yes.md
Evidence-based debugging, safety gates, and verified code fixes
All Skills in This Repository (3)
Pure Emerald Level Indicatorsyes-ja
Enforce AI safety, evidence-based reasoning, and thoroughness across debugging, implementation, configuration, and deployment tasks.
yes-zh
Enforce evidence-based reasoning and safety gates for AI modifications.
yes
Enforce evidence-based verification and safety gates before and after coding actions.
Frequently Asked Questions
FAQPage SchemaHow to install YES.md?โผ
Run `npx skills add sstklen/yes.md --all -g -y` in your terminal to install all language versions globally.
What does YES.md actually do?โผ
It forces your coding assistant to verify every claim with real command output, back up files before editing, and run ripple checks after every fix so nothing else breaks.
How is YES.md different from PUA-style skills?โผ
PUA skills only push the model to keep trying, while YES.md adds safety gates, evidence rules, and direction checks so persistence never goes the wrong way.
Does YES.md work with Claude Code and Codex?โผ
Yes. It follows the standard SKILL.md format and runs in Claude Code, OpenAI Codex CLI, and other compatible coding environments.
Is YES.md available in Chinese or Japanese?โผ
Yes. It ships with three language variants: English (yes), Chinese (yes-zh), and Japanese (yes-ja), all installed together.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core