2026 07 24

---
title: kenzzark/polengshui-skill
content_type: repo
engine: v2
category: daily-digests/2026-07-24
tech_stack:
- YAML
- Markdown
- CLI Tools
- Agent Skills Framework
- Structured Prompting
quality_score: 8
rag_relevance: 7
deployment_complexity: Low
tags:
- evidence-based critique
- premortem analysis
- decision validation
- risk auditing
- adversarial review
source: https://github.com/kenzzark/polengshui-skill
stars: 0
language: None
last_updated: '2026-07-10T16:18:22Z'
discovered_at: '2026-07-10T16:24:14Z'
evaluated_by: mistral-small-latest
---

## Summary
A skill framework that transforms AI critique into an evidence-based, verifiable, and actionable adversarial review process. It helps users challenge assumptions, validate claims, and identify risks in decisions, plans, or ideas by enforcing structured evidence audits and premortem analyses.

## Key Features
- Structured adversarial review process for AI-generated or human ideas
- Evidence auditing to separate facts, inferences, and assumptions
- Premortem analysis to identify failure conditions and termination criteria
- Low-cost validation pathways for high-risk assumptions
- Modular and extensible framework for custom scenarios and domains

## Why It Matters for RAG Builders
It provides a systematic way to challenge AI outputs and human decisions with verifiable evidence, reducing blind spots and improving decision quality in RAG pipelines.

## Tech Stack Deep Dive
### YAML
Automated review identified **YAML** as a key module contributing to infrastructure orchestration or cognitive reasoning boundaries in this project.

### Markdown
Automated review identified **Markdown** as a key module contributing to infrastructure orchestration or cognitive reasoning boundaries in this project.

### CLI Tools
Automated review identified **CLI Tools** as a key module contributing to infrastructure orchestration or cognitive reasoning boundaries in this project.

### Agent Skills Framework
Automated review identified **Agent Skills Framework** as a key module contributing to infrastructure orchestration or cognitive reasoning boundaries in this project.

### Structured Prompting
Automated review identified **Structured Prompting** as a key module contributing to infrastructure orchestration or cognitive reasoning boundaries in this project.



## Installation
```bash
# Please check the repository README for specific installation instructions.
```

## Related Vault Entries
<!-- Auto-populated by build-index.js based on tech_stack overlap -->