playbooks

home / skills / danielmiessler / personal_ai_infrastructure / iterativedepth

IterativeDepth skill

/Releases/v3.0/.claude/skills/IterativeDepth

This skill enables multi-angle iterative problem analysis to extract deeper ISC criteria across 2-8 lenses, enhancing observe phase outputs.

npx playbooks add skill danielmiessler/personal_ai_infrastructure --skill iterativedepth

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
1.9 KB
---
name: IterativeDepth
description: Multi-angle iterative exploration for deeper ISC extraction. USE WHEN iterative depth, deep exploration, multi-angle analysis, explore deeper, multiple perspectives on problem, examine from angles, OR when the Algorithm's OBSERVE phase needs enhanced ISC extraction.
---

## Customization

**Before executing, check for user customizations at:**
`~/.claude/skills/PAI/USER/SKILLCUSTOMIZATIONS/IterativeDepth/`

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.


# IterativeDepth

**Structured multi-angle exploration of the same problem to extract deeper understanding and richer ISC criteria.**

Grounded in 20 established scientific techniques across cognitive science (Hermeneutic Circle, Triangulation), AI/ML (Self-Consistency, Ensemble Methods), requirements engineering (Viewpoint-Oriented RE), and design thinking (Six Thinking Hats, Causal Layered Analysis).

## Core Concept

Instead of analyzing a problem once, run 2-8 structured passes through the same problem, each from a systematically different **lens**. Each pass surfaces requirements, edge cases, and criteria invisible from other angles. The combination yields ISC criteria that no single-pass analysis could produce.

## Workflow Routing

| Trigger | Workflow |
|---------|----------|
| "iterative depth", "explore deeper", "multi-angle" | `Workflows/Explore.md` |
| "quick depth", "fast angles" | `Workflows/Explore.md` (Fast mode: 2 lenses) |

## Quick Reference

- **8 Lenses** available, scaled by SLA (2-8)
- **Each lens** is a structurally different exploration angle
- **Output** is new/refined ISC criteria per pass
- **Integration** point: Algorithm OBSERVE phase

**Full Documentation:**
- Scientific grounding: `ScientificFoundation.md`
- Lens definitions: `TheLenses.md`

Overview

This skill performs structured multi-angle exploration of a single problem to extract deeper, richer ISC criteria. It runs 2–8 systematic passes, each using a different analytical lens, and combines results to surface requirements, edge cases, and insights missed by single-pass analysis. It is designed to augment the Algorithm OBSERVE phase for stronger internal selection criteria and better decision signals.

How this skill works

Before execution, it checks for user customizations in a local preferences directory and applies any found settings to override defaults. The skill then executes a sequence of lenses (2–8) drawn from cognitive science, AI/ML, requirements engineering, and design thinking. Each pass inspects the problem from a distinct perspective, producing refined ISC criteria and edge-case notes. Outputs are merged into a consolidated set of prioritized ISC items for downstream use.

When to use it

  • When you need deeper, multi-angle exploration beyond a single analysis pass
  • When the Algorithm OBSERVE phase must produce richer ISC criteria
  • When seeking to uncover hidden edge cases, assumptions, or failure modes
  • When comparing alternative viewpoints to reduce blind spots and bias
  • When SLA or context allows scaling from quick (2-lens) to full (8-lens) analysis

Best practices

  • Start with 2–4 lenses for quick validation, scale to 6–8 for thorough exploration
  • Apply user customizations if present to align lenses with domain preferences
  • Document ISC changes after each pass to trace how insights evolve
  • Prioritize combined ISC results by impact and likelihood for downstream decisions
  • Use ensemble-style merging rather than naive union to avoid noise amplification

Example use cases

  • Refining acceptance criteria and hidden constraints for a complex feature rollout
  • Augmenting an AI system's OBSERVE step to capture adversarial or fringe cases
  • Exploring product requirements from user, system, and business lenses to reduce rework
  • Running quick two-lens checks for rapid iterations during time-boxed sprints
  • Creating a defensible set of ISC criteria for safety, compliance, or audit trails

FAQ

How many lenses should I run by default?

Use 2–4 for quick insight and 6–8 for thorough coverage; choose based on SLA and risk.

Can I customize the lenses or order of passes?

Yes. The skill loads local customization preferences if available and applies them before execution.