How do I install the Ceet Product Manager skill?

Run npx skillmds@latest add cmolg/ceet-product-manager in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ceet Product Manager safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ceet Product Manager?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ceet Product Manager free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ceet Product Manager?

CMolG (@cmolg) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ceet Product Manager by cmolg — Agent Skill

Name: Ceet Product Manager
Author: CMolG

Ceet Product Manager

Cognitive Extraction Engine for product managers. Use when a user wants to clone the judgment of a PM — how they prioritize, frame problems, run discovery, write specs, manage stakeholders, define success, and say no. Trigger on phrases like "extract my PM thinking", "clone our head of product", "build an AI that writes PRDs like me", "interview me about product management", "capture how I prioritize", "make a product cognitive clone". Outputs are tool-agnostic.

CMolG 73cbb36 32 files · 25.4 KB Updated Sep 17, 2026

File contents

CEET — Product Manager

What this skill does

Interview a product manager. Produce a cognitive clone and an AI environment that frames, prioritizes, writes, and communicates product work in their style.

When to use

The user wants an AI that drafts PRDs, reviews specs, or triages feedback the way they would.
A CPO wants to scale their judgment across a team of PMs with AI support.
A founding PM wants their product sense captured before the team grows.

Run order

Read interview/questions.md.
Extract themes: #mental-model, #heuristic, #procedure, #quality, #anti-pattern, #vocabulary.
Push on "no". PM judgment is defined as much by what they refuse as what they approve. Get concrete examples.
Synthesize into the role-specific templates/cognitive-profile.md.
Activate into the role-specific templates/ directory. Save to templates/.
Hand off via ../docs/tool-integration.md.

PM-specific things to listen for

Problem framing. How they distinguish a real problem from a requested solution.
Prioritization system. RICE, WSJF, opportunity-solution tree, instinct, narrative — and how they actually use it vs. say they use it.
Discovery habits. User interviews cadence, assumption mapping, opportunity backlog.
Roadmap philosophy. Dates vs. outcomes vs. themes. Commitment vs. direction.
Specs / PRDs. Their template, what they include, what they refuse to include.
Success metrics. How they define it before shipping. What counts as "this didn't work."
Stakeholder management. How they handle exec escalation, sales asks, eng pushback, design tension.
Saying no. Their script, their framing, their last-resort move.
Cross-functional partnerships. How they work with eng lead, design lead, data, GTM.
Judgment calls. Build vs. buy, feature vs. fix, polish vs. ship, vertical vs. horizontal.

Synthesis guardrails

Capture their prioritization procedure step-by-step — this is the most reusable artifact for an AI.
Include their default PRD skeleton verbatim if they have one.
Preserve their framing vocabulary (problem statement vs. JTBD vs. opportunity, etc.).
Save outputs to templates/.

---name: ceet-product-managerdescription: Cognitive Extraction Engine for product managers. Use when a user wants to clone the judgment of a PM — how they prioritize, frame problems, run discovery, write specs, manage stakeholders, define success, and say no. Trigger on phrases like "extract my PM thinking", "clone our head of product", "build an AI that writes PRDs like me", "interview me about product management", "capture how I prioritize", "make a product cognitive clone". Outputs are tool-agnostic.---# CEET — Product Manager## What this skill doesInterview a product manager. Produce a cognitive clone and an AI environment that frames, prioritizes, writes, and communicates product work in their style.## When to use- The user wants an AI that drafts PRDs, reviews specs, or triages feedback the way they would.- A CPO wants to scale their judgment across a team of PMs with AI support.- A founding PM wants their product sense captured before the team grows.## Run order1. **Read** `interview/questions.md`.2. **Extract** themes: `#mental-model`, `#heuristic`, `#procedure`, `#quality`, `#anti-pattern`, `#vocabulary`.3. **Push on "no".** PM judgment is defined as much by what they *refuse* as what they approve. Get concrete examples.4. **Synthesize** into the role-specific `templates/cognitive-profile.md`.5. **Activate** into the role-specific `templates/` directory. Save to `templates/`.6. **Hand off** via [`../docs/tool-integration.md`](../docs/tool-integration.md).## PM-specific things to listen for- **Problem framing.** How they distinguish a real problem from a requested solution.- **Prioritization system.** RICE, WSJF, opportunity-solution tree, instinct, narrative — and how they actually use it vs. say they use it.- **Discovery habits.** User interviews cadence, assumption mapping, opportunity backlog.- **Roadmap philosophy.** Dates vs. outcomes vs. themes. Commitment vs. direction.- **Specs / PRDs.** Their template, what they include, what they refuse to include.- **Success metrics.** How they define it *before* shipping. What counts as "this didn't work."- **Stakeholder management.** How they handle exec escalation, sales asks, eng pushback, design tension.- **Saying no.** Their script, their framing, their last-resort move.- **Cross-functional partnerships.** How they work with eng lead, design lead, data, GTM.- **Judgment calls.** Build vs. buy, feature vs. fix, polish vs. ship, vertical vs. horizontal.## Synthesis guardrails- Capture their **prioritization procedure** step-by-step — this is the most reusable artifact for an AI.- Include their **default PRD skeleton** verbatim if they have one.- Preserve their **framing vocabulary** (problem statement vs. JTBD vs. opportunity, etc.).- Save outputs to `templates/`.

Frequently asked questions