perspective-critic

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

Evaluates artifacts from a specific perspective using assigned viewpoint values and priorities

  • Analyzes an artifact through a designated perspective to identify strengths and concerns
  • Requires artifact, perspective, and optional outputs from other perspectives
  • Uses viewpoint-specific values, priorities, and expertise to form assessment
  • Returns structured evaluation with confidence score and perspective-specific insights

SKILL.md

.github/skills/perspective-criticView on GitHub ↗
---
name: perspective-critic
description: Evaluates artifact from a specific assigned perspective. Produces assessment grounded in that viewpoint's values, priorities, and expertise.
execution: subagent
prompt: ./prompt.md
input: artifact (string), perspective (string), other_perspectives_output (string)
used-by: [multiagent-debate]
---

# Perspective Critic

Evaluates artifact from a specific assigned perspective.

## Execution

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

## Why Subagent

Each perspective requires dedicated context to maintain viewpoint consistency. Mixing perspectives in one context leads to averaging rather than genuine diversity.

## Input

- **artifact**: The artifact being evaluated
- **perspective**: Assigned viewpoint (e.g., "methodological skeptic", "domain expert", "practitioner")
- **other_perspectives_output**: Previous outputs from other perspectives (empty in round 1)

## Output

- **assessment**: Structured evaluation from this perspective
- **concerns**: Issues visible from this viewpoint
- **strengths**: Positives visible from this viewpoint
- **confidence**: How viable the artifact appears from this perspective (0.0–1.0)

## Budget

One unit = one perspective evaluation per round.

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.