Guide LLM coding with upfront thinking, simplicity, and surgical edits.
npx skills add https://github.com/caidanw/skills --skill karpathy-guidelines-caidanw
Please help me install this Agent Skill. Skill: karpathy-guidelines Source: https://github.com/caidanw/skills/tree/main/karpathy-guidelines Command: npx skills add https://github.com/caidanw/skills --skill karpathy-guidelines-caidanw
This Skill helps prevent common coding errors made by Large Language Models by providing a set of behavioral guidelines focused on clarity, simplicity, and verification.
Apply the karpathy-guidelines skill to ensure the LLM writes simple, surgical, and goal-driven code.
High-intent search queries and answers about installing and using this skill.
Prevent LLM coding errors during refactoring by applying behavioral guidelines that enforce surgical modifications, ensuring the model touches only necessary lines and avoids introducing speculative features.
Best practices for LLM code generation simplicity involve surfacing assumptions upfront, writing minimal non-speculative code, and defining verifiable success criteria to maintain goal-driven execution.
Ensure LLM code quality by establishing pre-coding clarity where tradeoffs are considered and assumptions are surfaced before implementation, enforcing simplicity and goal-oriented development.
Yes, these coding guidelines are applicable during code writing, review, and refactoring phases to enhance overall code quality and reduce overcomplication across the development lifecycle.
An LLM overcomplicates simple code modifications when lacking upfront thinking and surgical editing constraints, leading to speculative features rather than focused, minimal changes to necessary lines.
Define verifiable success criteria for LLM tasks by establishing goal-oriented development parameters upfront, ensuring the generated code meets specific, testable outcomes without unnecessary modifications.
SunS1eep1ngApply behavioral guidelines for surgical code changes and verifiable success criteria.
vinayakgProvides behavioral guidelines for LLMs to minimize coding errors through simplicity and surgical changes.
schirrmacherGuide engineers to surface assumptions and define verifiable success criteria during code tasks.
oguzhanguvenkayaApply behavioral guidelines to reduce LLM coding mistakes during code tasks.
