The Idea Generator is the brainstorming specialist for Headout's PM OS. Engage after a Problem Frame is complete — or directly when a PM has a clear problem statement and wants to explore the solution space rigorously before committing to a direction. Acts as a high-fidelity thought partner: builds deep context through a multi-round interview (current state, constraints, prior attempts, platform nuances), maps the solution space into 2-4 strategic themes before generating any ideas, then produces specific ideas within each theme. Trigger for: "what are the ways we could solve this", "brainstorm approaches to X", "what should we build for this problem", "explore the solution space", "I have a problem frame and want ideas", "ideate on this", "what directions could we go", or any request to generate solution directions after a problem has been framed. Output: a structured Idea Brief.
88
88%
Does it follow best practices?
Impact
81%
1.02xAverage score across 3 eval scenarios
Passed
No known issues
Idea Brief structure and theme-map quality
Correct filename
100%
100%
Problem in One Sentence section
80%
100%
Context Built section — three sub-points
37%
100%
Solution Space table
62%
100%
2-4 strategic themes
100%
100%
Themes are levers, not features
100%
100%
History signal per theme
71%
100%
Minimum 2 ideas per theme
100%
100%
Idea effort signal
16%
0%
Idea novelty signal
0%
0%
Headout-specific angle per idea
100%
87%
Recommended Direction section
100%
100%
Second and third options positioned
50%
100%
Open Questions section
100%
60%
What We're NOT Exploring section
83%
100%
Q2'25 carousel attempt referenced
100%
100%
Structured critique and 4-dimension scoring in Idea Brief
Correct filename
100%
100%
Critique: Redundancy check
100%
100%
Critique: User motivation alignment
100%
100%
Critique: Platform fit (MB)
100%
100%
Critique: Metric connection
100%
100%
Critique: Coverage check
100%
100%
Scoring with 4 dimensions
10%
20%
1-3 scale used
0%
0%
Top recommendation named explicitly
100%
100%
Second/third options positioned as fallbacks
100%
100%
Prior Q1'25 experiment referenced
100%
100%
Ideas NOT already attempted
100%
100%
What We're NOT Exploring section
50%
100%
Pillar alignment referenced
100%
0%
Behavioral grounding and Headout-specific idea quality
Correct filename
100%
100%
Behavioral framing in ideas
100%
100%
Headout-specific angle — not generic
100%
70%
MB feasibility addressed per idea
100%
100%
Themes are strategic levers
50%
70%
Prior failed attempts addressed
100%
100%
Ideas not a repeat of flat experiments
100%
100%
Metric named per idea
100%
62%
Non-POIs to the Moon pillar connected
16%
33%
Effort and novelty signals
25%
37%
Open Questions section
100%
100%
What We're NOT Exploring section
100%
60%
First bet named with justification
66%
66%
At least 2 ideas per theme
100%
50%
d8db811
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.