Skill389 repo starsupdated 19d ago

abstraction-laddering

Abstraction-laddering moves between concrete and abstract framings by escalating three levels up through "Why?" questions and descending three levels down through "How?" questions. Use this skill when research framings feel stuck or misaligned to identify the most productive level of analysis for your investigation. The subagent spawning mechanism constructs complete abstraction ladders within defined token budgets.

View source Repository: de-anthropocentric-research-engine

Install in Claude Code

Copy

git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/abstraction-laddering && cp -r /tmp/abstraction-laddering/skills/abstraction-laddering ~/.claude/skills/abstraction-laddering

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# Abstraction Laddering

Navigate abstraction levels to find productive framings.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent.

## Budget

One unit = one abstraction ladder construction.

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

<!-- END available-tables (generated) -->