Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Stop That Shit（别再造史了）｜面向 Codex/GPT 场景的多平台 Hook + Skill Guard：拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

⭐ Философия архитектуры ООП, SOLID-принципы, Dry, KISS и YAGNI

让 Codex 少烧 Token、少造复杂度，同时不降智的代码约束 Skill

Agentic Runtime

Stop agents from designing sloppy UI. Inspired by Impeccable, but without the plugin machinery. Just one SKILL.md file.

Low-level design of Ride-sharing Application Implementation.

Clean code principles and design patterns examples in Java with Unit Test cases

Low-level design of Cache Implementation.

Six Claude Code skills (architect, review-swarm, ask-the-council, prompt-generator, up-to-date, ponytail) bundled as an installable plugin.

Disciplined minimal code orchestrator with gated multi-model review before subagents ever start writing code.

Lean output mode for Claude Code: minimal solution, action-first structure, zero-fat density. Fuses caveman, ponytail, and i-have-adhd under one rule.

SOLID Design Principles with Implementation in Java 9

Ponytail, lazy senior dev mode, for DeepSeek Harness: 6 skills adapted from DietrichGebert/ponytail (MIT)

A SKILL.md for AI coding agents that stops overengineering before it starts. Turns KISS, YAGNI, and DRY into a real decision system — not just a reminder.

Put your glasses on. Evidence-first planning and bounded implementation diagnosis for AI coding agents.

Low-level design of Meeting Room Application Implementation.

A Codex and ChatGPT Skill that helps agents avoid scope creep and overengineering—finish the ask, prove it works, and keep software architecture clear.

This GPT is Overpowered but Overly Cautious. / 这个GPT明明超强却过分慎重。