Based on Andrej Karpathy's guidelines, this addresses the habits that trip up LLMs when writing code. It pushes for stating assumptions upfront, keeping implementations minimal without speculative features, making surgical edits that don't refactor unrelated code, and defining verifiable success criteria before starting work. The "think before coding" section is especially pointed about surfacing confusion rather than silently picking an interpretation. Use it when you're actually writing or modifying code, not for architecture discussions or documentation. It's opinionated about simplicity over flexibility, which means you'll need to override it when building genuinely extensible systems.
npx -y skills add tech-leads-club/agent-skills --skill coding-guidelines --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot