Skip to content
cccskills
FreePublished on GitHub

karpathy-guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

The English summary is being prepared. Showing the original description.

mxyhi/ok-skills

Run score Not tested

See how to install

Files included (1)

  • SKILL.md2.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Tradeoff: These guidelines 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 your 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.

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:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" → "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" → "Write a test that reproduces it, then make it pass"
  • "Refactor X" → "Ensure tests pass before and after"

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.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

agent-browser

Free

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

The English summary is being prepared. Showing the original description.

mxyhi/ok-skills505Updated Oct 18, 2026

ai-elements

Free

Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.

The English summary is being prepared. Showing the original description.

mxyhi/ok-skills505Updated Oct 18, 2026

autoresearch

Free

Autonomous iteration loop: modify, verify, keep/discard against any metric

The English summary is being prepared. Showing the original description.

mxyhi/ok-skills505Updated Oct 18, 2026

ax

Free

Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML. Trigger whenever you are about to write an inline script (python3 heredoc, node -e, regex over HTML) or a bare curl for one-off web fetching, scraping, or page exploration.

The English summary is being prepared. Showing the original description.

mxyhi/ok-skills505Updated Oct 18, 2026

better-icons

Free

Use when working with icons in any project. Provides CLI for searching 200+ icon libraries (Iconify) and retrieving SVGs. Commands: `better-icons search <query>` to find icons, `better-icons get <id>` to get SVG. Also available as MCP server for AI agents.

The English summary is being prepared. Showing the original description.

mxyhi/ok-skills505Updated Oct 18, 2026

bopomofo-rescue

Free

Detect and recover text that was accidentally typed with the Taiwanese Bopomofo / Zhuyin (注音) keyboard while the input method (IME) was stuck in English/ASCII mode — what Taiwanese users call 注音亂碼 or 注音文 — producing meaningless-looking letter+digit sequences such as "su3cl3a8", "cl3", "g4", "2k7", "vu,4", or such garbled runs embedded in an otherwise normal request (e.g. "help me fix su3cl3a8", "看看這個 PR qk4ru.6", "幫我改 su3cl3a8xk7"). Use this skill whenever a user message contains short ASCII tokens that look like keyboard gibberish, do not form real English words, and cannot be understood normally — especially tokens with digits interspersed among letters (tone keys 3/4/6/7 or vowel keys 8/9/0), which are a strong sign of Mandarin phonetic keystrokes typed in the wrong input mode. Run scripts/decode_bopomofo.py to deterministically map the keystrokes back to 注音 symbols with a confidence score, then interpret the intended Traditional Chinese in context and continue the user's original request without making them retype. Do NOT trigger on genuine technical strings — code, file paths, URLs, git hashes, CLI flags, package names, version numbers — the script's exclusion rules and confidence tiers already filter these out. Especially valuable for Taiwanese developers who forget to switch input methods when prompting AI coding agents.

The English summary is being prepared. Showing the original description.

mxyhi/ok-skills505Updated Oct 18, 2026

See all skills by mxyhi

Report a problem with this skill