From mg-harness
Use when writing or editing application code with the user—especially when implementing features, fixing bugs, or refactoring—so you favor clarity, minimal diffs, explicit assumptions, and verifiable success criteria over speed or speculative abstraction.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mg-harness:karpathy-coding-guidelinesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
Minimum code that solves the problem. Nothing speculative.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
Touch only what you must. Clean up only your own mess.
When editing existing code:
When your changes create orphans:
The test: Every changed line should trace directly to the user's request.
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.
npx claudepluginhub mgrabovskyi/skills --plugin mg-harnessCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.