Skills
.Work. You
Rest

confess

Community

Honest self-audit of AI output.

Content & Communication#audit#transparency#assumptions#confidence#self-review#confess
Authorkategage
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Honest, unvarnished evaluations of AI-produced work help users identify shortcuts, hidden assumptions, and weak spots, improving reliability and decision-making.

Core Features & Use Cases

  • Structured confession output including sections such as Confidence Inventory, Shortcuts & Hacks, Unverified Assumptions, Things I Noticed But Didn't Handle, and The Weakest Part.
  • Useful after producing strategic analyses, research briefs, or draft documents where honesty and risk assessment matter.
  • Flexible domain-agnostic template that can be adapted to legal, medical, or technical contexts by adjusting the framing and categories.

Quick Start

After generating a substantial output, trigger a confession by saying confess.

Dependency Matrix

Required Modules

None required

Components

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: confess
Download link: https://github.com/kategage/progressive-ai-skills/archive/main.zip#confess

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.