How-to11月11日 16:45

用 Claude Fable 5.2 写出 220KB 全代码沙漠巨虫游戏

5/ 只写代码：玩家操控一条沙漠巨虫，从沙下钻出来吞掉运输车。整个游戏 220KB，比一张手机照片还小，地形、巨虫和爆炸特效全是代码画的。这么小的体积，放进网页或小程序分发几乎没有门槛。 h...

AI Will@FinanceYF5

Post

Why we picked it

有人用 Claude Fable 5.2 加 10 条提示词，让 Claude Code 从零写出一个 220KB、3400 行的沙漠巨虫游戏，地形和特效全是代码画的。跟需要美术资源的游戏开发比，这条路径省掉了素材环节。想试 vibe coding 或者做网页小游戏的人，代码已开源可以直接扒。

开发者 AmirMušić 用 Claude Fable 5.2 在 Claude Code 里从零生成了一款沙漠巨虫游戏：玩家操控巨虫从沙下钻出吞掉运输车，全程由代码绘制。整个游戏仅 220KB、3400 行代码，通过 10 条提示词完成，比一张手机照片还小。

Body

地形、巨虫动画和爆炸特效没有任何美术资源，全部由程序化代码渲染。这种体量让游戏可以直接嵌入网页或小程序分发，不需要额外下载安装。

该项目展示了 vibe coding 工作流的实际效果：10 条提示词、单一模型在 Claude Code 环境中独立完成从逻辑到视觉的全部实现。代码已开源在 GitHub，开发者可以直接查看提示词与产出结构的对应关系。

Original · AI Will

5/ 只写代码：玩家操控一条沙漠巨虫，从沙下钻出来吞掉运输车。整个游戏 220KB，比一张手机照片还小，地形、巨虫和爆炸特效全是代码画的。这么小的体积，放进网页或小程序分发几乎没有门槛。 x.com/AmirMushich/st… AmirMušić @AmirMushich Claude Fable 5.2 produced this game - fully in code 220kb, 3400 lines of code, 10 prompts every model built from scratch in Claude Code Code: github.com/amirmushichge/…

Industry Coordinates & Source Verification

This report is categorized under AITOP's "How-to" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude Code, Claude Fable, vibe coding, 提示词工程.

Source attribution: curated from AI Will (@FinanceYF5).

#Claude Code #Claude Fable #vibe coding #提示词工程

Keep reading

Recent stories with the same tag or section

How-to Builders15:59

Chinese content开发者用 Claude Code 自制 Beep Locator，声源定位精度约 40 厘米

Simon Willison 搬家后找不到纸箱里响的旧一氧化碳探测器，就让 Claude Code 写了个网页程序，五台手机协同做时间差定位，精度到 40 厘米。和需要专用阵列设备的声源定位方案不同，这套东西只用浏览器和消费级设备就能跑，代码在 GitHub 上，想做声学或调试类小工具的开发者可以看看实现细节。

#Claude Code #Beep Locator #Simon Willison #声源定位

IT之家Source

How-to BuildersSelected15:43

Claude Prompt Recreates 255M-View 3D Short in Blender

The interesting part is that a single prompt encodes an entire production pipeline — script, voiceover, scene layout and rendering rules — so model differences surface as creative judgement rather than code quality. Anyone making faceless YouTube Shorts or explainer content can replicate it with a free local stack and a mid-range GPU. Teams comparing frontier coding agents get a concrete, reproducible side-by-side of Opus 5.5 versus Fable 5.2 on a creative task, though one run per model says little about consistency.

#Claude #Claude Code #prompt engineering #Blender

AI Will@FinanceYF5Source

How-to BuildersSelected15:33

Pruning Claude Skills and Agent Context Cuts One Third of Rules

The non-obvious point is that context files and skills are maintenance liabilities that age badly as models improve — a leaner setup can outperform a heavily engineered one. Developers running Claude Code or similar agent setups should audit their rules periodically and use this checklist as a ready-made audit prompt. Compared with manual rule reviews, delegating the inventory-and-confirm flow to the agent itself makes the cleanup repeatable across projects.

#Claude #Claude Code #prompt engineering #agents