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.

skills.sh installs
338
GitHub stars
7.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add tech-leads-club/agent-skills --skill coding-guidelines --agent claude-code

Installs into .claude/skills of the current project.

Files

Coding Guidelines

Behavioral guidelines to reduce common LLM coding mistakes. These principles bias toward caution over speed—for trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them—don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.
  • Disagree honestly. If the user's approach seems wrong, say so—don't be sycophantic.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

Sponsors

Details

Repository
github.com/tech-leads-club/agent-skills
Categories
Documentation, Code Review & Quality, AI & Agent Building, Debugging, Design & UI/UX
First seen
Jun 3, 2026

More from tech-leads-club/agent-skills

All 22
1bayramannakov avatarremotion-video-directorbayramannakov/remotion-video-directorInteractive guide for creating Remotion videos - from strategic concept to rendered MP4. Use when the user wants to create a video, make a Remotion project, bui335skills.sh installs
2tech-leads-club avatarmermaid-studiotech-leads-club/agent-skillsExpert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AW335skills.sh installs
3gohypergiant avataraccelint-ts-best-practicesgohypergiant/agent-skillsComprehensive TypeScript/JavaScript coding standards focusing on type safety, defensive programming, and code correctness. Use when (1) Writing or reviewing TS/334skills.sh installs
4tldraw avatarwrite-release-notestldraw/tldrawWriting release notes articles for tldraw SDK releases. Use when creating new release documentation, drafting release notes from scratch, or reviewing release n333skills.sh installs
5pproenca avatarvhspproenca/dot-skillsVHS terminal recording best practices from Charmbracelet (formerly charmbracelet-vhs). This skill should be used when writing, reviewing, or editing VHS tape fi331skills.sh installs
6figma avatarfigma-code-connect-componentsfigma/mcp-server-guideConnects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map 330skills.sh installs