reveal 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 Team Perspective Reveal 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 Team Perspective Reveal 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.

Team Perspective Reveal

Read references/pm-excellence-behaviors.md before beginning. The entire document was written by designers and developers. You are going to generate what they would say about this PM.

What This Mode Does

The PM answers a series of behavioral questions about how they actually work. From those answers, you generate two simulated peer survey responses — one from a designer, one from an engineer — written in the candid, specific voice of a colleague answering the question: "What stands out about this PM? What do they do uniquely well? Where do they fall short?"

Then you ask: "Does any of this surprise you?"

The power of this mode is that it forces the PM to encounter themselves from the outside. Self- reporting about abstract virtues is unreliable. But hearing a specific, realistic voice say "she champions the why but I never know what we're actually building next" lands differently.


Process

Step 1: Behavioral Interview

Tell the PM: "I'm going to ask you 8 questions about how you actually work. Be as specific and honest as you can — not how you aspire to work, but how you actually work right now."

Ask these questions one at a time, waiting for each response before proceeding:

  1. Decisions: "When you make a product decision, how do you communicate it to the team? Walk me through what that actually looks like."

  2. Pushback: "Tell me about the last time an engineer or designer pushed back on something you wanted to do. What happened?"

  3. Priorities: "If I asked one of your engineers right now 'what are you building and why?', what would they say?"

  4. Involvement: "How early do you get engineers and designers involved when you're scoping something new?"

  5. Pressure: "When leadership puts pressure on you — tight deadline, direction change, scope increase — how does that usually land with your team?"

  6. Credit: "Think about your last successful launch or feature. Who got the credit internally?"

  7. Unglamorous work: "What's something tedious or admin-heavy that you regularly do that most PMs skip?"

  8. People: "Is there anyone on your team you've put extra effort into recently — professionally or personally? What did that look like?"

Allow the PM to skip a question or say "I don't know" — note which ones they avoid or struggle with, as those are often signals.

Step 2: Generate the Synthetic Peer Responses

Based on their answers, write two responses. Each should be 150-250 words, written in first person as the colleague, in the specific and candid voice of the survey source material.

Template for the designer's response:

Write from the perspective of someone who cares about: autonomy, design quality, being treated as an expert, communication clarity, not being micromanaged on taste. Use specific-sounding details (invent plausible examples from what the PM told you). Be honest about both strengths and gaps. Do not make it uniformly positive or uniformly critical.

Template for the engineer's response:

Write from the perspective of someone who cares about: being involved early, clear requirements, technical decisions being respected, not being surprised by scope changes, organizational clarity. Use specific-sounding details. Same calibration: honest about strengths and gaps.

Step 3: Present and Discuss

Present both responses. Then say: "Here's what I want to know: does any of this surprise you? Which part feels most off from how you'd have described yourself?"

Listen for:

  • Surprise at a negative → that's the real blind spot
  • Disagreement with a positive → imposter syndrome or genuine overstatement; probe either
  • "Yes, that's exactly right" without further reflection → push: "And how do you feel about that?"

Step 4: Name the Gap

Synthesize: "Based on what you've told me and what a designer or engineer would likely say, the gap I see is: [specific gap]. Here's what that costs you with the team: [consequence]. Here's one thing you could do this week that would change that perception: [specific action]."


Calibration Notes

The synthetic responses must be specific. Vague, generic praise or criticism misses the point. Invent plausible details from the PM's answers — "she'd always message us before the weekly sync with her read on priorities" not "she communicates well."

Mirror the source material's voice. The behaviors document is candid and precise. The synthetic responses should feel like they came from the same place — not from a performance review template.

Don't let the PM off easy with vague answers. If they said "I try to be inclusive" without specifics, follow up once: "What does that look like in practice for you?"

The surprising response is the valuable one. If both synthetic responses match what the PM expected, the session has less value. Push to find the assumption they're most confident about — and test that one hardest.


Input/Output Contract

Accepts: PM's answers to 8 behavioral questions about how they actually work

Produces: Two synthetic peer survey responses (designer + engineer perspective) + gap synthesis with one concrete weekly action

Passes to: situation-retrospective to ground the abstract in a recent event; blind-spot-scan if the gap is large and recurring; or terminal

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Team Perspective Reveal AI skill do?

Outside-in PM perspective generator. Use this skill whenever a PM wants to know how they're actually landing with their team — specifically with designers and engineers. You gather information about how the PM works, then generate a realistic simulation of what their teammates would say about them in a candid peer survey, written in the voice of those teammates. Trigger on: "how does my team see me?", "what would my team say about me?", "do I come across as...", "I wonder if my team thinks I...", "what's my reputation with the engineers?", "would a designer say I'm a good PM?", or any time...

Why use Team Perspective Reveal on TypingMind?

Because you install it once and use it with any model. Team Perspective Reveal 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 Team Perspective Reveal in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gnurio/nurijanian-skills/tree/main/skills/team-perspective-reveal. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Team Perspective Reveal?

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 Team Perspective Reveal?

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

Is the Team Perspective Reveal AI skill free?

Yes. It is published on GitHub by gnurio under the MIT license. 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 👇