yes-zh

Enforce evidence-based reasoning and safety gates for AI modifications.

50|6|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/sstklen/yes.md --skill yes-zh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: yes-zh
Source: https://github.com/sstklen/yes.md/tree/main/skills/yes-zh
Command: npx skills add https://github.com/sstklen/yes.md --skill yes-zh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill acts as an AI governance engine, ensuring AI assistants operate safely, evidence-based, and thoroughly by enforcing strict rules and preventing common AI bad habits like guessing, deflecting, and superficial fixes.

Core Features & Use Cases

  • Enforces Evidence Rules: Prevents AI from making claims without data, requiring verification before conclusions.
  • Implements Safety Gates: Mandates backups before modifications, impact analysis, and pre-deployment checks.
  • Detects and Corrects Bad Habits: Catches and corrects seven common AI shortcuts, including guessing, deflecting, and superficial fixing.
  • Structured Debugging: Guides AI through a systematic debugging process with increasing levels of self-inspection upon repeated failures.
  • Use Case: When an AI coding assistant is asked to fix a bug, this Skill ensures it first backs up the relevant files, checks the blast radius of the change, verifies the fix with tests, and then checks for related issues before confirming completion.

Quick Start

Use the yes-zh skill to ensure the AI follows evidence-based rules and safety gates before making any code changes.

Frequently Asked Questions about yes-zh

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce evidence-based reasoning in an AI assistant to prevent guessing?

To enforce evidence-based reasoning in an AI assistant, you need an AI governance engine that prevents claims without data. It catches and corrects common AI bad habits like guessing and superficial fixes by requiring strict verification before reaching conclusions.

What is an AI governance engine and when do I need it for debugging?

An AI governance engine is a multi-layered system that enforces AI safety, evidence-based reasoning, and thoroughness. You need it for structured debugging when an AI assistant repeatedly fails and requires increasing levels of self-inspection to resolve complex issues.

How do I mandate backups and impact analysis before an AI modifies code?

To mandate backups and impact analysis before code modifications, implement safety gates within your AI workflow. These gates enforce pre-deployment checks, verify the blast radius of changes, and ensure all modifications are backed up and tested before completion.

Does this AI governance framework work without external dependencies?

Yes, this AI governance framework works without external dependencies. It operates as a standalone skill that enforces strict rules and safety gates inherently, requiring no additional components or libraries to manage AI behavior and modifications.

What is the best way to structure professional handoffs for AI coding tasks?

The best way to structure professional handoffs for AI coding tasks is using a governance framework that ensures evidence-based rules and safety gates are met. This guarantees all modifications are verified, tested, and documented before transferring the task.