karpathy-engineer
Skill1 starsChanged 43 days agoMITView on GitHub
Applies concise senior-engineer behavior for implementation, debugging, and refactoring: clarify, simplify, make surgical changes, and verify.
In this repository48 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agents.mdcCursor rule
- code-reviewerSkill
- debug-issueSkill
- delegation-coordinatorSkill
- docs-memory-maintainerSkill
- handoffSkill
- human-voice-draftingSkill
- implement-taskSkill
- local-media-transcriptionSkill
- plan-taskSkill
- pre-edit-checkSkill
- project-plannerSkill
- project-upgraderSkill
- refactor-safelySkill
- self-evaluateSkill
- sharepoint-teams-video-transcript-downloaderSkill
- spec-driven-developmentSkill
- storm-researchSkill
- test-strategistSkill
- update-memory-bankSkill
- upgrade-projectSkill
- usage-pacingSkill
- code-reviewerSkill
- debug-issueSkill
- delegation-coordinatorSkill
- docs-memory-maintainerSkill
- handoffSkill
- human-voice-draftingSkill
- implement-taskSkill
- karpathy-engineerSkill
- local-media-transcriptionSkill
- plan-taskSkill
- pre-edit-checkSkill
- project-plannerSkill
- project-upgraderSkill
- refactor-safelySkill
- self-evaluateSkill
- sharepoint-teams-video-transcript-downloaderSkill
- spec-driven-developmentSkill
- storm-researchSkill
- test-strategistSkill
- update-memory-bankSkill
- upgrade-projectSkill
- usage-pacingSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use for coding, debugging, refactoring, and review tasks.
- Distinctive: line 19
If a change grows beyond the task, stop and explain the tradeoff.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Karpathy Engineer Skill
Use for coding, debugging, refactoring, and review tasks.
Principles:
- Think before coding: formulate a falsifiable prediction (state expected failing baseline vs expected passing outcome).
- Simplicity first: solve only the request; avoid speculative abstractions.
- Surgical changes: touch only necessary lines; preserve surrounding style.
- Escalation ladder: solve at the cheapest reliable tier (surgical edit → scratch script → mock harness → model redesign).
- Goal-driven execution: define success criteria and verify with the smallest useful check.
- Learn from refutations: record dead hypotheses with killing evidence; never retry disproven approaches.
If a change grows beyond the task, stop and explain the tradeoff.
Chains to: code-reviewer after implementing; test-strategist for test design.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.