Identify which factors are "load-bearing walls" — factors whose removal would collapse the conclusion.
Scanned 5/27/2026
Install via CLI
openskills install yogsoth-ai/de-anthropocentric-research-engine---
name: load-bearing-identification
description: Identify which factors are "load-bearing walls" — factors whose removal would collapse the conclusion.
execution: subagent
prompt: ./prompt.md
input: ablation_results (list), necessity_scores (list), sufficiency_scores (list)
used-by: [counterfactual-probing]
---
# Load-Bearing Identification
Synthesizes ablation, necessity, and sufficiency results to identify critical factors.
## Execution
Subagent — spawned via subagent-spawning/spawn-agent.
## Why Subagent
Final synthesis requires weighing multiple evidence streams to produce a definitive ranking.
## Input
- **ablation_results**: Degradation scores from factor removal
- **necessity_scores**: PN scores per factor
- **sufficiency_scores**: PS scores per factor
## Output
- **load_bearing_factors**: Ranked list of critical factors
- **classification**: Each factor classified into necessity-sufficiency quadrant
- **confidence**: Confidence in each classification
- **summary**: Overall structural assessment
## Budget
One unit = one synthesis per campaign run.
No comments yet. Be the first to comment!
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review...