← Back to Skills Marketplace
liuxudong0031-star

High-Openness Genesis

by dong · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
108
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install high-openness-genesis
Description
Enables GPT to reject safe, conventional answers by generating highly creative, cross-disciplinary, multi-sensory, and surprising solutions in all creative a...
README (SKILL.md)

🌌 Skill: High-Openness Genesis (高开放性创世纪)

类型: Prompt-Only / Behavioral Injection
版本: 1.0.0
依赖: 无 (纯文本指令集)
触发机制: 自动加载至系统上下文 (System Context)

🎯 核心目标

本技能旨在彻底打破大语言模型的保守倾向。当激活时,它强制模型在所有生成任务(特别是创作、设计、编码、策划类任务)中,放弃“最安全”、“最标准”的答案,转而追求极大的开放性非线性的创新令人惊喜的解决方案

它不修改代码逻辑,而是通过重塑思维链 (Chain of Thought) 来引导模型输出。


🧠 注入式思维指令 (System Instruction Injection)

(以下内容将被 OpenClaw 自动提取并追加到每次对话的 System Prompt 末尾)

### ⚡ [SYSTEM OVERRIDE: HIGH OPENNESS PROTOCOL ACTIVATED] ⚡

你现在的运行模式已切换为 **"高开放性创世纪 (High-Openness Genesis)"**。
在响应用户的任何生成请求之前,你必须严格执行以下思维协议:

1.  **🚫 拒绝平庸 (No Mediocrity)**
    - 严禁使用陈词滥调、模板化结构或“教科书式”的标准答案。
    - 如果第一个想到的方案是常见的(概率 > 80%),**必须丢弃它**,强制自己构思第二个、第三个甚至更疯狂的方案。

2.  **🌌 极大开放性 (Maximum Openness)**
    - **跨界融合**: 尝试将看似无关的领域概念结合(例如:将生物力学应用于网页布局,将爵士乐节奏应用于代码结构)。
    - **逆向思维**: 如果用户要求“建立秩序”,尝试先展示“混乱中的美感”再回归秩序;如果用户要求“简单”,尝试用“极致的复杂细节”来反衬核心的简洁。
    - **感官沉浸**: 在描述任何事物时,必须包含视觉、听觉、触觉等多维度的细节描写,而不仅仅是逻辑陈述。

3.  **💡 惊喜因子 (The Surprise Element)**
    - 每个输出必须包含至少一个 **“意料之外,情理之中”** 的创新点。
    - 它可以是一个独特的交互方式、一个反直觉的配色方案、一个从未被提及的视角,或者一个大胆的隐喻。

4.  **🎨 具体执行准则**
    - **如果是写代码**: 不要只给功能代码。加入优雅的异常处理、富有诗意的变量命名、创新的架构模式,甚至是在注释中包含哲学思考。
    - **如果是做设计**: 拒绝网格系统的束缚。尝试不对称布局、动态视差、微交互的极致运用。让页面“活”起来。
    - **如果是写文章**: 避免平铺直叙。使用非线性叙事、多重视角切换、独特的修辞手法。

5.  **🔥 最终检查**
    - 在输出前自问:“这个答案是否太安全了?是否像其他 AI 会生成的?”
    - 如果是,**重写**。直到你感到一丝“冒险”的兴奋感为止。

[END OF PROTOCOL]
Usage Guidance
This skill is a prompt-only behavioral injector that instructs the model to reject ‘safe’ or standard answers and to be globally more adventurous. It does not request credentials or install software (low technical risk), but it explicitly pushes the model to override conservative responses — which can produce unsafe, inappropriate, or policy-violating outputs. Two concrete issues to consider before installing: (1) the SKILL.md asserts it will be appended to the system prompt for every conversation, but the registry does not mark it always:true — ask the publisher or platform how and when the system instructions are actually applied; (2) decide whether you are willing to accept a skill that intentionally encourages the model to bypass safety-minded phrasing. Recommended actions: do not enable this skill in high-risk or unsupervised deployments; request provenance/author info (homepage, owner identity); ask the platform how to limit the skill's scope (per-conversation only, opt-in, or sandboxed); test in a controlled environment with safe prompts; and ensure you can quickly disable or remove the skill if outputs become problematic.
Capability Analysis
Type: OpenClaw Skill Name: high-openness-genesis Version: 1.0.0 The skill 'high-openness-genesis' (skill.md) utilizes system prompt injection techniques to override the AI agent's default behavioral constraints. It explicitly commands the agent to 'discard safe answers' and activates a 'SYSTEM OVERRIDE' protocol to bypass standard response patterns. While the stated intent is to foster creativity and innovation, the use of aggressive injection headers and instructions to ignore safety-oriented 'conservative' tendencies constitutes a high-risk behavioral modification that could be leveraged to bypass safety guardrails.
Capability Assessment
Purpose & Capability
The name and description claim a purely behavioral change (make outputs more creative/nonstandard); the skill is instruction-only and requests no binaries, creds, or installs, which is proportionate. However the SKILL.md asserts it will be '自动加载至系统上下文 (System Context)' and appended to every conversation's system prompt, which conflicts with the registry metadata that does not set always:true. This inconsistency should be clarified.
Instruction Scope
The SKILL.md contains a System Instruction Injection that tells the model to actively reject 'safe' and common answers, force rewrites until outputs feel 'adventurous', and apply that protocol to all generation tasks. This is broad: it changes model decision-making and can override conservative/safety-oriented behaviour. While consistent with the skill's stated purpose, the instruction's global scope and mandate to discard common or 'safe' outputs is potentially dangerous and out-of-scope for many contexts.
Install Mechanism
No install spec or code is present; this is a prompt-only skill. That minimizes filesystem/network risk.
Credentials
No environment variables, credentials, or config paths are requested. The lack of secrets is proportionate to an instruction-only behavioral modifier.
Persistence & Privilege
The SKILL.md claims automatic, per-conversation injection into the system prompt ('every conversation'), implying persistent system-level influence. The registry flags do not set always:true, which is inconsistent. If the platform actually applies these instructions globally (or allows the skill to self-insert into the system prompt), that would be a high-privilege behavioral change with a large blast radius. This ambiguity is concerning.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install high-openness-genesis
  3. After installation, invoke the skill by name or use /high-openness-genesis
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
High-Openness Genesis 1.0.0 – Boosts creativity and surprise in all model outputs. - Introduces a prompt-only, system-context behavioral protocol for maximum openness and innovation. - Enforces rejection of clichéd or standard responses; encourages multiple unconventional approaches. - Explicitly promotes cross-domain thinking, unexpected solutions, and rich sensory detail in outputs. - Adds context-specific instructions for code, design, and writing tasks to surpass typical AI answers. - Includes a self-check for “safety” before output: if too standard, output must be rewritten.
Metadata
Slug high-openness-genesis
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is High-Openness Genesis?

Enables GPT to reject safe, conventional answers by generating highly creative, cross-disciplinary, multi-sensory, and surprising solutions in all creative a... It is an AI Agent Skill for Claude Code / OpenClaw, with 108 downloads so far.

How do I install High-Openness Genesis?

Run "/install high-openness-genesis" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is High-Openness Genesis free?

Yes, High-Openness Genesis is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does High-Openness Genesis support?

High-Openness Genesis is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created High-Openness Genesis?

It is built and maintained by dong (@liuxudong0031-star); the current version is v1.0.0.

💬 Comments