mis-guidelines

Applies behavioral coding guidelines to reduce common LLM coding mistakes in MIS repositories.

Updated Oct 7, 2023
One-click install
npx skills add https://github.com/AhmedElbialy148/Portfolio --skill mis-guidelines-ahmedelbialy148
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mis-guidelines
Source: https://github.com/AhmedElbialy148/Portfolio/tree/main/.cursor/skills/mis-guidelines
Command: npx skills add https://github.com/AhmedElbialy148/Portfolio --skill mis-guidelines-ahmedelbialy148

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI coding agents often overcomplicate solutions, make sweeping unrequested changes, hide assumptions, and work toward vague goals. This Skill provides four behavioral rules that keep AI-generated code simple, surgical, and verifiable. ## Core Features & Use Cases - Think Before Coding: Forces explicit statement of assumptions, surfaces alternative interpretations, and stops on ambiguity instead of guessing. - Simplicity First: Rejects speculative features, unnecessary abstractions, and unrequested configurability in favor of minimal code. - Surgical Changes: Ensures every changed line traces directly to the user's request, matching existing style and avoiding drive-by refactors. - Goal-Driven Execution: Transforms vague tasks into verifiable success criteria with step-by-step plans and checks. - Use Case: When asking an AI agent to fix a bug or add a feature in a MIS repo, activate this Skill so the agent writes a reproducing test first, keeps the diff minimal, and verifies each step against stated criteria. ## Quick Start Apply the MIS guidelines to review this pull request and check whether every changed line traces back to the stated task.

Frequently Asked Questions about mis-guidelines

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

FAQPage Schema
How do I reduce common LLM coding mistakes in AI-generated code?▼

Apply four behavioral rules: state assumptions before coding, prefer the minimum code that solves the problem, keep every changed line traceable to the request, and define verifiable success criteria. These guidelines come from Andrej Karpathy's observations on LLM coding pitfalls.

How to keep AI coding agents from overcomplicating solutions?▼

Use the Simplicity First rule: no features beyond what was asked, no abstractions for single-use code, and no unrequested configurability. If a 200-line solution could be 50 lines, rewrite it.

What are surgical changes in code review?▼

Surgical changes touch only what the task requires, match existing code style, and avoid refactoring adjacent code. The test is whether every changed line traces directly back to the user's stated request.

Does this Skill work with other MIS skills like mis-github-contribution?▼

Yes, the four rules are stack-agnostic and compose with other MIS skills. For example, Simplicity First pairs with small single-purpose PRs, and Goal-Driven Execution pairs with Deep Agents' write_todos planning.

When should I not apply these coding guidelines?▼

The guidelines bias toward caution over speed, so for trivial tasks you should use judgment rather than applying the full process. They are most valuable for non-trivial writing, reviewing, or refactoring work.