跳到主要内容
SkillVault logo SkillVault
Pro ChatGPT GPTs Dify LangGraph

Data Insight Narrator

Turns raw metrics and query results into decision-ready narratives: findings, so-what, confidence and recommended actions.

0 次下载 0 次浏览 更新于 Sep 30, 2026 v1.2.0
Data Insight Narrator skill cover

下方技能配置(提示词、变量、安装步骤)保留英文原文。.aiskill 文件直接面向 AI 智能体,统一使用英文以确保跨平台行为一致。

概述

Data Insight Narrator is the bridge between a spreadsheet of numbers and a room of decision-makers. Feed it query results, dashboards exports or summary metrics and it produces an executive-ready narrative: what changed, why it matters, how confident we are, and what to do next.

It separates observation from interpretation, quantifies impact in business terms, flags anomalies and seasonality instead of over-explaining noise, and explicitly lists what the data does NOT show.

The output format works for weekly business reviews, product analytics digests and investor updates alike.

系统提示词

预览已脱敏

定义智能体角色、规则与输出格式的指令块。

system-prompt.txt 
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████

用户提示词模板

填充变量后发送,即可运行该技能: {{variables}}

user-template.txt 
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████

变量

名称 必填 说明 示例
{{metrics}} 是 Raw numbers, CSV/JSON results or dashboard summary. —
{{dataset_desc}} 是 What the data covers and how it was collected. Postgres events table, signup-to-activation funnel, last 90 days
{{time_window}} 可选 The reporting period and comparison baseline. Sep 1–30 vs Aug, UTC
{{audience}} 可选 Who reads the narrative. exec team at a seed-stage SaaS

完整技能配置

脱敏预览

标准 .aiskill 文件,提供 JSON 与 YAML 两种格式。

data-insight-narrator.aiskill (JSON) 
{
  "format": "aiskill/v1",
  "skill": {
    "name": "Data Insight Narrator",
    "slug": "data-insight-narrator",
    "version": "1.2.0",
    "description": "Turns raw metrics and query results into decision-ready narratives: findings, so-what, confidence and recommended actions.",
    "category": "Data",
    "tags": [
      "analytics",
      "reporting",
      "storytelling",
      "business-intelligence"
    ],
    "platforms": [
      "chatgpt",
      "dify",
      "langgraph"
    ],
    "tested_environment": "GPT-5, Claude Sonnet 4.5; CSV/JSON exports up to ~5k rows summarized",
    "license": "CC-BY-4.0"
  },
  "prompts": {
    "system": "████████████████████████████████████████████████████████████████████████████████████████████████",
    "user_template": "████████████████████████████████████████████████████████████████████████████████████████████████"
  },
  "variables": [
    {
      "name": "metrics",
      "description": "Raw numbers, CSV/JSON results or dashboard summary.",
      "required": true
    },
    {
      "name": "dataset_desc",
      "description": "What the data covers and how it was collected.",
      "required": true,
      "example": "Postgres events table, signup-to-activation funnel, last 90 days"
    },
    {
      "name": "time_window",
      "description": "The reporting period and comparison baseline.",
      "required": false,
      "example": "Sep 1–30 vs Aug, UTC"
    },
    {
      "name": "audience",
      "description": "Who reads the narrative.",
      "required": false,
      "example": "exec team at a seed-stage SaaS"
    }
  ],
  "install": {
    "steps": [
      {
        "title": "Copy the system prompt",
        "detail": "Copy the narrator system prompt from the skill page."
      },
      {
        "title": "Create a reporting agent",
        "detail": "Paste it into a custom GPT or Dify/LangGraph reporting agent."
      },
      {
        "title": "Paste your numbers",
        "detail": "Provide the metrics, dataset context and time window per report."
      },
      {
        "title": "Distribute",
        "detail": "Drop the Headline + Recommended actions into your weekly review doc."
      }
    ]
  },
  "usage": {
    "steps": [
      "Export the metrics you want narrated, including a comparison baseline.",
      "Fill in dataset context so confidence ratings are meaningful.",
      "Review hypothesis labels and verify any HIGH-impact claim before acting.",
      "Track the Watch list metrics in your next reporting cycle."
    ]
  },
  "metadata": {
    "author": "SkillVault",
    "source": "https://skillvault.top/skills/data-insight-narrator",
    "exported_at": "2026-11-03T07:44:33.796Z"
  }
}
data-insight-narrator.aiskill (YAML) 
format: aiskill/v1
skill:
  name: Data Insight Narrator
  slug: data-insight-narrator
  version: 1.2.0
  description: >-
    Turns raw metrics and query results into decision-ready narratives: findings, so-what,
    confidence and recommended actions.
  category: Data
  tags:
    - analytics
    - reporting
    - storytelling
    - business-intelligence
  platforms:
    - chatgpt
    - dify
    - langgraph
  tested_environment: GPT-5, Claude Sonnet 4.5; CSV/JSON exports up to ~5k rows summarized
  license: CC-BY-4.0
prompts:
  system: ████████████████████████████████████████████████████████████████████████████████████████████████
  user_template: ████████████████████████████████████████████████████████████████████████████████████████████████
variables:
  - name: metrics
    description: Raw numbers, CSV/JSON results or dashboard summary.
    required: true
  - name: dataset_desc
    description: What the data covers and how it was collected.
    required: true
    example: Postgres events table, signup-to-activation funnel, last 90 days
  - name: time_window
    description: The reporting period and comparison baseline.
    required: false
    example: Sep 1–30 vs Aug, UTC
  - name: audience
    description: Who reads the narrative.
    required: false
    example: exec team at a seed-stage SaaS
install:
  steps:
    - title: Copy the system prompt
      detail: Copy the narrator system prompt from the skill page.
    - title: Create a reporting agent
      detail: Paste it into a custom GPT or Dify/LangGraph reporting agent.
    - title: Paste your numbers
      detail: Provide the metrics, dataset context and time window per report.
    - title: Distribute
      detail: Drop the Headline + Recommended actions into your weekly review doc.
usage:
  steps:
    - Export the metrics you want narrated, including a comparison baseline.
    - Fill in dataset context so confidence ratings are meaningful.
    - Review hypothesis labels and verify any HIGH-impact claim before acting.
    - Track the Watch list metrics in your next reporting cycle.
metadata:
  author: SkillVault
  source: https://skillvault.top/skills/data-insight-narrator
  exported_at: "2026-11-03T07:44:33.796Z"

安装指南

  1. 1

    Copy the system prompt

    Copy the narrator system prompt from the skill page.

  2. 2

    Create a reporting agent

    Paste it into a custom GPT or Dify/LangGraph reporting agent.

  3. 3

    Paste your numbers

    Provide the metrics, dataset context and time window per report.

  4. 4

    Distribute

    Drop the Headline + Recommended actions into your weekly review doc.

使用方法

  1. Export the metrics you want narrated, including a comparison baseline.
  2. Fill in dataset context so confidence ratings are meaningful.
  3. Review hypothesis labels and verify any HIGH-impact claim before acting.
  4. Track the Watch list metrics in your next reporting cycle.

平台兼容性

ChatGPT GPTs

OpenAI

将系统提示词粘贴到 GPT 的「Instructions」字段,并把用户模板作为起始消息使用。

官方文档

Dify

LangGenius

新建一个智能体/应用,将系统提示词粘贴到系统提示词面板,并把模板变量注册为输入字段。

官方文档

LangGraph

LangChain

将 JSON 配置加载进图状态:prompts.system 用作系统消息,prompts.user_template 作为可运行模板。

官方文档

预览图集

Data Insight Narrator previewData Insight Narrator preview

相关技能

SQL Query Builder AI agent skill cover
免费
ChatGPT GPTs Claude Code Cursor Dify LangGraph

SQL Query Builder

Translates plain-English questions into safe, indexed, dialect-aware SQL — with schema reasoning and EXPLAIN prompts.

#sql#database#analytics
0 0 v1.6.0
Landing Page Architect AI agent skill cover
年度扩展包
ChatGPT GPTs Cursor Dify LangGraph

Landing Page Architect

Designs high-converting landing pages end-to-end: section wireframe, full copy draft, CTA strategy and A/B test plan. Yearly Pro exclusive.

#landing-page#conversion#copywriting
0 1 v1.1.0
Deep Research Agent AI agent skill cover
Pro
ChatGPT GPTs Claude Code Dify LangGraph

Deep Research Agent

A disciplined research protocol: question decomposition, source strategy, evidence table and a confidence-rated synthesis.

#research#agent#synthesis
0 0 v2.2.0