steel-manning-synthesis

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/steel-manning-synthesis

Synthesizes all attacks and verdicts into a final unified assessment

  • Identifies and addresses every attack without ignoring them.
  • Deploys external tools to analyze and integrate various perspectives on attacks and verdicts.
  • Utilizes decision-making logic to weigh competing viewpoints impartially, ensuring balanced synthesis.
  • Generates a comprehensive report including the final verdict, surviving concerns with severity ratings, and recommended modifications.

SKILL.md

.github/skills/steel-manning-synthesisView on GitHub ↗
---
name: steel-manning-synthesis
description: Synthesize all attacks and verdicts into a final unified assessment with surviving concerns and recommended modifications.
execution: subagent
prompt: ./prompt.md
input: all_attacks, all_verdicts
used-by: [steel-manning]
---

# Steel-Manning Synthesis

The final integration step — synthesizes all perspective attacks, debate verdicts, and challenge results into a unified assessment. Produces the campaign's final verdict with surviving concerns and recommended modifications.

## Execution

Spawns a subagent that receives all attack and verdict data from the campaign and produces the final synthesis.

## Why Subagent

- Synthesis requires impartial integration across all prior work
- Must weigh competing perspectives without favoring any
- Isolation from individual attack/verdict roles ensures balanced final assessment

## HARD-GATE

Output must include:
- Final verdict: ACCEPT / REJECT / REVISE
- Every attack addressed (not ignored)
- Surviving concerns with severity ratings
- Recommended modifications (if REVISE)
- Confidence level in the verdict

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

SkillDescription
abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
ablation-component-mappingMap system architecture to ablatable units for ablation studies
ablation-designDesign ablation studies to isolate component contributions in ML systems
ablation-executionRemove components one by one from a system, record the response/impact of each removal.
abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
abstraction-ladderPerform bisociation at multiple abstraction levels
abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.