闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > sensitivity-charts
s

灵敏度图表

技能标识：sensitivity-charts

Visualize how changes in variables affect outcomes. Use for risk analysis and decision support.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.0.0
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

灵敏度图表

敏感性图表

元数据

  • - 名称: sensitivity-charts
  • 描述: 敏感性分析与龙卷风图
  • 触发词: 敏感性、龙卷风图、假设分析、变量影响

指令

对$ARGUMENTS执行敏感性分析。

框架

龙卷风图

基准情景：1亿美元
│
┌─────────┼─────────┐
│ +2000万│ │-1000万 价格
├─────────┼─────────┤
│ +1500万│ │-800万 销量
├─────────┼─────────┤
│ +800万│ │-1200万 成本
├─────────┼─────────┤
│ +500万│ │-300万 组合
└─────────┼─────────┘
│
▼

待测试变量

变量范围影响程度
价格±10%高
销量
±20% | 高 | | 成本 | ±15% | 中 | | 组合 | ±5% | 低 |

输出

敏感性分析：[决策/项目]

变量影响排名

变量基准值低值情景高值情景影响
价格10085 (-15%)115 (+15%)3000万
销量
100万 | 80万 | 120万 | 2500万 | | 成本 | 50 | 45 | 55 | 2000万 | | 组合 | 50/50 | 40/60 | 60/40 | 1000万 |

情景分析

情景净现值概率期望值
基准情景1亿美元50%5000万
乐观情景
1.5亿美元 | 20% | 3000万 | | 悲观情景 | 6000万 | 30% | 1800万 | | 期望值 | | | 9800万 |

关键发现

  1. 1. 最敏感变量：价格（±3000万影响）
  2. 最不敏感变量：组合（±1000万影响）
  3. 盈亏平衡点：[分析]

风险缓解措施

  1. 1. [针对最敏感变量的缓解措施]
  2. [针对第二敏感变量的缓解措施]

提示

  • - 重点关注前5-7个变量
  • 使用现实范围
  • 同时展示上行和下行空间

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 sensitivity-charts-1776112082 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 sensitivity-charts-1776112082 技能

通过命令行安装

skillhub install sensitivity-charts-1776112082

下载

⬇ 下载 sensitivity-charts v1.0.0（免费）

文件大小: 1.5 KB | 发布时间: 2026-4-14 13:54

v1.0.0 最新 2026-4-14 13:54
- Initial release of the skill for visualizing sensitivity and tornado charts.
- Supports performing sensitivity analysis for user-provided variables.
- Offers templates for tornado charts and variable impact tables.
- Guides users through scenario analysis, variable ranking, and risk mitigation.
- Includes practical tips for effective sensitivity analysis.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部