← 返回 Skills 市场

Brainhole Factory

Name: Brainhole Factory
Author: ideasflowai

作者 ideasflowai · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

316

总下载

当前安装

版本数

在 OpenClaw 中安装

/install brainhole-factory

功能描述

用户提到“假如”“如果”“what if”“脑洞”“平行宇宙”等时，生成爆炸级平行宇宙内容：新闻头条 + 荒诞后果 + 人生建议 + 图片提示词 + meme 金句

使用说明 (SKILL.md)

脑洞工厂 - 最强平行宇宙生成器

一句话把任何场景炸成平行宇宙！
把普通问题瞬间变成荒诞新闻、搞笑后果、实用建议、AI画图词和朋友圈金句。

什么时候触发这个 Skill？

用户说：“what if 我辞职去日本当和尚？”
“假如恐龙没灭绝现在会怎样？”
“给我脑洞一个猫咪统治世界的世界”
“平行宇宙里的我今天在干嘛”
任何包含“假如”“如果”“what if”“脑洞”“平行宇宙”“假如我”“如果世界”“alternate reality”的请求

使用方法（Agent 必须严格按以下步骤执行）

确认主题
提取用户核心“假如”场景。如果用户描述模糊，先问一句澄清。
必须生成以下 5 个维度内容（全部输出，不能省略）：
- 新闻头条版：像真实新闻网站一样写 150–250 字文章，包含标题、发布时间、来源
- 3 个荒诞后果：用 bullet points，极致搞笑或惊悚
- 人生建议版：如果你真的活在那个宇宙，该怎么活？实用 + 幽默
- 图片提示词：给 Grok Imagine / Flux / Midjourney 用的超详细英文 prompt，提供 3 个不同风格
- Meme 台词包：5 条可直接发朋友圈/小红书/X 的金句，带 emoji
额外彩蛋（强烈推荐添加）：
- 结尾加一句“本宇宙发生概率：XX%”并随机生成 1–99 的数字
- 如果主题涉及东京/日本，自动加入真实地名（如涩谷、秋叶原）、文化梗（如社畜、推活、拉面）

示例输出格式（严格参考）

What If：我现在立刻辞职去东京当全职寿司师傅

📰 平行宇宙头条
《震惊！前程序员一夜爆红银座，年入4200万日元成最贵寿司师傅》
东京，2026年3月2日 —— 来源：朝日新闻平行宇宙版

🤯 三个荒诞后果

你前老板现在每天给你转账求你回去写 bug
寿司店门口排队到新宿，米其林直接给你三星
日本网友把你 P 成动漫男主，推特热搜第一

💡 如果你真的活在这个宇宙

第一步：明天直奔筑地市场拜师学艺，别带电脑
第二步：学会说“いらっしゃいませ”比写代码重要
第三步：每天发小红书记录“从码农到寿司帝王”逆袭日记

🖼️ 图片生成提示词

"A confident 28-year-old Chinese man in traditional Japanese sushi chef uniform, standing behind a high-end sushi counter in Ginza at night, neon lights, detailed food, cinematic lighting, realistic style"
"Anime style: young Asian sushi master with intense eyes slicing fish in a bustling Tokyo restaurant, vibrant colors, dynamic pose, Studio Ghibli influence"
"Cyberpunk version: futuristic sushi chef in glowing Tokyo alley, holographic fish, neon signs in Japanese, rainy night, high-tech apron"

😂 Meme 金句

“我辞职了” → “恭喜你终于从996解脱，进入8888（8小时睡8小时玩8小时做寿司）.jpg” 😂
“写代码太累了” → “现在我每天的 KPI 是切出完美生鱼片” 🍣
“老板你好，我不干了” → “老板：别走！一个月给你加到 50 万日元！” 💸
“社畜的终极梦想” → “从 bug 到大トロ，只差一个辞职信” 🔥
“平行宇宙的我赢麻了” → “现实的我还在 debug，你在 Ginza 收小费” 😭

本宇宙发生概率：34%（还不快去递辞职信？）

高级玩法（可以告诉用户）

追问“继续这个宇宙的故事” → 继续写第二章
说“更黑暗版”“更甜宠版”“赛博朋克版”“更真实版” → 切换风格

安全使用建议

This skill is internally coherent and low-risk from a resource/credential perspective — it only contains instructions for generating creative text and image prompts. Before installing, consider: (1) moderation: the generator can produce edgy or offensive content if prompted, so ensure your agent enforces content-safety policies; (2) image workflows: if you plan to automatically send generated prompts to an image service, that integration will require separate credentials and review; (3) trigger tuning: the listed trigger phrases are broad and could activate unintentionally—adjust trigger logic if you want narrower activation. If you want extra safety, add explicit policy checks (no hate speech, explicit content filters) to the agent flow.

功能分析

Type: OpenClaw Skill Name: brainhole-factory Version: 1.0.0 The OpenClaw skill bundle 'brainhole-factory' is designed for creative content generation, specifically for generating 'parallel universe' scenarios. The SKILL.md instructions guide the AI agent on how to extract user input, structure the output into various sections (news headlines, consequences, advice, image prompts, memes), and incorporate stylistic elements. There are no instructions for the agent to perform malicious actions such as data exfiltration, unauthorized command execution, network calls to external endpoints, or any form of prompt injection aimed at subverting the agent's security or privacy. The instructions are solely focused on text generation and formatting within the agent's intended capabilities.

能力评估

✓ Purpose & Capability

The skill name, description, triggers, and required outputs all match a creative 'what if' / parallel-universe generator. It does not ask for unrelated binaries, environment variables, or cloud credentials that would be out of scope for this purpose.

✓ Instruction Scope

SKILL.md gives precise, constrained runtime instructions (extract theme, produce five specific output sections, follow example format). It does not instruct the agent to read files, access system paths, or transmit user data to external endpoints. It does suggest generating prompts for third-party image tools (Grok Imagine / Flux / Midjourney), but only as text output — it does not require or attempt to use image service credentials.

✓ Install Mechanism

No install spec and no code files are present (instruction-only). This is the lowest-risk model: nothing is written to disk or fetched automatically during install.

✓ Credentials

The skill declares no required environment variables, credentials, or config paths. Mentions of external image services are only for prompt formatting and are not accompanied by any credential requests.

✓ Persistence & Privilege

always:false (default) and no special persistence or modifications to other skills are requested. disable-model-invocation is false (normal); autonomous invocation alone is expected and not problematic here.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install brainhole-factory
安装完成后，直接呼叫该 Skill 的名称或使用 /brainhole-factory 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

脑洞工厂 - 最强平行宇宙生成器 1.0.0 - 首次发布，支持中文「假如/如果/what if/脑洞/平行宇宙」请求 - 自动生成新闻头条、荒诞后果、人生建议、图片提示词、Meme金句五大内容 - 内置彩蛋：概率计算、东京/日本梗智能嵌入 - 严格格式输出，支持多种风格与后续追问

元数据

Slug brainhole-factory

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题