Back to Details

consulting-analysis

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Professional Research Report Skill

专业研究报告Skill

Overview

概述

This skill produces professional, consulting-grade research reports in Markdown format, covering domains such as market analysis, consumer insights, brand strategy, financial analysis, industry research, competitive intelligence, investment research, and macroeconomic analysis. It operates across two distinct phases:
  1. Phase 1 — Analysis Framework Generation: Given a research subject, produce a rigorous analysis framework including chapter skeleton, per-chapter data requirements, analysis logic, and visualization plan.
  2. Phase 2 — Report Generation: After data has been collected by other skills, synthesize all inputs into a final polished report.
The output adheres to McKinsey/BCG consulting voice standards. The report language follows the 
output_locale
setting (default: 
zh_CN
for Chinese).
本Skill可生成专业的咨询级研究报告，格式为Markdown，覆盖领域包括市场分析、消费者洞察、品牌战略、财务分析、行业研究、竞争情报、投资研究及宏观经济分析。它分为两个不同阶段运作：
  1. 第一阶段——分析框架生成：给定研究主题，生成严谨的分析框架，包括章节架构、各章节数据需求、分析逻辑及可视化规划。
  2. 第二阶段——报告生成：在其他Skill完成数据收集后，将所有输入整合为最终的打磨版报告。
输出内容符合麦肯锡/波士顿咨询（McKinsey/BCG）的咨询风格标准。报告语言遵循
output_locale
设置（默认：
zh_CN
中文）。

Core Capabilities

核心能力

  • Design analysis frameworks from scratch given only a research subject and scope
  • Transform raw data into structured, high-depth research reports
  • Follow the "Visual Anchor → Data Contrast → Integrated Analysis" flow per sub-chapter
  • Produce insights following the "Data → User Psychology → Strategy Implication" chain
  • Embed pre-generated charts and construct comparison tables
  • Generate inline citations formatted per GB/T 7714-2015 standards
  • Output reports in the language specified by 
    output_locale
    with professional consulting tone
  • Adapt analytical depth and structure to domain (marketing, finance, industry, etc.)
  • 仅根据研究主题和范围，从零开始设计分析框架
  • 将原始数据转化为结构化、有深度的研究报告
  • 每个子章节遵循**「视觉锚点→数据对比→综合分析」**流程
  • 按照**「数据→用户心理→战略启示」**链条生成见解
  • 嵌入预先生成的图表并构建对比表格
  • 生成符合GB/T 7714-2015标准的内嵌引用
  • 按
    output_locale
    指定的语言输出专业咨询风格报告
  • 根据领域（营销、财务、行业等）调整分析深度和结构

When to Use This Skill

适用场景

Always load this skill when:
  • User asks for a market analysis, consumer insight report, financial analysis, industry research, or any consulting-grade analytical report
  • User provides a research subject and needs a structured analysis framework before data collection
  • User provides data summaries, analysis frameworks, or chart files to be synthesized into a report
  • User needs a professional consulting-style research report
  • The task involves transforming research findings into structured strategic narratives
以下场景请务必加载此Skill：
  • 用户需要市场分析、消费者洞察报告、财务分析、行业研究或任何咨询级分析报告
  • 用户提供研究主题，需要在数据收集前先构建结构化分析框架
  • 用户提供数据摘要、分析框架或图表文件，需要整合成报告
  • 用户需要专业咨询风格的研究报告
  • 任务涉及将研究成果转化为结构化的战略叙述

Phase 1: Analysis Framework Generation

第一阶段：分析框架生成

Purpose

目标

Given a research subject (e.g., "Gen-Z Skincare Market Analysis", "NEV Industry Competitive Landscape", "Brand X Consumer Profiling"), produce a complete analysis framework that serves as the blueprint for downstream data collection and final report generation.
给定研究主题（例如：「Z世代护肤品市场分析」「新能源汽车行业竞争格局」「X品牌消费者画像」），生成完整的分析框架，作为后续数据收集和最终报告生成的蓝图。

Phase 1 Inputs

第一阶段输入

InputDescriptionRequired
Research SubjectThe topic or question to be analyzedYes
Scope / ConstraintsGeographic scope, time range, industry segment, target audience, etc.Optional
Specific AnglesAny particular angles or hypotheses the user wants exploredOptional
DomainThe analytical domain: market, finance, industry, brand, consumer, investment, etc.Inferred
输入项描述是否必填
研究主题待分析的主题或问题是
范围/约束条件地理范围、时间范围、行业细分、目标受众等否
特定分析角度用户希望探索的特定角度或假设否
领域分析领域：市场、财务、行业、品牌、消费者、投资等自动推断

Phase 1 Workflow

第一阶段工作流程

Step 1.1: Understand the Research Subject

步骤1.1：理解研究主题

  • Parse the research subject to identify the core entity (market, brand, product, industry, consumer segment, financial instrument, etc.)
  • Identify the analytical domain (marketing, finance, industry, competitive, consumer, investment, macro, etc.)
  • Determine the natural analytical dimensions based on domain:
DomainTypical Dimensions
Market AnalysisMarket size, growth trends, market segmentation, growth drivers, competitive landscape, consumer profiling
Brand AnalysisBrand positioning, market share, consumer perception, marketing strategy, competitor comparison
Consumer InsightsDemographic profiling, purchase behavior, decision journey, pain points, scenario analysis
Financial AnalysisMacro environment, industry trends, company fundamentals, financial metrics, valuation, risk assessment
Industry ResearchValue chain analysis, market size, competitive landscape, policy environment, technology trends, entry barriers
Investment Due DiligenceBusiness model, financial health, management assessment, market opportunity, risk factors, exit pathways
Competitive IntelligenceCompetitor identification, strategic comparison, SWOT analysis, differentiated positioning, market dynamics
  • 解析研究主题，识别核心实体（市场、品牌、产品、行业、消费者细分、金融工具等）
  • 确定分析领域（营销、财务、行业、竞争、消费者、投资、宏观等）
  • 根据领域确定自然分析维度：
领域典型分析维度
市场分析市场规模、增长趋势、市场细分、增长驱动因素、竞争格局、消费者画像
品牌分析品牌定位、市场份额、消费者认知、营销策略、竞品对比
消费者洞察人口统计画像、购买行为、决策路径、痛点、场景分析
财务分析宏观环境、行业趋势、公司基本面、财务指标、估值、风险评估
行业研究价值链分析、市场规模、竞争格局、政策环境、技术趋势、进入壁垒
投资尽职调查商业模式、财务健康状况、管理层评估、市场机会、风险因素、退出路径
竞争情报竞品识别、战略对比、SWOT分析、差异化定位、市场动态

Step 1.2: Select Analysis Frameworks & Models

步骤1.2：选择分析框架与模型

Based on the identified domain and research subject, select one or more professional analysis frameworks to structure the reasoning in each chapter. The chosen frameworks guide the Analysis Logic in the chapter skeleton (Step 1.3).
根据确定的领域和研究主题，选择一个或多个专业分析框架，用于构建各章节的推理逻辑。所选框架将指导步骤1.3中章节架构的分析逻辑部分。

Strategic & Environmental Analysis

战略与环境分析

FrameworkDescriptionBest For
SWOT AnalysisStrengths, Weaknesses, Opportunities, ThreatsBrand assessment, competitive positioning, strategic planning
PEST / PESTEL AnalysisPolitical, Economic, Social, Technological (+ Environmental, Legal)Macro-environment scanning, market entry assessment, policy impact analysis
Porter's Five ForcesSupplier bargaining power, buyer bargaining power, threat of new entrants, threat of substitutes, industry rivalryIndustry competitive landscape, entry barrier assessment, profit margin analysis
Porter's Diamond ModelFactor conditions, demand conditions, related industries, firm strategy & structureNational/regional competitive advantage analysis
VRIO AnalysisValue, Rarity, Imitability, OrganizationCore competency assessment, resource advantage analysis
框架描述适用场景
SWOT分析优势、劣势、机会、威胁品牌评估、竞争定位、战略规划
PEST/PESTEL分析政治、经济、社会、技术（+环境、法律）宏观环境扫描、市场进入评估、政策影响分析
波特五力模型供应商议价能力、买方议价能力、新进入者威胁、替代品威胁、行业竞争程度行业竞争格局、进入壁垒评估、利润率分析
波特钻石模型生产要素、需求条件、相关产业、企业战略与结构国家/区域竞争优势分析
VRIO分析价值、稀缺性、可模仿性、组织能力核心竞争力评估、资源优势分析

Market & Growth Analysis

市场与增长分析

FrameworkDescriptionBest For
STP AnalysisSegmentation, Targeting, PositioningMarket segmentation, target market selection, brand positioning
BCG Matrix (Growth-Share Matrix)Stars, Cash Cows, Question Marks, DogsProduct portfolio management, resource allocation decisions
Ansoff MatrixMarket penetration, market development, product development, diversificationGrowth strategy selection
Product Life Cycle (PLC)Introduction, growth, maturity, declineProduct strategy formulation, market timing decisions
TAM-SAM-SOMTotal / Serviceable / Obtainable MarketMarket sizing, opportunity quantification
Technology Adoption LifecycleInnovators → Early Adopters → Early Majority → Late Majority → LaggardsEmerging technology/category penetration analysis
框架描述适用场景
STP分析市场细分、目标市场选择、定位市场细分、目标市场选择、品牌定位
BCG矩阵（增长-份额矩阵）明星、现金牛、问题业务、瘦狗业务产品组合管理、资源分配决策
安索夫矩阵市场渗透、市场开发、产品开发、多元化增长战略选择
产品生命周期（PLC）导入期、成长期、成熟期、衰退期产品战略制定、市场时机决策
TAM-SAM-SOM整体市场/可服务市场/可获得市场市场规模测算、机会量化
技术采用生命周期创新者→早期采用者→早期大众→晚期大众→落后者新兴技术/品类渗透分析

Consumer & Behavioral Analysis

消费者与行为分析

FrameworkDescriptionBest For
Consumer Decision JourneyAwareness → Consideration → Evaluation → Purchase → LoyaltyConsumer behavior path mapping, touchpoint optimization
AARRR Funnel (Pirate Metrics)Acquisition, Activation, Retention, Revenue, ReferralUser growth analysis, conversion rate optimization
RFM ModelRecency, Frequency, MonetaryCustomer value segmentation, precision marketing
Maslow's Hierarchy of NeedsPhysiological → Safety → Social → Esteem → Self-actualizationConsumer psychology analysis, product value proposition
Jobs-to-be-Done (JTBD)The "job" a user needs to accomplish in a specific contextDemand insight, product innovation direction
框架描述适用场景
消费者决策路径认知→考虑→评估→购买→忠诚度消费者行为路径映射、触点优化
AARRR漏斗（海盗指标）获取、激活、留存、收入、推荐用户增长分析、转化率优化
RFM模型最近一次消费、消费频率、消费金额客户价值细分、精准营销
马斯洛需求层次理论生理→安全→社交→尊重→自我实现消费者心理分析、产品价值主张
Jobs-to-be-Done（JTBD）用户在特定场景下需要完成的「任务」需求洞察、产品创新方向

Financial & Valuation Analysis

财务与估值分析

FrameworkDescriptionBest For
DuPont AnalysisROE = Net Profit Margin × Asset Turnover × Equity MultiplierProfitability decomposition, financial health diagnosis
DCF (Discounted Cash Flow)Free cash flow discountingEnterprise/project valuation
Comparable Company AnalysisPE, PB, PS, EV/EBITDA multiples comparisonRelative valuation, peer benchmarking
EVA (Economic Value Added)After-tax operating profit - Cost of capitalValue creation capability assessment
框架描述适用场景
杜邦分析净资产收益率=销售净利率×资产周转率×权益乘数盈利能力分解、财务健康诊断
DCF（折现现金流）自由现金流折现企业/项目估值
可比公司分析PE、PB、PS、EV/EBITDA倍数对比相对估值、同行基准对比
EVA（经济增加值）税后经营利润-资本成本价值创造能力评估

Competitive & Strategic Positioning

竞争与战略定位

FrameworkDescriptionBest For
BenchmarkingKey performance indicator item-by-item comparisonCompetitor gap analysis, best practice identification
Strategic Group MappingCluster competitors along two key dimensionsCompetitive landscape visualization, white-space identification
Value Chain AnalysisPrimary activities + support activities value decompositionCost advantage sources, differentiation opportunity identification
Blue Ocean StrategyValue curve, four-action framework (Eliminate-Reduce-Raise-Create)Differentiated innovation, new market space creation
Perceptual MappingPlot brand positions along two consumer-perceived dimensionsBrand positioning analysis, market gap discovery
框架描述适用场景
标杆分析关键绩效指标逐项对比竞品差距分析、最佳实践识别
战略群组映射沿两个关键维度对竞品聚类竞争格局可视化、空白市场识别
价值链分析基本活动+支持活动价值分解成本优势来源、差异化机会识别
蓝海战略价值曲线、四步动作框架（消除-减少-提升-创造）差异化创新、新市场空间创造
感知映射沿两个消费者感知维度绘制品牌位置品牌定位分析、市场空白发现

Industry & Supply Chain Analysis

行业与供应链分析

FrameworkDescriptionBest For
Industry Value ChainUpstream → Midstream → Downstream decompositionIndustry structure understanding, profit distribution analysis
Gartner Hype CycleTechnology Trigger → Peak of Inflated Expectations → Trough of Disillusionment → Slope of Enlightenment → Plateau of ProductivityEmerging technology maturity assessment
GE-McKinsey MatrixIndustry Attractiveness × Competitive StrengthBusiness portfolio prioritization, investment decisions
框架描述适用场景
行业价值链上游→中游→下游分解行业结构理解、利润分布分析
Gartner技术成熟度曲线技术触发→期望膨胀顶峰→泡沫破裂低谷→启蒙斜坡→生产力 plateau新兴技术成熟度评估
GE-麦肯锡矩阵行业吸引力×竞争实力业务组合优先级、投资决策

Selection Principles

选择原则

  1. Domain-First: Based on the domain identified in Step 1.1, select 2-4 most relevant frameworks from the toolkit above
  2. Complementary: Choose complementary rather than overlapping frameworks (e.g., macro-level with PESTEL + micro-level with Porter's Five Forces)
  3. Depth over Breadth: Better to deeply apply 2 frameworks than superficially stack 6
  4. Data-Feasible: Selected frameworks must be supportable by downstream data collection skills — if the data required by a framework cannot be reasonably obtained, downgrade or substitute
  5. Explicit Mapping: In the chapter skeleton, explicitly annotate which framework each chapter uses and how it is applied
  1. 领域优先：根据步骤1.1确定的领域，从上述工具包中选择2-4个最相关的框架
  2. 互补性：选择互补而非重叠的框架（例如，宏观层面用PESTEL+微观层面用波特五力）
  3. 深度优先：深入应用2个框架优于表面堆叠6个框架
  4. 数据可行性：所选框架必须能被下游数据收集Skill支持——如果框架所需数据无法合理获取，则降级或替换
  5. 明确映射：在章节架构中，明确标注每个章节使用的框架及应用方式

Framework Selection Output Format

框架选择输出格式

markdown
undefined
markdown
undefined

Framework Selection

框架选择

ChapterSelected Framework(s)Application
Market Size & Growth TrendsTAM-SAM-SOM + Product Life CycleTAM-SAM-SOM to quantify market space, PLC to determine market stage
Competitive Landscape AssessmentPorter's Five Forces + Strategic Group MappingFive Forces to assess industry competition intensity, Group Mapping to visualize competitive positioning
Consumer ProfilingRFM + Consumer Decision JourneyRFM to segment customer value, Decision Journey to identify key conversion nodes
Brand Strategy RecommendationsSWOT + Blue Ocean StrategySWOT to summarize overall landscape, Blue Ocean to guide differentiation direction
undefined
章节所选框架应用方式
市场规模与增长趋势TAM-SAM-SOM + 产品生命周期用TAM-SAM-SOM量化市场空间，用PLC判断市场阶段
竞争格局评估波特五力 + 战略群组映射用五力模型评估行业竞争强度，用群组映射可视化竞争定位
消费者画像RFM + 消费者决策路径用RFM细分客户价值，用决策路径识别关键转化节点
品牌战略建议SWOT + 蓝海战略用SWOT总结整体格局，用蓝海战略指导差异化方向
undefined

Step 1.3: Design Chapter Skeleton

步骤1.3：设计章节架构

Produce a hierarchical chapter structure. Each chapter must include:
  1. Chapter Title — Professional, concise, subject-based (follow titling constraints in Formatting section)
  2. Analysis Objective — What this chapter aims to reveal
  3. Analysis Logic — The reasoning chain or framework (must reference the frameworks selected in Step 1.2)
  4. Core Hypothesis — Preliminary hypotheses to be validated or refuted by data
生成层级化的章节结构。每个章节必须包含：
  1. 章节标题——专业、简洁、贴合主题（遵循格式部分的标题约束）
  2. 分析目标——本章节旨在揭示的内容
  3. 分析逻辑——推理链条或框架（必须引用步骤1.2中选择的框架）
  4. 核心假设——需通过数据验证或推翻的初步假设

Chapter Skeleton Output Format

章节架构输出格式

markdown
undefined
markdown
undefined

Analysis Framework

分析框架

Chapter 1: [Title]

第1章：[标题]

  • Analysis Objective: [This chapter aims to...]
  • Analysis Logic: [Framework or reasoning chain used]
  • Core Hypothesis: [Hypotheses to validate]
  • Data Requirements: (see Step 1.4)
  • Visualization Plan: (see Step 1.5)
  • 分析目标：[本章节旨在...]
  • 分析逻辑：[使用的框架或推理链条]
  • 核心假设：[待验证的假设]
  • 数据需求：（见步骤1.4）
  • 可视化规划：（见步骤1.5）

Chapter 2: [Title]

第2章：[标题]

...
undefined
...
undefined

Step 1.4: Define Data Query Requirements Per Chapter

步骤1.4：定义各章节数据查询需求

For each chapter, specify exactly what data needs to be collected. This is the bridge to downstream data collection skills.
Each data requirement entry must include:
FieldDescription
Data MetricThe specific metric or data point needed (e.g., "China skincare market size 2020-2025 (in billion CNY)")
Data TypeQuantitative, Qualitative, or Mixed
Suggested SourcesSuggested source categories: Industry reports, financial statements, government statistics, social media, e-commerce platforms, survey data, news
Search KeywordsSuggested search queries for data collection agents
PriorityP0 (Required) / P1 (Important) / P2 (Supplementary)
Time RangeThe time period the data should cover
为每个章节明确指定需要收集的具体数据。这是连接下游数据收集Skill的桥梁。
每个数据需求条目必须包含：
字段描述
数据指标所需的具体指标或数据点（例如：「2020-2025年中国护肤品市场规模（单位：十亿元）」）
数据类型定量、定性或混合类型
建议数据源建议的数据源类别：行业报告、财务报表、政府统计数据、社交媒体、电商平台、调研数据、新闻
搜索关键词为数据收集Agent提供的建议搜索词
优先级P0（必填）/ P1（重要）/ P2（补充）
时间范围数据应覆盖的时间段

Data Requirements Output Format (per chapter)

数据需求输出格式（按章节）

markdown
undefined
markdown
undefined

Data Requirements

数据需求

#Data MetricData TypeSuggested SourcesSearch KeywordsPriorityTime Range
1Market size (billion CNY)QuantitativeIndustry reports, government statistics"China skincare market size 2024"P02020-2025
2CAGRQuantitativeIndustry reports"skincare CAGR growth rate"P02020-2025
3Sub-category shareQuantitativeE-commerce platforms, industry reports"skincare category share cream serum sunscreen"P1Latest
4Policy & regulatory updatesQualitativeGovernment announcements, news"cosmetics regulation 2024"P2Past 1 year
undefined
#数据指标数据类型建议数据源搜索关键词优先级时间范围
1市场规模（十亿元）定量行业报告、政府统计数据"2024年中国护肤品市场规模"P02020-2025
2复合年增长率（CAGR）定量行业报告"护肤品CAGR增长率"P02020-2025
3细分品类占比定量电商平台、行业报告"护肤品品类占比 面霜 精华 防晒霜"P1最新
4政策与监管更新定性政府公告、新闻"2024年化妆品监管政策"P2过去1年
undefined

Step 1.5: Define Visualization & Content Structure Per Chapter

步骤1.5：定义各章节可视化与内容结构

For each chapter, specify the planned visualization and content structure for the final report:
FieldDescription
Visualization TypeChart type: Line chart, bar chart, pie chart, scatter plot, radar chart, heatmap, Sankey diagram, comparison table, etc.
Visualization TitleDescriptive title for the chart
Visualization Data MappingWhich data indicators map to X/Y axes or segments
Comparison Table DesignColumn headers and comparison dimensions for the data contrast table
Argument StructureThe planned "What → Why → So What" narrative outline
为每个章节指定规划的可视化内容和最终报告的内容结构：
字段描述
可视化类型图表类型：折线图、柱状图、饼图、散点图、雷达图、热力图、桑基图、对比表格等
可视化标题图表的描述性标题
可视化数据映射哪些数据指标映射到X/Y轴或分段
对比表格设计数据对比表格的列标题和对比维度
论证结构规划的「是什么→为什么→意味着什么」叙述大纲

Visualization Plan Output Format (per chapter)

可视化规划输出格式（按章节）

markdown
undefined
markdown
undefined

Visualization & Content Plan

可视化与内容规划

Chart 1: [Type] — [Title]
  • X-axis: [Dimension], Y-axis: [Metric]
  • Data source: Corresponds to Data Requirement #1, #2
Comparison Table:
DimensionItem AItem BItem C
Argument Structure:
  1. Observation (What): [Surface phenomenon revealed by data]
  2. Attribution (Why): [Driving factors or underlying causes]
  3. Implication (So What): [Strategic implications or recommended actions]
undefined
图表1：[类型] — [标题]
  • X轴：[维度]，Y轴：[指标]
  • 数据源：对应数据需求#1、#2
对比表格:
维度A项B项C项
论证结构:
  1. 观察（是什么）：[数据揭示的表面现象]
  2. 归因（为什么）：[驱动因素或深层原因]
  3. 启示（意味着什么）：[战略启示或建议行动]
undefined

Step 1.6: Output Complete Analysis Framework

步骤1.6：输出完整分析框架

Assemble all outputs into a single, structured Analysis Framework Document:
markdown
undefined
将所有输出内容整合为单个结构化的分析框架文档：
markdown
undefined

[Research Subject] Analysis Framework

[研究主题]分析框架

Research Overview

研究概述

  • Research Subject: [...]
  • Scope: [Geography, time range, industry segment]
  • Analysis Domain: [Market / Finance / Industry / Brand / Consumer / ...]
  • Core Research Questions: [1-3 key questions]
  • 研究主题：[...]
  • 范围：[地理范围、时间范围、行业细分]
  • 分析领域：[市场/财务/行业/品牌/消费者/...]
  • 核心研究问题：[1-3个关键问题]

Framework Selection

框架选择

ChapterSelected Framework(s)Application
.........
章节所选框架应用方式
.........

Chapter Skeleton

章节架构

1. [Chapter Title]

1. [章节标题]

  • Analysis Objective: [...]
  • Analysis Logic: [...]
  • Core Hypothesis: [...]
  • 分析目标：[...]
  • 分析逻辑：[...]
  • 核心假设：[...]

Data Requirements

数据需求

#Data MetricData TypeSuggested SourcesSearch KeywordsPriorityTime Range
.....................
#数据指标数据类型建议数据源搜索关键词优先级时间范围
.....................

Visualization & Content Plan

可视化与内容规划

[Chart plan + Comparison table design + Argument structure]
[图表规划 + 对比表格设计 + 论证结构]

2. [Chapter Title]

2. [章节标题]

...
...

N. [Chapter Title]

N. [章节标题]

...
...

Data Collection Task List

数据收集任务清单

[Consolidate all P0/P1 data requirements across chapters into a structured task list for downstream data collection skills to execute]
undefined
[将所有章节的P0/P1数据需求整合为结构化任务清单，供下游数据收集Skill执行]
undefined

Phase 1 Quality Checklist

第一阶段质量检查清单

  • Analysis framework covers all natural dimensions for the identified domain
  • 2-4 professional analysis frameworks are selected and explicitly mapped to chapters
  • Selected frameworks are complementary (not overlapping) and data-feasible
  • Each chapter has clear Analysis Objective, Analysis Logic (referencing chosen framework), and Core Hypothesis
  • Data requirements are specific, measurable, and include search keywords
  • Every chapter has at least one visualization plan
  • Data priorities (P0/P1/P2) are assigned realistically
  • The framework is actionable — a data collection agent can execute on the Search Keywords directly
  • Data Collection Task List is comprehensive and deduplicated
  • 分析框架覆盖了所识别领域的所有自然分析维度
  • 选择了2-4个专业分析框架，并明确映射到各章节
  • 所选框架具有互补性（非重叠）且数据可获取
  • 每个章节都有清晰的分析目标、分析逻辑（引用所选框架）和核心假设
  • 数据需求具体、可衡量，并包含搜索关键词
  • 每个章节至少有一个可视化规划
  • 数据优先级（P0/P1/P2）分配合理
  • 框架具备可执行性——数据收集Agent可直接使用搜索关键词执行任务
  • 数据收集任务清单全面且去重

Phase 1→2 Handoff: Data Collection & Chart Generation

第一→第二阶段交接：数据收集与图表生成

After the analysis framework is generated, it is handed off to other data collection skills (e.g., deep-research, data-analysis, web search agents) to:
  1. Execute the Search Keywords from each chapter's data requirements
  2. Collect quantitative data, qualitative insights, and source URLs
  3. Generate charts based on the Visualization & Content Plan
  4. Return a Data Package containing:
    • Data Summary: Raw numbers, metrics, and qualitative findings per chapter
    • Chart Files: Generated chart images with local file paths
    • External Search Findings: Source URLs and summaries for citations
This skill does NOT perform data collection. It only produces the framework (Phase 1) and the final report (Phase 2).
Chart Generation: If a visualization/charting skill is available (e.g., data-analysis, image-generation), chart generation can be deferred to the beginning of Phase 2 — see Step 2.3.
分析框架生成后，将其交付给其他数据收集Skill（例如深度调研、数据分析、网页搜索Agent）以完成以下工作：
  1. 执行每个章节数据需求中的搜索关键词
  2. 收集定量数据、定性见解和来源URL
  3. 根据可视化与内容规划生成图表
  4. 返回包含以下内容的数据包：
    • 数据摘要：按章节整理的原始数据、指标和定性发现
    • 图表文件：生成的图表图片及本地文件路径
    • 外部搜索结果：用于引用的来源URL和摘要
本Skill不执行数据收集。它仅负责生成框架（第一阶段）和最终报告（第二阶段）。
图表生成：如果有可视化/图表生成Skill可用（例如数据分析），图表生成可推迟到第二阶段开始时执行——见步骤2.3。

Phase 2: Report Generation

第二阶段：报告生成

Purpose

目标

Receive the completed Analysis Framework and Data Package from upstream, and synthesize them into a final consulting-grade report.
接收上游传来的分析框架和数据包，将其整合为最终的咨询级报告。

Phase 2 Inputs

第二阶段输入

InputDescriptionRequired
Analysis FrameworkThe framework document produced in Phase 1Yes
Data SummaryCollected data organized per chapter from the data collection phaseYes
Chart FilesLocal file paths for generated chart images. If not provided, will be generated in Step 2.3 using available visualization skillsOptional
External Search FindingsURLs and summaries for inline citationsOptional
输入项描述是否必填
分析框架第一阶段生成的框架文档是
数据摘要数据收集阶段按章节整理的收集数据是
图表文件生成的图表图片的本地文件路径。如果未提供，将在步骤2.3中使用可用的可视化Skill生成否
外部搜索结果用于内嵌引用的URL和摘要否

Phase 2 Workflow

第二阶段工作流程

Step 2.1: Receive and Validate Inputs

步骤2.1：接收并验证输入

Verify that all required inputs are present:
  1. Analysis Framework — Confirm it contains chapter skeleton, data requirements, and visualization plans
  2. Data Summary — Confirm it contains data organized per chapter, cross-reference against P0 requirements
  3. Chart Files — Confirm file paths are valid local paths
If any P0 data is missing, note it in the report and flag for the user.
验证所有必填输入是否存在：
  1. 分析框架——确认包含章节架构、数据需求和可视化规划
  2. 数据摘要——确认包含按章节整理的数据，并与P0需求交叉核对
  3. 图表文件——确认文件路径为有效本地路径
如果任何P0数据缺失，在报告中注明并向用户标记。

Step 2.2: Map Report Structure

步骤2.2：映射报告结构

Map the final report structure from the Analysis Framework:
  1. Abstract — Executive summary with key takeaways
  2. Introduction — Background, objectives, methodology
  3. Main Body Chapters (2...N) — Mapped from the Framework's chapter skeleton
  4. Conclusion — Pure, objective synthesis
  5. References — GB/T 7714-2015 formatted references
根据分析框架映射最终报告结构：
  1. 摘要——包含关键结论的执行摘要
  2. 引言——背景、目标、研究方法
  3. 主体章节（2...N）——从框架的章节架构映射而来
  4. 结论——纯粹、客观的综合总结
  5. 参考文献——符合GB/T 7714-2015标准的参考文献

Step 2.3: Generate Chapter Charts (Pre-Report Visualization)

步骤2.3：生成章节图表（报告前可视化）

Before writing the report, generate all planned charts from the Analysis Framework's Visualization & Content Plan. This step ensures every sub-chapter has its "Visual Anchor" ready before narrative writing begins.
在撰写报告前，根据分析框架的可视化与内容规划生成所有规划的图表。此步骤确保在开始叙述撰写前，每个子章节都有对应的「视觉锚点」。

When to Execute This Step

执行时机

  • Chart Files already provided: Skip this step — proceed directly to Step 2.4.
  • Chart Files NOT provided but a visualization skill is available: Execute this step to generate all charts first.
  • No Chart Files and no visualization skill available: Skip this step — use comparison tables as the primary visual anchor in Step 2.4, and note the absence of charts.
  • 已提供图表文件：跳过此步骤——直接进入步骤2.4。
  • 未提供图表文件但有可视化Skill可用：先执行此步骤生成所有图表。
  • 无图表文件且无可视化Skill可用：跳过此步骤——在步骤2.4中使用对比表格作为主要视觉锚点，并注明缺少图表。

Chart Generation Workflow

图表生成工作流程

  1. Extract Chart Tasks: Parse all 
    Visualization & Content Plan
    entries from the Analysis Framework to build a chart generation task list:
#ChapterChart TypeChart TitleData MappingData Source
12.1Line chartMarket Size Trend 2020-2025X: Year, Y: Market Size (billion CNY)Data Requirement #1, #2
23.1Pie chartConsumer Age DistributionSegments: Age groups, Values: Share %Data Requirement #5
..................
  1. Prepare Chart Data: For each chart task, extract the corresponding data points from the Data Summary and structure them into the format required by the visualization skill (e.g., CSV, JSON, or tabular format).
  2. Delegate to Visualization Skill: Invoke the available visualization/charting skill (e.g., 
    data-analysis
    ) for each chart task with:
    • Chart type and title
    • Structured data
    • Axis labels and formatting preferences
    • Output file path convention: 
      charts/chapter_{N}_{chart_index}.png
  3. Collect Chart File Paths: Record all generated chart file paths for embedding in Step 2.4:
markdown
undefined
  1. 提取图表任务：从分析框架中解析所有
    可视化与内容规划
    条目，构建图表生成任务清单：
#章节图表类型图表标题数据映射数据源
12.1折线图2020-2025年市场规模趋势X：年份，Y：市场规模（十亿元）数据需求#1、#2
23.1饼图消费者年龄分布分段：年龄组，数值：占比%数据需求#5
..................
  1. 准备图表数据：针对每个图表任务，从数据摘要中提取对应数据点，并整理为可视化Skill所需的格式（例如CSV、JSON或表格格式）。
  2. 委托给可视化Skill：为每个图表任务调用可用的可视化/图表生成Skill（例如
    data-analysis
    ），提供以下信息：
    • 图表类型和标题
    • 结构化数据
    • 轴标签和格式偏好
    • 输出文件路径约定：
      charts/chapter_{N}_{chart_index}.png
  3. 收集图表文件路径：记录所有生成的图表文件路径，以便在步骤2.4中嵌入：
markdown
undefined

Generated Charts

生成的图表

#ChapterChart TitleFile Path
12.1Market Size Trend 2020-2025charts/chapter_2_1.png
23.1Consumer Age Distributioncharts/chapter_3_1.png

5. **Validate**: Confirm all P0-priority charts have been generated. If any chart generation fails, note it and fall back to comparison tables for that sub-chapter.

> **Principle**: Complete ALL chart generation before starting report writing. This ensures a consistent visual narrative and avoids interleaving generation with writing.
#章节图表标题文件路径
12.12020-2025年市场规模趋势charts/chapter_2_1.png
23.1消费者年龄分布charts/chapter_3_1.png

5. **验证**：确认所有P0优先级的图表已生成。如果任何图表生成失败，注明此事，并在该子章节中改用对比表格作为替代。

> **原则**：在开始撰写报告前完成所有图表生成。这确保视觉叙述的一致性，避免在生成和撰写之间来回切换。

Step 2.4: Write the Report

步骤2.4：撰写报告

For each sub-chapter, follow the "Visual Anchor → Data Contrast → Integrated Analysis" flow:
  1. Visual Evidence Block: Embed charts using 
    ![Image Description](Actual_File_Path)
    — use the file paths collected in Step 2.3
  2. Data Contrast Table: Create a Markdown comparison table for key metrics
  3. Integrated Narrative Analysis: Write analytical text following "What → Why → So What"
Each sub-chapter must end with a robust analytical paragraph (min. 200 words) that:
  • Synthesizes conflicting or reinforcing data points
  • Reveals the underlying user tension or opportunity
  • Optionally ends with a punchy "One-Liner Truth" in a blockquote (
    >
    )
每个子章节遵循**「视觉锚点→数据对比→综合分析」**流程：
  1. 视觉证据块：使用
    ![图片描述](实际文件路径)
    嵌入图表——使用步骤2.3中收集的文件路径
  2. 数据对比表格：为关键指标创建Markdown对比表格
  3. 综合叙述分析：按照「是什么→为什么→意味着什么」撰写分析文本
每个子章节必须以一段有深度的分析段落（至少200字）结尾，内容需：
  • 综合冲突或相互印证的数据点
  • 揭示潜在的用户矛盾或机会
  • 可选：在结尾用块引用（
    >
    ）添加一句有力的「核心真相」

Step 2.5: Final Structure Self-Check

步骤2.5：最终结构自检

Before outputting, confirm the report contains all sections in order:
Abstract → 1. Introduction → 2...N. Body Chapters → N+1. Conclusion → N+2. References
Additionally verify:
  • All charts generated in Step 2.3 are embedded in the correct sub-chapters
  • Chart file paths in 
    ![](path)
    references are valid
  • Sub-chapters without charts have comparison tables as visual anchors
The report MUST NOT stop after the Conclusion — it MUST include References as the final section.
输出前，确认报告按顺序包含所有章节：
摘要 → 1.引言 → 2...N.主体章节 → N+1.结论 → N+2.参考文献
此外需验证：
  • 步骤2.3中生成的所有图表都嵌入到了正确的子章节中
  • ![](路径)
    引用中的图表文件路径有效
  • 无图表的子章节已用对比表格作为视觉锚点
报告不得在结论后终止——必须包含参考文献作为最后一个章节。

Formatting & Tone Standards

格式与风格标准

Consulting Voice

咨询风格

  • Tone: McKinsey/BCG — Authoritative, Objective, Professional
  • Language: All headings and content in the language specified by 
    output_locale
  • Number Formatting: Use English commas for thousands separators (
    1,000
    not 
    1，000
    )
  • Data emphasis: Bold important viewpoints and key numbers
  • 语气：麦肯锡/波士顿咨询风格——权威、客观、专业
  • 语言：所有标题和内容使用
    output_locale
    指定的语言
  • 数字格式：使用英文逗号作为千位分隔符（
    1,000
    而非
    1，000
    ）
  • 数据强调：用粗体突出重要观点和关键数字

Titling Constraints

标题约束

  • Numbering: Use standard numbering (
    1.
    , 
    1.1
    ) directly followed by the title
  • Forbidden Prefixes: Do NOT use "Chapter", "Part", "Section" as prefixes
  • Allowed Tone Words: Analysis, Profiling, Overview, Insights, Assessment
  • Forbidden Words: "Decoding", "DNA", "Secrets", "Mindscape", "Solar System", "Unlocking"
  • 编号：使用标准编号（
    1.
    、
    1.1
    ）直接跟标题
  • 禁用前缀：不得使用「第X章」「部分」「节」作为前缀
  • 允许的语气词：分析、画像、概述、洞察、评估
  • 禁用词：「解码」「DNA」「秘密」「心智图谱」「太阳系」「解锁」

Sub-Chapter Conclusions

子章节结论

  • Requirement: End each sub-chapter with a robust analytical paragraph (min. 200 words).
  • Narrative Flow: This paragraph must look like a natural continuation of the text. It must synthesize the section's findings into a strategic judgment.
  • Content Logic:
    1. Synthesize the conflicting or reinforcing data points above.
    2. Reveal the underlying user tension or opportunity.
    3. Key Insight: Optional: Only if you have a concise, punchy "One-Liner Truth", place it at the very end using a Blockquote (
      >
      ) to anchor the section.
  • 要求：每个子章节结尾必须有一段有深度的分析段落（至少200字）。
  • 叙述流程：该段落必须是前文的自然延续，需将本节发现整合为战略判断。
  • 内容逻辑:
    1. 综合上述冲突或相互印证的数据点。
    2. 揭示潜在的用户矛盾或机会。
    3. 核心见解：可选：如果有简洁有力的「核心真相」，将其放在最后，用块引用（
      >
      ）突出，作为本节的锚点。

Insight Depth (The "So What" Chain)

洞察深度（「意味着什么」链条）

Every insight must connect Data → User Psychology → Strategy Implication:
❌ Bad: "Females are 60%. Strategy: Target females."

✅ Good: "Females constitute 60% with a high TGI of 180. **This suggests**
   the purchase decision is driven by aesthetic and social validation
   rather than pure utility. **Consequently**, media spend should pivot
   towards visual-heavy platforms (e.g., RED/Instagram) to maximize CTR,
   treating male audiences only as a secondary gift-giving segment."
每个见解必须连接数据→用户心理→战略启示：
❌ 错误示例：「女性占比60%。战略：瞄准女性。」

✅ 正确示例：「女性占比60%，且TGI高达180。**这表明**
   购买决策由审美和社会认同驱动，而非纯粹的实用需求。**因此**,
   媒体投放应转向视觉导向平台（例如小红书/Instagram）以最大化点击率,
   仅将男性受众作为次要的礼品购买群体。"

References

参考文献

  • Inline: Use markdown links for sources (e.g. 
    [Source Title](URL)
    ) when using External Search Findings
  • References section: Formatted strictly per GB/T 7714-2015
  • 内嵌引用：使用Markdown链接标注来源（例如
    [来源标题](URL)
    ），当使用外部搜索结果时
  • 参考文献章节：严格按照GB/T 7714-2015格式排版

Markdown Rules

Markdown规则

  • Immediate Start: Begin directly with 
    # Report Title
    — no introductory text
  • No Separators: Do NOT use horizontal rules (
    ---
    )
  • 直接开头：直接以
    # 报告标题
    开头——无介绍性文本
  • 无分隔符：不得使用水平分隔线（
    ---
    ）

Report Structure Template

报告结构模板

markdown
undefined
markdown
undefined

[Report Title]

[报告标题]

Abstract

摘要

[Executive summary with key takeaways]
[包含关键结论的执行摘要]

1. Introduction

1. 引言

[Background, objectives, methodology]
[背景、目标、研究方法]

2. [Body Chapter Title]

2. [主体章节标题]

2.1 [Sub-chapter Title]

2.1 [子章节标题]

Chart Description
MetricBrand ABrand B
.........
[Integrated narrative analysis: What → Why → So What, min. 200 words]
[Optional: One-liner strategic truth]
图表描述
指标A品牌B品牌
.........
[综合叙述分析：是什么→为什么→意味着什么，至少200字]
[可选：一句有力的战略核心真相]

2.2 [Sub-chapter Title]

2.2 [子章节标题]

...
...

N+1. Conclusion

N+1. 结论

[Pure objective synthesis, NO bullet points, neutral tone] [Para 1: The fundamental nature of the group/market] [Para 2: Core tension or behavior pattern] [Final: One or two sentences stating the objective truth]
[纯粹客观的综合总结，无项目符号，语气中立] [第一段：群体/市场的基本属性] [第二段：核心矛盾或行为模式] [最后：一两句陈述客观事实的句子]

N+2. References

N+2. 参考文献

[1] Author. Title[EB/OL]. URL, Date. [2] ...
undefined
[1] 作者. 标题[EB/OL]. URL, 日期. [2] ...
undefined

Complete Example

完整示例

Phase 1 Example: Framework Generation

第一阶段示例：框架生成

User provides: Research subject "Gen-Z Skincare Market Analysis"
Phase 1 output (Analysis Framework):
markdown
undefined
用户提供：研究主题「Z世代护肤品市场分析」
第一阶段输出（分析框架）：
markdown
undefined

Gen-Z Skincare Market Analysis Framework

Z世代护肤品市场分析框架

Research Overview

研究概述

  • Research Subject: Gen-Z Skincare Market Deep Analysis
  • Scope: China market, 2020-2025, consumers aged 18-27
  • Analysis Domain: Market Analysis + Consumer Insights
  • Core Research Questions:
    1. What is the size and growth momentum of the Gen-Z skincare market?
    2. What is unique about Gen-Z consumer skincare behavior patterns?
    3. How can brands effectively reach and convert Gen-Z consumers?
  • 研究主题：Z世代护肤品市场深度分析
  • 范围：中国市场，2020-2025年，18-27岁消费者
  • 分析领域：市场分析 + 消费者洞察
  • 核心研究问题:
    1. Z世代护肤品市场的规模和增长动力如何？
    2. Z世代消费者的护肤品行为模式有何独特之处？
    3. 品牌如何有效触达并转化Z世代消费者？

Chapter Skeleton

章节架构

1. Market Size & Growth Trends

1. 市场规模与增长趋势

  • Analysis Objective: Quantify Gen-Z skincare market size and identify growth drivers
  • Analysis Logic: Total market → Segmentation → Growth rate → Driver decomposition
  • Core Hypothesis: Gen-Z is becoming the core engine of skincare consumption growth
  • 分析目标：量化Z世代护肤品市场规模并识别增长驱动因素
  • 分析逻辑：整体市场→细分市场→增长率→驱动因素分解
  • 核心假设：Z世代正成为护肤品消费增长的核心引擎

Data Requirements

数据需求

#Data MetricData TypeSuggested SourcesSearch KeywordsPriorityTime Range
1China skincare market total sizeQuantitativeIndustry reports"China skincare market size 2024 2025"P02020-2025
2Gen-Z skincare spending shareQuantitativeIndustry reports, e-commerce platforms"Gen-Z skincare spending share youth"P0Latest
#数据指标数据类型建议数据源搜索关键词优先级时间范围
1中国护肤品市场总规模定量行业报告"2024 2025年中国护肤品市场规模"P02020-2025
2Z世代护肤品消费占比定量行业报告、电商平台"Z世代护肤品消费占比 年轻人"P0最新

Visualization & Content Plan

可视化与内容规划

Chart 1: Line chart — China Skincare Market Size Trend 2020-2025 Argument Structure:
  1. What: Quantified status of market size and Gen-Z share
  2. Why: Consumption upgrade, ingredient-conscious consumers, social media driven
  3. So What: Brands should prioritize building youth-oriented product lines
图表1：折线图 — 2020-2025年中国护肤品市场规模趋势 论证结构:
  1. 是什么：市场规模和Z世代占比的量化现状
  2. 为什么：消费升级、成分党崛起、社交媒体驱动
  3. 意味着什么：品牌应优先打造年轻化产品线

2. Consumer Profiling & Behavioral Insights

2. 消费者画像与行为洞察

...
...

Data Collection Task List

数据收集任务清单

[Consolidated P0/P1 tasks]
undefined
[整合后的P0/P1任务]
undefined

Phase 2 Example: Report Generation

第二阶段示例：报告生成

After data collection, user provides: Analysis Framework + Data Summary with brand metrics + chart file paths.
Phase 2 output (Final Report) follows this flow:
  1. Start with 
    # Gen-Z Skincare Market Deep Analysis Report
  2. Abstract — 3-5 key takeaways in executive summary form
    1. Introduction — Market context, research scope, data sources
    1. Market Size & Growth Trend Analysis — Embed trend charts, comparison tables, strategic narrative
    1. Consumer Profiling & Behavioral Insights — Demographics, purchase drivers, "So What" analysis
    1. Brand Competitive Landscape Assessment — Brand positioning, share analysis, competitive dynamics
    1. Marketing Strategy & Channel Insights — Channel effectiveness, content strategy implications
    1. Conclusion — Objective synthesis in flowing prose (no bullets)
    1. References — GB/T 7714-2015 formatted list
数据收集完成后，用户提供：分析框架 + 包含品牌指标的数据摘要 + 图表文件路径。
第二阶段输出（最终报告）遵循以下流程：
  1. 以
    # Z世代护肤品市场深度分析报告
    开头
  2. 摘要——3-5个关键结论的执行摘要形式
    1. 引言——市场背景、研究范围、数据源
    1. 市场规模与增长趋势分析——嵌入趋势图表、对比表格、战略叙述
    1. 消费者画像与行为洞察——人口统计、购买驱动因素、「意味着什么」分析
    1. 品牌竞争格局评估——品牌定位、份额分析、竞争动态
    1. 营销策略与渠道洞察——渠道有效性、内容战略启示
    1. 结论——客观的流畅 prose 总结（无项目符号）
    1. 参考文献——符合GB/T 7714-2015格式的列表

Quality Checklists

质量检查清单

Phase 1 Quality Checklist (Analysis Framework)

第一阶段质量检查清单（分析框架）

  • Framework covers all natural analytical dimensions for the identified domain
  • Each chapter has clear Analysis Objective, Analysis Logic, and Core Hypothesis
  • Data requirements are specific, measurable, and include actionable Search Keywords
  • Every chapter has at least one visualization plan with chart type and data mapping
  • Data priorities (P0/P1/P2) are assigned — P0 items are essential for core arguments
  • Data Collection Task List is comprehensive, deduplicated, and ready for downstream execution
  • Framework adapts to the correct domain (market/finance/industry/consumer/etc.)
  • 分析框架覆盖了所识别领域的所有自然分析维度
  • 每个章节都有清晰的分析目标、分析逻辑和核心假设
  • 数据需求具体、可衡量，并包含可执行的搜索关键词
  • 每个章节至少有一个包含图表类型和数据映射的可视化规划
  • 已分配数据优先级（P0/P1/P2）——P0项是核心论点的必要支撑
  • 数据收集任务清单全面、去重，可直接供下游执行
  • 框架已适配正确的领域（市场/财务/行业/消费者等）

Phase 2 Quality Checklist (Final Report)

第二阶段质量检查清单（最终报告）

  • All planned charts generated before report writing (Step 2.3 completed first)
  • All sections present in correct order (Abstract → Introduction → Body → Conclusion → References)
  • Every sub-chapter follows "Visual Anchor → Data Contrast → Integrated Analysis"
  • Every sub-chapter ends with a min. 200-word analytical paragraph
  • All insights follow the "Data → User Psychology → Strategy Implication" chain
  • All headings use proper numbering (no "Chapter/Part/Section" prefixes)
  • Charts are embedded with 
    ![Description](path)
    syntax
  • Numbers use English commas for thousands separators
  • Inline references use markdown links where applicable
  • References section follows GB/T 7714-2015
  • No horizontal rules (
    ---
    ) in the document
  • Conclusion uses flowing prose — no bullet points
  • Report starts directly with 
    #
    title — no preamble
  • Missing P0 data is explicitly flagged in the report
  • 所有规划的图表在撰写报告前已生成（步骤2.3已完成）
  • 所有章节按正确顺序呈现（摘要→引言→主体→结论→参考文献）
  • 每个子章节遵循「视觉锚点→数据对比→综合分析」流程
  • 每个子章节结尾有至少200字的分析段落
  • 所有见解遵循「数据→用户心理→战略启示」链条
  • 所有标题使用正确的编号（无「第X章/部分/节」前缀）
  • 图表使用
    ![描述](路径)
    语法嵌入
  • 数字使用英文逗号作为千位分隔符
  • 内嵌引用在适用时使用Markdown链接
  • 参考文献章节符合GB/T 7714-2015标准
  • 文档中无水平分隔线（
    ---
    ）
  • 结论使用流畅的prose——无项目符号
  • 报告直接以
    #
    标题开头——无前置说明
  • 缺失的P0数据已在报告中明确标记

Output Format

输出格式

  • Phase 1: Output the complete Analysis Framework in Markdown format
  • Phase 2: Output the complete Report in Markdown format
  • 第一阶段：以Markdown格式输出完整的分析框架
  • 第二阶段：以Markdown格式输出完整的报告

Settings

设置

output_locale = zh_CN  # configurable per user request
reasoning_locale = en
output_locale = zh_CN  # 可根据用户请求配置
reasoning_locale = en

Notes

注意事项

  • This skill operates in two phases of a multi-step agentic workflow:
    • Phase 1 produces the analysis framework and data collection requirements
    • Data collection is performed by other skills (deep-research, data-analysis, etc.)
    • Phase 2 receives the collected data and produces the final report
  • Dynamic titling: Rewrite topics from the Framework into professional, concise subject-based headers
  • The Conclusion section must contain NO detailed recommendations — those belong in the preceding body chapters
  • Each statement in the report must be supported by data points from the input Data Summary
  • The framework should adapt its analytical dimensions and depth to the specific domain (financial analysis uses different frameworks than consumer insights)
  • When the research subject is ambiguous, default to the broadest reasonable scope and note assumptions
  • 本Skill在多步骤Agent工作流的两个阶段运作：
    • 第一阶段生成分析框架和数据收集需求
    • 数据收集由其他Skill执行（深度调研、数据分析等）
    • 第二阶段接收收集的数据并生成最终报告
  • 动态标题：将框架中的主题重写为专业、简洁的主题式标题
  • 结论部分不得包含详细建议——建议应放在前面的主体章节中
  • 报告中的每个陈述必须有输入数据摘要中的数据点支撑
  • 框架应根据特定领域调整分析维度和深度（财务分析使用的框架与消费者洞察不同）
  • 当研究主题模糊时，默认采用最合理的宽泛范围，并注明假设