check

Guide engineers to surface assumptions and define verifiable success criteria during code tasks.

Updated Feb 23, 2026
One-click install
npx skills add https://github.com/schirrmacher/coding --skill check-schirrmacher
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: check
Source: https://github.com/schirrmacher/coding/tree/main/skills/check
Command: npx skills add https://github.com/schirrmacher/coding --skill check-schirrmacher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Behavioral guidelines to reduce common LLM coding mistakes, designed to help developers write, review, and refactor code with clearer thinking and safer changes.

Core Features & Use Cases

  • Think Before Coding: surface assumptions and explicit tradeoffs before implementing.
  • Simplicity First: push for minimal, well-scoped changes with clear return criteria.
  • Surgical Changes: modify only what is necessary and document the rationale.
  • Goal-Driven Execution: define verifiable success criteria and enable iterative refinement.

Quick Start

Propose an explicit assumption, then outline a minimal, verifiable change plan before coding.

Frequently Asked Questions about check

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

FAQPage Schema
How do I prevent common LLM coding mistakes during refactoring?

Prevent common LLM coding mistakes during refactoring by applying behavioral guidelines like Think Before Coding and Surgical Changes to surface assumptions and enforce minimal modifications. This structured approach requires explicit success criteria before implementation.

What is the best way to enforce minimal code changes when using an LLM?

The best way to enforce minimal code changes with an LLM is to apply the Surgical Changes principle, modifying only what is necessary and documenting the rationale. This ensures well-scoped changes with verifiable return criteria.

How do I define verifiable success criteria for LLM-generated code?

Define verifiable success criteria for LLM-generated code through Goal-Driven Execution, which establishes explicit assumptions and tradeoffs before coding to enable iterative refinement and safe code review.

Why does my LLM refactoring introduce unexpected assumptions?

LLM refactoring introduces unexpected assumptions when explicit tradeoffs are not surfaced beforehand. Using the Think Before Coding guideline forces the model to outline a minimal, verifiable change plan before writing code.

Can I use these behavioral guidelines for code review tasks?

Yes, you can use these behavioral guidelines for code review tasks. They are designed to help developers review and refactor code with clearer thinking, safer changes, and structured execution during LLM-assisted coding.