coding-guidelines

Applies behavioral guidelines that reduce common LLM coding mistakes during implementation and review.

Updated Sep 15, 2026
One-click install
npx skills add https://github.com/Peterson-Benhame/agent-skills --skill coding-guidelines-peterson-benhame
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-guidelines
Source: https://github.com/Peterson-Benhame/agent-skills/tree/main/packages/skills-catalog/skills/%28development%29/coding-guidelines
Command: npx skills add https://github.com/Peterson-Benhame/agent-skills --skill coding-guidelines-peterson-benhame

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? LLM coding assistants often over-engineer solutions, make silent assumptions, and touch unrelated code. This Skill enforces disciplined behavioral guidelines that keep code changes minimal, explicit, and verifiable. ## Core Features & Use Cases - Think Before Coding: Surfaces assumptions, ambiguities, and tradeoffs before implementation instead of guessing silently. - Simplicity First: Blocks speculative features, unnecessary abstractions, and unrequested configurability. - Surgical Changes: Restricts edits to only what the task requires, matching existing style and avoiding drive-by refactors. - Goal-Driven Execution: Converts tasks into verifiable success criteria with test-backed loops. - Use Case: When asking an AI agent to fix a bug or add a feature, activate these guidelines so the agent writes a reproducing test first, changes only the relevant lines, and avoids rewriting surrounding code. ## Quick Start Apply the coding guidelines while implementing this feature and keep the changes minimal and test-verified.

Frequently Asked Questions about coding-guidelines

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

FAQPage Schema
How do I stop an AI coding assistant from over-engineering solutions?

Apply simplicity-first guidelines that forbid speculative features, single-use abstractions, and unrequested configurability. The Skill instructs the agent to write the minimum code that solves the problem and rewrite anything a senior engineer would call overcomplicated.

How to keep AI code changes scoped to only what was requested?

Use surgical-change rules: every modified line must trace directly to the user's request. The agent must not refactor adjacent code, reformat unrelated sections, or delete pre-existing dead code unless explicitly asked.

When should I not use these coding guidelines?

Do not use them for architecture design, documentation writing, or non-code tasks, as stated in the Skill description. For trivial tasks, apply judgment rather than enforcing the full process overhead.

How do the guidelines verify that a bug fix actually works?

They use goal-driven execution: the agent writes a test that reproduces the bug, then makes it pass. Multi-step tasks are planned with explicit verification checks for each step.

Do these guidelines work with any programming language or framework?

Yes, the guidelines are language-agnostic behavioral instructions. They govern how the agent reasons, plans, and edits code rather than referencing any specific language, library, or toolchain.