Karpathy guidelines — behavioral rules against common LLM coding mistakes
Think before coding, simplicity first, surgical changes, goal-driven execution — derived from Andrej Karpathy's observations on LLM coding pitfalls
- What
- Think before coding, simplicity first, surgical changes, goal-driven execution — derived from Andrej Karpathy's observations on LLM coding pitfalls
- Cost
- Free
- Needs
- nothing to install — the skill is a set of behavioral guidelines your agent applies when writing, reviewing or refactoring code
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @multica-ai's behavioral guidelines for agents, derived from Andrej Karpathy's observations on how LLM-written code goes wrong. Four rules: think before coding (state assumptions explicitly, surface tradeoffs, push back when a simpler approach exists, ask instead of hiding confusion), simplicity first (minimum code that solves the problem — no speculative features, single-use abstractions, unrequested configurability, or impossible-scenario error handling; "if you write 200 lines and it could be 50, rewrite it"), surgical changes (touch only what the request requires, match existing style, mention unrelated dead code instead of deleting it, clean up only the orphans your own changes created), and goal-driven execution (transform tasks into verifiable success criteria and loop until verified — "add validation" becomes "write tests for invalid inputs, then make them pass"). MIT-licensed per the skill's frontmatter (note: the repo manifest declares no license — see caveat). Honest caveats: the guidelines bias toward caution over speed, so use judgment on trivial tasks; the tradeoff list is explicitly about coding agents, not a general writing style; license stated as MIT in the SKILL.md frontmatter while the repository manifest shows none — confirm before redistributing. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Karpathy guidelines is a free listing for behavioral guidelines for agents, from Karpathy's observations on LLM coding pitfalls. Four rules: think before coding, simplicity first, surgical changes, and goal-driven execution. Think before coding means stating assumptions explicitly, surfacing tradeoffs, and asking instead of hiding confusion. Simplicity means the minimum code that solves the problem, with no speculative features.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 2c60614Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: nothing to install — the skill is a set of behavioral guidelines your agent applies when writing, reviewing or refactoring code Install "Karpathy guidelines — behavioral rules against common LLM coding mistakes" for me. It gives my agent @multica-ai's guidelines derived from Andrej Karpathy's LLM coding pitfalls: think before coding (state assumptions, surface tradeoffs, ask), simplicity first (minimum code, no speculation), surgical changes (minimal diffs, match style), goal-driven execution (verifiable success criteria, loop until verified). MIT-licensed per the SKILL.md frontmatter (repository manifest declares no license — confirm before redistributing). Repository: https://raw.githubusercontent.com/multica-ai/andrej-karpathy-skills/2c606141936f1eeef17fa3043a72095b4765b9c2/skills/karpathy-guidelines/SKILL.md Pinned version: install the code at commit 2c606141936f1eeef17fa3043a72095b4765b9c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "karpathy-guidelines". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing — they are guidelines; tell the agent to apply them on its next coding task). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 2c60614 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.