skills.rest
tmdgusya
tmdgusyaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agentic-karpathy

Enforces surgical LLM coding changes with predefined rules and success criteria.

273|26|Updated Apr 5, 2026
Search Tags:#coding#guidelines#best-practices#code-review#guardrails#surgical-changes#llm-coding
One-click install
npx skills add https://github.com/tmdgusya/roach-pi --skill agentic-karpathy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agentic-karpathy
Source: https://github.com/tmdgusya/roach-pi/tree/main/extensions/agentic-harness/skills/agentic-karpathy
Command: npx skills add https://github.com/tmdgusya/roach-pi --skill agentic-karpathy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents common LLM coding mistakes by enforcing surgical changes, reading before editing, strict scope discipline, and explicit success criteria during software development.

Core Features & Use Cases

  • Enforces Hard Gates that must be satisfied before changes (Read before you write, Scope to the request, Verify assumptions, Define success).
  • Provides The Five Rules to guide safe coding, including Make Surgical Changes and Read The Existing Code, to minimize unnecessary edits.
  • Suitable for use during feature implementation, refactoring, or code reviews to ensure changes are minimal, well-justified, and verifiable.

Quick Start

Before writing any code, read the Karpathy Guidelines and apply the four hard gates and the five rules to ensure surgical, verifiable edits.

Frequently Asked Questions about agentic-karpathy

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

FAQPage Schema
How do I prevent LLM coding mistakes and unnecessary edits during feature development?▼

To prevent LLM coding mistakes, enforce surgical changes by applying hard gates like reading existing code before writing, verifying assumptions, and defining explicit success criteria to keep edits minimal and verifiable.

What are surgical changes in AI code generation and when should I use them?▼

Surgical changes in AI code generation are minimal, well-justified edits scoped strictly to the request. Use them during feature implementation, refactoring, or code reviews to minimize unnecessary modifications and maintain scope discipline.

How do I apply code review guardrails to verify LLM generated code assumptions?▼

To verify LLM generated code assumptions during code review, enforce explicit success criteria and require the model to read surrounding code before editing, ensuring all changes are traceable and assumptions are validated against the existing codebase.

Does enforcing strict scope discipline work across different programming languages?▼

Yes, enforcing strict scope discipline works across programming languages by applying universal rules like verifying assumptions and defining success, guiding users to stay within requested scope regardless of the specific language used.

When should I not use surgical coding discipline for AI assisted bug fixes?▼

You should not use surgical coding discipline when a bug fix requires broad architectural changes beyond the requested scope, as the rules enforce minimal edits and strict scope adherence to prevent unnecessary modifications.

Related Skills

Explore More Software Engineering Skills→
corticalstackcorticalstack
1

iterate-plan

Revise existing implementation plans with user feedback and codebase research.

Community
Intermediate
harrymunroharrymunro
1

prd

Generate a structured PRD with goals, user stories, and success metrics.

Community
Advanced
baphledbaphled
1

check-compliance

Run linting, formatting, security scans, and tests before committing code.

Community
Intermediate
sputnikussputnikus

karpathy-guidelines

Apply behavioral guidelines for AI coding assistants to reduce common LLM mistakes.

Community
Basic