Multi-Angle Problem Analysis

Iterativedepth

by danielmiessler · MIT license · ★ 19,269 on GitHub · v1.1.16

Structured multi-angle exploration running 2-8 sequential passes over the same problem, each through a different scientific lens, to surface hidden requirements and edge cases invisible from one angle; each pass yields new ISC criteria.…

---
name: IterativeDepth
version: 1.1.16
description: "Structured multi-angle exploration running 2-8 sequential passes over the same problem, each through a different scientific lens, to surface hidden requirements and edge cases invisible from one angle; each pass yields new ISC criteria. USE WHEN iterative depth, explore deeper, multi-angle analysis, surface hidden requirements, blind spot check, what am I missing. NOT FOR scope/zoom analysis (use ApertureOscillation)."
---

## Customization

**Before executing, check for user customizations at:**
`~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/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

## What It Does

Overview

Before executing, check for user customizations at: ~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/IterativeDepth/

Manual install (npx, ZIP)

Claude Codenpx skills add danielmiessler/LifeOS --skill IterativeDepth -g -a claude-code

Claude Code (degit)npx degit danielmiessler/LifeOS/LifeOS/install/skills/IterativeDepth#main ~/.claude/skills/iterativedepth

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md3.3 KB

Read SKILL.md here

danielmiessler/main1 file shown

SKILL.md3.3 KB

Browse every file on GitHub↗

SKILL.md

Show the full text62 lines

iterativedepth/SKILL.md62 lines · 3.3 KB

PreviewCode

Outline

RawView on GitHub

Customization

Before executing, check for user customizations at: ~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/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

What It Does

IterativeDepth examines one problem through several structurally different lenses — literal, stakeholder, failure, temporal, and more — merging what each angle surfaces into ISC criteria a single pass misses. Grounded in 20 established techniques across cognitive science, AI/ML, requirements engineering, and design thinking (see ScientificFoundation.md).

The Deliverable

A done run produces:

A deduplicated ISC set — each criterion binary-testable, 8-12 words, phrased as a state not an action. No two criteria restate each other.
Refinements to existing criteria, each noting what changed and why.
Anti-criteria — failure modes that must NOT happen.
At least one surprising cross-angle finding — a requirement that only appeared because two lenses collided. A run that surfaces nothing a single pass would have missed added no value.

Passes stop when a new lens repeats what earlier lenses already found. Non-redundant angles are what matter; more angles for their own sake are not.

The Lenses

TheLenses.md is a catalog of eight exploration angles. Draw from it — pick the lenses the problem calls for, in whatever order, as many as earn their keep. No fixed count, no prescribed sequence: a security problem leans on the failure and adversary angles, a UX problem on the experiential one. Let the problem select the lenses.

Workflow Routing

Workflow	Trigger	File
Explore	"iterative depth", "explore deeper", "multi-angle"	`Workflows/Explore.md`

Reference

Lens catalog: TheLenses.md
Scientific grounding: ScientificFoundation.md

Gotchas

2-8 lens passes, not infinite. Diminishing returns after ~5 passes for most topics.
Each pass should surface genuinely NEW requirements, not restate previous findings. If passes start repeating, stop early.
This is a BPE-fragile skill. Monitor whether smarter models make it unnecessary. Quarterly test recommended.

Execution Log

After completing any workflow, append a single JSONL entry:

echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","skill":"IterativeDepth","workflow":"WORKFLOW_USED","input":"8_WORD_SUMMARY","status":"ok|error","duration_s":SECONDS}' >> ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl

Replace WORKFLOW_USED with the workflow executed, 8_WORD_SUMMARY with a brief input description, and SECONDS with approximate wall-clock time. Log status: "error" if the workflow failed.

1	---
2	name: IterativeDepth
3	version: 1.1.16
4	description: "Structured multi-angle exploration running 2-8 sequential passes over the same problem, each through a different scientific lens, to surface hidden requirements and edge cases invisible from one angle; each pass yields new ISC criteria. USE WHEN iterative depth, explore deeper, multi-angle analysis, surface hidden requirements, blind spot check, what am I missing. NOT FOR scope/zoom analysis (use ApertureOscillation)."
5	---
6
7	## Customization
8
9	Before executing, check for user customizations at:
10	`~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/IterativeDepth/`
11
12	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.
13
14
15	# IterativeDepth
16
17	## What It Does
18
19	IterativeDepth examines one problem through several structurally different lenses — literal, stakeholder, failure, temporal, and more — merging what each angle surfaces into ISC criteria a single pass misses. Grounded in 20 established techniques across cognitive science, AI/ML, requirements engineering, and design thinking (see `ScientificFoundation.md`).
20
21	## The Deliverable
22
23	A done run produces:
24
25	- A deduplicated ISC set — each criterion binary-testable, 8-12 words, phrased as a state not an action. No two criteria restate each other.
26	- Refinements to existing criteria, each noting what changed and why.
27	- Anti-criteria — failure modes that must NOT happen.
28	- At least one surprising cross-angle finding — a requirement that only appeared because two lenses collided. A run that surfaces nothing a single pass would have missed added no value.
29
30	Passes stop when a new lens repeats what earlier lenses already found. Non-redundant angles are what matter; more angles for their own sake are not.
31
32	## The Lenses
33
34	`TheLenses.md` is a catalog of eight exploration angles. Draw from it — pick the lenses the problem calls for, in whatever order, as many as earn their keep. No fixed count, no prescribed sequence: a security problem leans on the failure and adversary angles, a UX problem on the experiential one. Let the problem select the lenses.
35
36	## Workflow Routing
37
38	\| Workflow \| Trigger \| File \|
39	\|----------\|---------\|------\|
40	\| Explore \| "iterative depth", "explore deeper", "multi-angle" \| `Workflows/Explore.md` \|
41
42	## Reference
43
44	- Lens catalog: `TheLenses.md`
45	- Scientific grounding: `ScientificFoundation.md`
46
47	## Gotchas
48
49	- 2-8 lens passes, not infinite. Diminishing returns after ~5 passes for most topics.
50	- Each pass should surface genuinely NEW requirements, not restate previous findings. If passes start repeating, stop early.
51	- This is a BPE-fragile skill. Monitor whether smarter models make it unnecessary. Quarterly test recommended.
52
53	## Execution Log
54
55	After completing any workflow, append a single JSONL entry:
56
57	```bash
58	echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","skill":"IterativeDepth","workflow":"WORKFLOW_USED","input":"8_WORD_SUMMARY","status":"ok\|error","duration_s":SECONDS}' >> ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl
59	```
60
61	Replace `WORKFLOW_USED` with the workflow executed, `8_WORD_SUMMARY` with a brief input description, and `SECONDS` with approximate wall-clock time. Log `status: "error"` if the workflow failed.
62