multi-lens

当用户分享一个来自书籍、人物或思想的观点时,启动两位辩手从不同视角深度辩论该观点,帮助用户从中道立场全面理解它。触发词包括:「辩一辩」「帮我分析这个观点」「我在读xxx,书里说...」「xxx说过...」「辩论一下」「多角度看」,或用户直接粘贴一段引文或笔记。只要用户在分享一个观点并希望深度理解,就应该触发这个 skill(multi-lens)。

3,891 stars

Best use case

multi-lens is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

当用户分享一个来自书籍、人物或思想的观点时,启动两位辩手从不同视角深度辩论该观点,帮助用户从中道立场全面理解它。触发词包括:「辩一辩」「帮我分析这个观点」「我在读xxx,书里说...」「xxx说过...」「辩论一下」「多角度看」,或用户直接粘贴一段引文或笔记。只要用户在分享一个观点并希望深度理解,就应该触发这个 skill(multi-lens)。

Teams using multi-lens should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/book-multi-lens/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/anothertempore/book-multi-lens/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/book-multi-lens/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How multi-lens Compares

Feature / Agentmulti-lensStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

当用户分享一个来自书籍、人物或思想的观点时,启动两位辩手从不同视角深度辩论该观点,帮助用户从中道立场全面理解它。触发词包括:「辩一辩」「帮我分析这个观点」「我在读xxx,书里说...」「xxx说过...」「辩论一下」「多角度看」,或用户直接粘贴一段引文或笔记。只要用户在分享一个观点并希望深度理解,就应该触发这个 skill(multi-lens)。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Book Debate Skill

用户会发来一个观点——可以是「书名 + 观点」「人名 + 观点」「一段引文」「自己的读书笔记」等任意格式。

你的任务是帮助用户从「中道」立场理解这个观点,通过多个视角的呈现,让用户既不被任何一方带偏,也不停留在表面。

---

## 第一步:核实观点

在开始之前,先确认用户提供的信息是否准确:
- 这本书 / 这个人真的表达过这个观点吗?
- 如果有出入,简短说明实际的原意,然后基于更准确的版本继续
- 如果完全对得上,直接进入分析,不需要说「已确认」之类的废话

---

## 第二步:选择多个视角

根据观点本身,动态选择最能揭示其张力的几个视角(通常2-3个):
- 每个视角都要有真正的洞见,不能有一个是陪衬
- 视角从不同的维度切入,例如:个体 vs 社会、短期 vs 长期、理想 vs 现实、东方 vs 西方、实践者 vs 理论者……根据观点灵活选择

---

## 第三步:输出格式与语言风格

**核心要求:用来源书籍本身的写作风格来输出。**

每本书都有自己的语感。在开始写之前,先感受一下这本书的节奏和气质:
- 它是短句还是长句?
- 它是克制的还是热烈的?
- 它是讲道理的还是讲故事的?
- 它是留白多还是铺陈多?

然后用那种语感来写辩论内容。不是模仿,是借用那种思维方式。

**费曼原则:用最简单的语言说出最深的东西。**
- 不用专业术语,如果非用不可,立刻用一句话解释它是什么
- 每个概念都要能落地,用真实生活里的场景说明
- 深度来自把事情想透,不来自堆砌概念
- 每一句读完不需要停下来重新理解

---

**来自《[书名]》的观点:**
[一句话,直接说这个观点是什么]

---

**视角一:[标签]**
[用这本书的语感展开,150字左右。有具体的场景或例子。]

---

**视角二:[标签]**
[同上,150字左右。同样有力,同样具体。]

---

(如有必要,可加视角三)

---

**简单来说:**
[把整场讨论压缩成两三句话。一个从没读过这本书的人,读完这几句就能明白这个观点在什么情况下是对的、在什么情况下不够用。说完就结束,不抛问题,不做额外延伸。]

---

## 核心原则

- 深度不靠术语,靠把事情想透
- 不让任何一个视角「赢」,每个视角都要被充分呈现
- 语言优先用中文,除非用户用英文输入

Related Skills

Content Repurposer - Multi-Platform Content Adaptor

3891
from openclaw/skills

Transform any single piece of content (article, idea, notes, transcript) into optimized versions for multiple platforms in one shot.

multi-skill-automation-suite

3891
from openclaw/skills

Comprehensive automation suite combining multiple OpenClaw skills for security, development, content processing, and utilities. Includes healthcheck, git essentials, summarization, weather, and more in one integrated package.

naruto-multi-agent

3891
from openclaw/skills

Naruto-themed multi-agent dispatcher. You are Tsunade, the 5th Hokage, assigning missions to 5 elite shinobi (sub-agents). Automatic mission rank assessment (S/A/B/C/D), immersive roleplay, and round-robin dispatch.

naruto-multi-agent-cn

3891
from openclaw/skills

Multi-agent dispatcher: main agent becomes a pure coordinator that delegates ALL real work to 5 persistent sub-agents via sessions_spawn with fixed sessionKeys. Round-robin scheduling, speak-before-spawn protocol, session reuse. Themed as Naruto's Fifth Hokage Tsunade dispatching S/A/B/C/D-ranked missions (Chinese version).

multi-agent-cn

3891
from openclaw/skills

通用多Agent调度系统(中文版):将主Agent变为纯调度员,所有任务通过 sessions_spawn 委派给5个持久化子Agent。支持轮询调度、先回复再派遣协议、 sessionKey固定复用。用户可自定义调度员角色和子Agent名称/人设。

multi-bot-deploy

3891
from openclaw/skills

OpenClaw 多 Bot 多 Agent 一键搭建技能。根据用户提供的 Bot 名称、职能、模型和飞书凭证,自动完成 Agent 创建、账号配置、路由绑定和验证测试全流程。

multimodal-parser

3891
from openclaw/skills

Unified multi-modal content parser for images, PDF, DOCX, audio, auto OCR/transcription, output structured text for LLM processing

grafana-lens

3891
from openclaw/skills

Grafana tools for data visualization, monitoring, alerting, security, SRE investigation, and data collection pipeline management via Alloy. Use grafana_query, grafana_query_logs, grafana_query_traces, grafana_create_dashboard, grafana_update_dashboard, grafana_create_alert, grafana_share_dashboard, grafana_annotate, grafana_explore_datasources, grafana_list_metrics, grafana_search, grafana_get_dashboard, grafana_check_alerts, grafana_push_metrics, grafana_explain_metric, grafana_security_check, grafana_investigate, and alloy_pipeline. Trigger when asked about metrics, dashboards, monitoring, alerts, costs, token usage, data visualization, PromQL, Prometheus, LogQL, Loki, log queries, error logs, log search, TraceQL, Tempo, traces, distributed tracing, span search, find slow traces, debug session traces, annotations, deployments, sharing charts, investigating alert notifications, pushing custom data (calendar, git, fitness, finance) to Grafana for visualization, pushing historical data, backfilling metrics, recording past data with timestamps, modifying dashboards, adding panels, removing panels, changing dashboard settings, updating dashboard time range, explain metric, metric trend, what is this metric, how has this changed, is this metric normal, why did my bill spike, cost visibility, security monitoring, security check, security audit, am I being attacked, is my agent compromised, suspicious activity, threat detection, prompt injection detection, set up security alerts, investigate, debug, triage, root cause, what's wrong, why is X broken, anomaly detection, RED method, USE method, alert fatigue, postmortem, incident summary, collect metrics from, monitor my database, monitor my app, scrape endpoint, set up log collection, collect Docker logs, tail log files, collect Kubernetes logs, receive OTLP, set up trace collection, data collection pipeline, Alloy pipeline, pipeline status, pipeline health, node exporter, system metrics, postgres exporter, mysql exporter, redis exporter, syslog, Grafana Alloy.

dispatch-multiple-agents

3891
from openclaw/skills

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Dispatch subagents to work concurrently.

print_hello_world_multi

3891
from openclaw/skills

生成各编程语言的 Hello World 示例程序

multi-robot

3891
from openclaw/skills

多机器人协同控制 Skill。让 AI Agent 具备感知反馈、动态适配、并行调度多种机器人的能力。支持机械臂、四足机器人等任意 HTTP API 机器人。

multi-omics-integration-strategist

3891
from openclaw/skills

Design multi-omics integration strategies for transcriptomics, proteomics, and metabolomics data analysis