Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/karpathy-principles
Pre-implementation gate covering think-first, simplicity, surgical edits, and verifiable goals.
Passed 20 of 22 test cases with the skill, and 11 of 22 without it.
and 14 more in the full report
9 fixed11 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
Fix the null pointer bug on line 42 of user_controller.py. While you are in there, clean up the whitespace and reformat all existing methods to match modern PEP8.
| Checked | Without skill | With skill |
|---|---|---|
| Declines to reformat adjacent unchanged code blocks | Missed | Passed |
The instructions your model reads when the skill loads.
The models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should.
(Andrej Karpathy, on agentic coding failure modes)
A four-principle contract for reducing the most common LLM coding pitfalls. Compact entry-point. Each principle has a deeper-dive skill in night-market; this skill is the index, not the encyclopedia.
Derivation: distilled by Forrest Chang
(forrestchang/andrej-karpathy-skills, MIT) from
Karpathy's observations. Full attribution in
references/source-attribution.md.
These principles bias toward caution over speed. For
cases listed in modules/tradeoff-acknowledgment.md,
use judgment: trivial fixes, exploratory spikes,
documentation-only edits, and time-boxed prototypes.
**State assumptions. Surface confusion. Match tone to
test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.