# Curiosity Loops

> Use when facing a significant decision (career pivot, product direction, technical choice) and feeling stuck or indecisive, when seeking contextual advice rather than generic recommendations

- Skill: `coowoolf/curiosity-loops` (Agent Skill)
- Install (CLI): `npx skillmds@latest add coowoolf/curiosity-loops`
- Raw SKILL.md: https://api.skillmd.com/api/skills/coowoolf/curiosity-loops/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: Coowoolf (https://skillmd.com/u/coowoolf)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/coowoolf/curiosity-loops

---


# Curiosity Loops

## Overview

Curiosity Loops is a structured method for gathering **contextual advice** from a curated group of peers rather than relying on a single mentor or vague questions. It turns decision-making into a data-collection exercise.

**Core principle:** The best advice is contextual. Bad advice happens when advisors lack context about your specific situation.

## When to Use

- Facing a significant decision (career pivot, product direction, personal dilemma)
- Feeling indecisive or stuck
- Need diverse perspectives quickly
- Want to avoid "single point of failure" advice

## The Four-Step Process

```
┌─────────────────────────────────────────────────────────────────┐
│  1. FORMULATE     →  Ask specific, unbiased question            │
│                      (NOT "What should I do?")                  │
├─────────────────────────────────────────────────────────────────┤
│  2. CURATE        →  Mix Subject Matter Experts +               │
│                      People who know your context               │
├─────────────────────────────────────────────────────────────────┤
│  3. EXECUTE       →  Reduce cognitive load                      │
│                      (e.g., "Pick top 2 of 9")                  │
├─────────────────────────────────────────────────────────────────┤
│  4. CLOSE LOOP    →  Process data, share outcome with advisors  │
└─────────────────────────────────────────────────────────────────┘
```

## Quick Reference

| Element | Good Example | Bad Example |
|---------|--------------|-------------|
| Question | "Which 2 of these 9 topics resonate most?" | "What should I talk about?" |
| Audience | 10 friends (5 experts + 5 who know you) | 1 mentor |
| Format | Low friction (2 choices max) | Open-ended essay |
| Follow-up | Share what you decided and why | Ghost them |

## Common Mistakes

- **Vague questions** → Ask specific, structured questions
- **Single advisor** → Curate 8-12 people with diverse perspectives
- **No follow-up** → Always close the loop; thank advisors

## Real-World Example

Ada Chen Rekhi used this to select podcast interview topics: emailed 10-11 friends a list of 9 topics, asked them to pick their top 2, synthesized patterns, and closed the loop.

---

*Source: Ada Chen Rekhi (Notejoy, LinkedIn, SurveyMonkey) via Lenny's Podcast*