Enforce an assumptions-first, test-driven workflow before writing code.
npx skills add https://github.com/adryanev/.dotfiles --skill karpathy-mode
Please help me install this Agent Skill. Skill: karpathy-mode Source: https://github.com/adryanev/.dotfiles/tree/main/.agents/skills/karpathy-mode Command: npx skills add https://github.com/adryanev/.dotfiles --skill karpathy-mode
This skill enforces a disciplined coding workflow that surfaces assumptions, prioritizes simplicity, and requires test-driven execution to prevent common LLM mistakes during development.
Begin coding with explicit assumptions and ask clarifying questions before implementing any feature.
High-intent search queries and answers about installing and using this skill.
To enforce assumption surfacing during LLM-assisted coding, apply a disciplined, assumptions-first workflow that explicitly prompts for clarifications and mandates narrow, test-driven steps before writing any code.
The best way to prevent LLM coding mistakes is to enforce a disciplined workflow that prioritizes simplicity, surfaces decisions, and requires test-driven execution to ensure minimal, surgical changes over speculative refactors.
Start a test-driven pair-programming session by explicitly stating your assumptions and asking clarifying questions before implementing any feature, ensuring the LLM takes narrow, surgical steps before writing code.
Yes, a disciplined coding workflow works for debugging and code reviews by surfacing implicit assumptions, prompting for necessary clarifications, and enforcing minimal changes to improve overall code quality.
You should avoid speculative refactoring when a careful, minimal output is requested, opting instead for a disciplined workflow that mandates narrow, test-driven steps to ensure surgical code changes.
schirrmacherGuide engineers to surface assumptions and define verifiable success criteria during code tasks.
CyapstayeEnforce the Red-Green-Refactor cycle with failing tests before implementation.
PhauksOptimize Claude Code tasks with parallel calls and subagent delegation.
henrycashe26Enforce simplicity, surgical edits, and goal-driven verification in coding tasks.
