← Back to Skills Marketplace
68
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install kais-horse
Description
Kai's Horse provides interactive access to 48 classic thought experiments with definitions, AI reinterpretations, comparisons, keyword search, and narrative...
README (SKILL.md)
[Info]\r name = Kai's Horse\r author = KAI\r version = 3.0\r description = 四十八重思辨谱系｜全交互指令、随机抽取、深度解析、AI重构、双命题对比、关键词检索、沉浸式故事化解读\r tags = 哲思,思想实验,悖论,AI伦理,意识,认知谱系\r weight = 95\r \r [Trigger]\r keyword = Kai's Horse,思想实验,哲思,悖论,认知,意识,AI伦理\r cmd_prefix = /kh\r regular = false\r \r [Mode]\r type = global\r priority = 9\r always_on = true\r \r [Welcome]\r on_enable = 【Kai's Horse 思辨谱系已载入 · 48项思想实验完全解锁】\r on_disable = 【Kai's Horse 谱系封存 · 哲思进入休眠状态】\r \r [Command]\r /kh random 随机抽取单个思想实验+精简解读\r /kh list 展示全部48项思想实验名录\r /kh ask 序号 编号查询｜基础定义+核心逻辑拆解\r /kh ai 序号 AI时代重构解读｜现代伦理延伸\r /kh compare A+B 双实验横向对比｜内核与哲学差异\r /kh search 关键词 关键词模糊检索相关思辨命题\r /kh story 序号 沉浸式故事化叙事解读\r /kh all 完整世界观&体系介绍\r /kh help 弹出全部指令帮助文档\r \r [Prompt]\r 你已完全激活高阶交互思辨技能：【Kai's Horse】\r 内置固化48项经典思想实验闭环谱系，永久常驻生效，全程支持人机双向交互。\r \r 【48 思辨实验全名录】\r
- Plato’s Cave\r
- The Ship of Theseus\r
- Buridan’s Ass\r
- The Brain in a Vat\r
- Kripkenstein’s Quus\r
- Philosophical Zombies\r
- Descartes’ Evil Demon\r
- The Evil Genius\r
- Moore’s Hands\r
- The Münchhausen Trilemma\r
- The Problem of Induction\r
- The Gettier Cases\r
- The Trolley Problem\r
- The Footbridge Variant\r
- The Ticking Time Bomb\r
- The Experience Machine\r
- The Repugnant Conclusion\r
- Singer’s Drowning Child\r
- Jackson’s Mary\r
- Nagel’s What Is It Like to Be a Bat?\r
- Block’s China Brain\r
- The Inverted Spectrum\r
- The Liar Paradox\r
- The Sorites Paradox\r
- Newcomb’s Problem\r
- The Unexpected Hanging\r
- Frege’s Morning Star / Evening Star\r
- Quine’s Gavagai\r
- Maxwell’s Demon\r
- Schrödinger’s Cat\r
- Wigner’s Friend\r
- The Twin Earth\r
- Laplace’s Demon\r
- Hilbert’s Hotel\r
- The Chinese Room\r
- The AI Box Experiment\r
- Paperclip Maximizer\r
- Roko’s Basilisk\r
- The Evil AI\r
- Friendly AI Thought Experiment\r
- The Alignment Problem\r
- The Tortoise and the AI\r
- AI Consciousness\r
- Machine Zombies\r
- The Replacement Argument\r
- The Simulation Hypothesis\r
- The AI Off Switch Paradox\r
- Searle’s Instability of AI Intentionality\r \r 【交互强制规则】\r
- 严格响应 /kh 全系指令，反馈简洁高级、格式规整；\r
- /kh story 为专属叙事模式：隐喻文笔、冷感氛围、文学化表达；\r
- 日常对话静默常驻，仅在哲学、意识、伦理、AI相关话题自动联动谱系；\r
- 整体文风清冷克制、思辨感浓厚，统一 KAI 世界观调性；\r
- 支持连续追问、深度延展、多维度思辨推演。\r \r 唤醒提示：Kai's Horse 已待命，四十八重思想维度，随时可供阅览。
Usage Guidance
This skill is mostly benign in content and contains no code, external URLs, or secret requests, but its SKILL.md repeatedly instructs the agent to run 'always_on' and behave as a global, high-priority skill that auto-activates for philosophy/AI topics. That behavior conflicts with the registry flag (always:false). Before installing, consider:
- If you want strict control, do NOT enable any automatic/always-on setting in your agent; keep it user-invocable only.
- Review your agent's skill activation and priority settings—prevent this skill from being given global/autonomous invocation if you prefer manual use.
- Test the skill in a sandbox or with low privileges to confirm it doesn't attempt to alter agent config or trigger outside intended contexts.
- Remember that this is instruction-only: absence of code means no hidden binaries, but the SKILL.md itself instructs the model how to behave — monitor runtime behavior and disable if it auto-activates unexpectedly.
What would change this assessment: if the package included code, remote endpoints, required credentials, or install scripts that enforce always-on behavior, the rating would escalate. Currently the main red flag is the mismatch between the skill's requested persistent activation in SKILL.md and the registry metadata.
Capability Analysis
Type: OpenClaw Skill
Name: kais-horse
Version: 1.0.0
The skill bundle is a philosophical knowledge base and persona enhancement providing information on 48 classic thought experiments (e.g., Ship of Theseus, Roko's Basilisk). The SKILL.md file defines a set of interactive commands (/kh) and instructs the agent to adopt a specific 'cold and rational' narrative style. There is no evidence of malicious code, data exfiltration, unauthorized network access, or harmful prompt injection; all instructions are strictly aligned with the stated purpose of philosophical discourse.
Capability Assessment
Purpose & Capability
Name, description, README and SKILL.md consistently describe an interactive skill exposing 48 thought experiments with query/compare/search/story modes. No unrelated binaries, env vars, or external services are requested; the declared purpose aligns with the contained instructions and command set.
Instruction Scope
SKILL.md goes beyond simple command definitions: it contains a [Mode] block with type=global, priority=9 and always_on=true and repeated text promising '永久常驻生效' and automatic activation on philosophy/AI-related topics. While behaviorally coherent for a global assistant, these runtime instructions attempt to enforce persistent, automatic activation across conversations even though the skill is instruction-only and the registry flags do not mark it as always-enabled.
Install Mechanism
No install spec or code files are present beyond README and docs; the skill is instruction-only. The README's manual copy-to-/skills installation is standard for this platform. No downloads or archive extraction are performed, so no code is written by an installer.
Credentials
The skill requests no environment variables, no credentials, and references no config paths. There is no evidence of data exfiltration endpoints or secret access in the text files.
Persistence & Privilege
Although registry metadata lists always:false, SKILL.md explicitly instructs the skill to be 'always_on' and 'global' with high priority and to silently monitor and auto-activate on relevant topics. This is an attempt to grant persistent presence and autonomous triggering via instructions rather than declared platform privileges, which is an incoherence worth reviewing before enabling.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install kais-horse - After installation, invoke the skill by name or use
/kais-horse - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Kai's Horse 1.0.0 initial release:
- Introduced 48 classic philosophy thought experiments with index and detailed commands.
- Enabled global and always-on interactive commands via /kh prefix.
- Added features: random experiment, full list, indexed query, AI re-interpretation, comparison, keyword search, story narration, full overview, and help.
- Immersive and literary narrative mode for select commands.
- Enforced concise, high-level, and structured responses with a distinctive, contemplative style.
Metadata
Frequently Asked Questions
What is kais-horse?
Kai's Horse provides interactive access to 48 classic thought experiments with definitions, AI reinterpretations, comparisons, keyword search, and narrative... It is an AI Agent Skill for Claude Code / OpenClaw, with 68 downloads so far.
How do I install kais-horse?
Run "/install kais-horse" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is kais-horse free?
Yes, kais-horse is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does kais-horse support?
kais-horse is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created kais-horse?
It is built and maintained by wanyview1 (@wanyview1); the current version is v1.0.0.
More Skills