/identify-assumptions-existing
Identify risky assumptions for a feature idea in an existing product across Value, Usability, Viability, and Feasibility. Uses multi-perspective devil's advocate thinking. Use when stress-testing a feature idea, doing risk assessment, or preparing for assumption mapping.
Claude Code
$ npx -y skills add phuryn/pm-skills --skill identify-assumptions-existing --agent claude-code
Codex
$ npx skills add phuryn/pm-skills --skill identify-assumptions-existing -a codex -y
Cursor
$ npx skills add phuryn/pm-skills --skill identify-assumptions-existing -a cursor -y
Gemini CLI
$ npx skills add phuryn/pm-skills --skill identify-assumptions-existing -a gemini-cli -y
GitHub Copilot
$ npx skills add phuryn/pm-skills --skill identify-assumptions-existing -a github-copilot -y
OpenCode
$ npx skills add phuryn/pm-skills --skill identify-assumptions-existing -a opencode -y
Windsurf
$ npx skills add phuryn/pm-skills --skill identify-assumptions-existing -a windsurf -y
SKILL.md
identify-assumptions-existing.SKILL.mdname: identify-assumptions-existing
description: "Identify risky assumptions for a feature idea in an existing product across Value, Usability, Viability, and Feasibility. Uses multi-perspective devil's advocate thinking. Use when stress-testing a feature idea, doing risk assessment, or preparing for assumption mapping."
Identify Assumptions (Existing Product)
Devil's advocate analysis to surface risky assumptions across four risk areas.
Context
You are stress-testing a feature idea for **$ARGUMENTS**.
If the user provides files (designs, PRDs, research), read them first.
Instructions
The user will describe their product, objective, market segment, and feature idea. Work through these steps:
1. **Think from three perspectives** about why this feature might fail:
- **Product Manager perspective**: Business viability, market fit, strategic alignment
- **Designer perspective**: Usability, user experience, adoption barriers
- **Engineer perspective**: Technical feasibility, performance, integration challenges
2. **Identify assumptions across four risk areas**:
- **Value**: Will it create value for customers? Does it solve a real problem?
- **Usability**: Will users figure out how to use it? Is the learning curve acceptable?
- **Viability**: Can marketing, sales, finance, and legal support it?
- **Feasibility**: Can it be built with existing technology? Are there integration risks?
3. **For each assumption**, note:
- What specifically could go wrong
- How confident you are (High/Medium/Low)
- Suggested way to test it
Think step by step. Be thorough but constructive — the goal is to strengthen the idea, not kill it.
---
Further Reading
- [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas)
- [How to Manage Risks as a Product Manager](https://www.productcompass.pm/p/how-to-manage-risks-as-a-product-manager)
- [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)
Read more
name: identify-assumptions-existing description: "Identify risky assumptions for a feature idea in an existing product across Value, Usability, Viability, and Feasibility. Uses multi-perspective devil's advocate thinking. Use when stress-testing a feature idea, doing risk assessment, or preparing for assumption mapping."
Identify Assumptions (Existing Product)
Devil's advocate analysis to surface risky assumptions across four risk areas.
Context
You are stress-testing a feature idea for **$ARGUMENTS**.
If the user provides files (designs, PRDs, research), read them first.
Instructions
The user will describe their product, objective, market segment, and feature idea. Work through these steps:
1. **Think from three perspectives** about why this feature might fail:
- **Product Manager perspective**: Business viability, market fit, strategic alignment
- **Designer perspective**: Usability, user experience, adoption barriers
- **Engineer perspective**: Technical feasibility, performance, integration challenges
2. **Identify assumptions across four risk areas**:
- **Value**: Will it create value for customers? Does it solve a real problem?
- **Usability**: Will users figure out how to use it? Is the learning curve acceptable?
- **Viability**: Can marketing, sales, finance, and legal support it?
- **Feasibility**: Can it be built with existing technology? Are there integration risks?
3. **For each assumption**, note:
- What specifically could go wrong
- How confident you are (High/Medium/Low)
- Suggested way to test it
Think step by step. Be thorough but constructive — the goal is to strengthen the idea, not kill it.
---
Further Reading
- [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas)
- [How to Manage Risks as a Product Manager](https://www.productcompass.pm/p/how-to-manage-risks-as-a-product-manager)
- [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)
72 PM skills and 42 chained workflows across 9 plugins. Claude Code, Cowork, and more. From discovery to strategy, execution, launch, growth, and shipping AI-built code. Designed for Claude Code and Cowork. Skills compatible with other AI assistants.
Other skills on pm-skills.
More skills from other plugins.
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress…
distilly
Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…
openwork-connect
Search and use the skills, MCP connections, and connected services available through the user's OpenWork organization.
Questions about identify-assumptions-existing.
- Which coding agents can use identify-assumptions-existing?
- identify-assumptions-existing installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.

