insight

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/insight

Understand WHY gaps persist — root causes, stakeholders, tensions, and hidden assumptions.

SKILL.md

.github/skills/insightView on GitHub ↗
---
name: insight
description: Insight Campaign — deep root-cause analysis of why research gaps persist. 5 strategies (root-cause-drilling, stakeholder-mapping, tension-mining, question-reformulation, assumption-audit), 4 tactics, 13 subagent SOPs.
execution: campaign
used-by: deep-insight
---

# Insight

Understand WHY gaps persist — root causes, stakeholders, tensions, and hidden assumptions.

## Design Philosophy

This campaign is a strategy book — CC reads, internalizes, and autonomously constructs an approach. The SKILL.md files are textbooks, not scripts. CC decides execution order, depth, and iteration based on research context.

## Strategy Routing

| Signal | Strategy |
|--------|----------|
| 为什么存在、根因、5 Whys、鱼骨图、因果树 | → root-cause-drilling |
| 谁受影响、利益相关者、JTBD、CSH 12 问 | → stakeholder-mapping |
| 对立力量、张力、极性、冲突蒸发 | → tension-mining |
| 如何框定问题、HMW、抽象阶梯、苏格拉底 | → question-reformulation |
| 隐含假设、脆弱性、前提审计、红队 | → assumption-audit |

## Available Tactics

- causal-tree-building — logical causal tree construction
- dialectical-synthesis — thesis-antithesis-synthesis cycle
- boundary-unfolding — expose hidden system boundaries
- assumption-stress-test — systematic assumption stress testing

## Available SOPs

**Import (5):** web-search, web-research, paper-overview, paper-search, paper-research

**Subagent (13):** five-whys-drilling, ishikawa-decomposition, current-reality-tree, csh-12-question, jtbd-mapping, salience-classification, evaporating-cloud, polarity-mapping, abstraction-laddering, hmw-formulation, socratic-probing, abp-vulnerability-classification, clr-validation

**Shared (2):** evidence-synthesis, assumption-surfacing

## Context Management

context-checkpoint after each strategy completes. Accumulated state persists across strategies within a campaign run.

More from yogsoth-ai/de-anthropocentric-research-engine