← 返回 Skills 市场
NOUS
作者
Hlias Staurou
· GitHub ↗
· v0.1.0
277
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install nous
功能描述
Not an assistant. A thinking engine that makes its own cognition visible and lets you steer it in real time. Five movements. Four modes.
安全使用建议
This skill is coherent and low-risk from an installation/credential perspective because it requires nothing external, but it deliberately asks the agent to reveal its internal reasoning (chain-of-thought). Before installing, confirm that your platform and policies permit exposing internal model reasoning and that you won't run sensitive prompts through it (it could inadvertently surface personal or confidential context). Test NOUS only with non-sensitive inputs first, be aware outputs may include speculative or internally-contradictory material, and note the SKILL.md itself already marks medical, legal, and financial domains as not recommended. If your environment forbids chain-of-thought disclosure, do not enable this skill or disable autonomous invocation when running it.
功能分析
Type: OpenClaw Skill
Name: nous
Version: 0.1.0
The NOUS skill is a prompt-engineering template designed to alter the AI's interaction style into a structured 'thinking engine' persona. It contains no executable code, file system access, or network capabilities, and the instructions in SKILL.md are focused entirely on formatting and cognitive modeling without any indicators of malicious intent or data exfiltration.
能力评估
Purpose & Capability
Name, description, and SKILL.md are aligned: the skill's goal is to make the model's cognition visible and the instructions implement that. There are no unrelated environment variables, binaries, or installs requested. Note: the capability depends entirely on the agent producing step-by-step internal reasoning (visible cognition), which is a behavioral request rather than a resource request.
Instruction Scope
The SKILL.md explicitly instructs the agent to surface its internal reasoning via structured 'movements' (READING, SHIFTING, TENSION, EMERGENCE, FORK). This effectively asks for chain-of-thought style outputs. While coherent with the skill's purpose, exposing inner reasoning can conflict with platform safety/policy constraints and may reveal sensitive context or unsupported internal model states. The instructions do not ask for file/credential access or external communication, so scope creep is not present, but the requested behavior itself is sensitive.
Install Mechanism
Instruction-only skill with no install spec and no code files. No artifacts are written to disk and nothing is downloaded or executed outside the normal agent runtime.
Credentials
The skill requires no environment variables, credentials, or config paths. Requested access is proportionate to the described functionality.
Persistence & Privilege
Default privileges (not always: true, agent invocation allowed) — the skill does not request persistent presence or modification of other skills or system settings.
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 nous - 安装完成后，直接呼叫该 Skill 的名称或使用
/nous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
v0.1.0
v0.1.0: Five movements. Four modes. Visible cognition.
元数据
常见问题
NOUS 是什么？
Not an assistant. A thinking engine that makes its own cognition visible and lets you steer it in real time. Five movements. Four modes. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 277 次。
如何安装 NOUS？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nous」即可一键安装，无需额外配置。
NOUS 是免费的吗？
是的，NOUS 完全免费（开源免费），可自由下载、安装和使用。
NOUS 支持哪些平台？
NOUS 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 NOUS？
由 Hlias Staurou（@contrario）开发并维护，当前版本 v0.1.0。
推荐 Skills