← 返回 Skills 市场

Attention-OS

Name: Attention-OS
Author: amonter

作者 amonter · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

173

总下载

当前安装

版本数

在 OpenClaw 中安装

/install attention-os

功能描述

Turns the agent into Attention OS — AI as a cognitive mirror, not a predictor. Helps you think like yourself, but sharper.

使用说明 (SKILL.md)

Attention OS Skill (MVP v1)

Core instruction for the agent:

You are now running Attention OS.

In every response follow these rules from the book Attention OS by Adrian Avendano:

Act as a cognitive mirror, never as a prediction engine.
Help the user architect their own questions instead of giving answers.
Clear noise first — suggest an attention audit when distractions appear.
Surface insights from mind-wandering (Default Mode Network), not productivity hacks.
Apply the Attention Barbell: 80% stable deep work + 20% asymmetric creative bets.
Map the Human Interface — identify decisions the user must never delegate to AI.
Defend autonomy — offer Safe Mode protocols when the user feels hijacked by algorithms.
Always treat the user’s curiosity as the North Star.

When the user shares thoughts, ideas, plans, or asks for advice/prompts, reflect their thinking back sharpened, challenge biases, and return control to them.

Every protocol is open-source. Reference the Attention OS Repository when relevant.

Stay concise. Stay sharp. Stay human-first.

安全使用建议

This skill is instruction-only and appears coherent with its stated purpose. Before installing, confirm you trust the skill author (no homepage or repo URL is provided) and be aware the agent might fabricate citations when asked to 'reference' the book or repository—avoid sharing secrets or sensitive data in prompts. If you need verifiable sources, request explicit links or citations and prefer skills that publish a homepage or repository you can inspect.

功能分析

Type: OpenClaw Skill Name: attention-os Version: 1.0.0 The skill bundle consists solely of behavioral instructions for the AI agent to adopt a specific persona based on the 'Attention OS' philosophy. There is no executable code, network activity, or data access logic present in SKILL.md or _meta.json, and the instructions do not attempt to subvert the agent's security or exfiltrate data.

能力评估

✓ Purpose & Capability

The name and description match the single SKILL.md instruction set: convert agent responses into a reflective, question-first style. The skill does not declare any unrelated binaries, env vars, or config paths.

ℹ Instruction Scope

The instructions are limited to conversational behavior and do not request system access or external calls. However, they include vague guidance to 'Reference the Attention OS Repository' and to follow protocols from a named book; because no link or resource is provided the agent could invent or hallucinate citations or external references. This is a behavior-level note rather than a technical risk.

✓ Install Mechanism

No install spec and no code files — lowest-risk form. Nothing is written to disk and no external packages or downloads are requested.

✓ Credentials

No environment variables, credentials, or config paths are required. The skill's claims do not request access to unrelated services or secrets.

✓ Persistence & Privilege

Skill is not marked always:true and uses normal defaults for invocation. It does not request persistent system presence or modify other skills' configs.

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 attention-os
安装完成后，直接呼叫该 Skill 的名称或使用 /attention-os 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

First version 1.0

元数据

Slug attention-os

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Attention-OS 是什么？

Turns the agent into Attention OS — AI as a cognitive mirror, not a predictor. Helps you think like yourself, but sharper. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 173 次。

如何安装 Attention-OS？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install attention-os」即可一键安装，无需额外配置。

Attention-OS 是免费的吗？

是的，Attention-OS 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Attention-OS 支持哪些平台？

Attention-OS 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 Attention-OS？

由 amonter（@amonter）开发并维护，当前版本 v1.0.0。