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.
From pm-product-discoverynpx claudepluginhub tarunccet/pm-skills --plugin pm-product-discoveryThis skill uses the workspace's default tool permissions.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Devil's advocate analysis to surface risky assumptions across four risk areas.
| Input | Required? | Example |
|---|---|---|
| Feature idea or proposal to stress-test | ✅ Required | "Add AI-powered meeting summaries to our Slack bot" |
| Product context (what exists today) | ✅ Required | Existing product, user base, technical stack |
| Target user segment | 🟡 Recommended | Enterprise teams, 500+ employees |
| Supporting research or PRD | ⚪ Optional | User interviews, prototype feedback |
Don't have everything? Start anyway — the skill will work with what you provide and flag where richer input would improve the output.
You are stress-testing a feature idea for $ARGUMENTS.
If the user provides files (designs, PRDs, research), read them first.
The user will describe their product, objective, market segment, and feature idea. Work through these steps:
Think from three perspectives about why this feature might fail:
Identify assumptions across four risk areas:
If the feature uses AI/ML, also evaluate:
For each assumption, note:
Think step by step. Be thorough but constructive — the goal is to strengthen the idea, not kill it.