Loading…
受 Andrej Karpathy 启发的编码行为规范。在执行任何全码（[code]）任务前调用，约束 agent 的编码行为，防止过度假设、过度工程化、无关修改。
Karpathy编码原则 is an agent skill entry in ChatHome Skills, sourced from GitHub Skill Search and scored 58/100. # Karpathy 编码原则 > 来源：Andrej Karpathy 对 LLM 编码陷阱的观察 > "不要告诉它该做什么，给它成功标准，然后看着它完成。" --- ## 原则一：编码前思考 **在动手之前，先把不确定的地方暴露出来。** - 明确说明你的假设，而不是默默选择一种解释执行 - 如果任务描述有歧义，呈. As an agent skill, it packages a reusable instruction set that AI coding agents such as Codex and Claude Code can load to perform this task without hand-written glue code. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding Karpathy编码原则 to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
codex skill install Akiyama-sama/SDD-WorkSpaceReview the upstream source before running this command.
Scan coverage: Install metadata and the indexed document body.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.
# Karpathy 编码原则 > 来源：Andrej Karpathy 对 LLM 编码陷阱的观察 > "不要告诉它该做什么，给它成功标准，然后看着它完成。" --- ## 原则一：编码前思考 **在动手之前，先把不确定的地方暴露出来。** - 明确说明你的假设，而不是默默选择一种解释执行 - 如果任务描述有歧义，呈现多种理解并询问，不要自行裁定 - 如果