pretty-but-wrong
OfficialExpose issues in AI docs before sharing.
Content & Communication#data-integrity#fact-check#document-quality#review-workflow#hostile-review#unsourced-claims#ai-deliverables
Authorm2ai-portfolio
Version1.0.0
Installs0
System Documentation
What problem does it solve?
AI-generated documents often look polished but can contain unsourced claims, outdated data, or obvious reasoning gaps. This skill provides a structured hostile-review pass to surface those issues before sharing with decision-makers.
Core Features & Use Cases
- Enumerates unsourced claims, stale data, and calculation errors without rewriting or fixing content.
- Produces a prioritized issue list with categories and severity, suitable for review cycles, governance, and risk assessment.
- Use Case: before distributing a board deck or external proposal, run this review to surface must-fix issues and get a clear remediation plan.
Quick Start
Use the hostile-review workflow to generate a ranked issue list for a document before distribution.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: pretty-but-wrong Download link: https://github.com/m2ai-portfolio/m2ai-skills-pack/archive/main.zip#pretty-but-wrong Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.