competitive-analysis by anthropics/financial-services-plugins
npx skills add https://github.com/anthropics/financial-services-plugins --skill competitive-analysis构建完整的竞争分析报告。这是一个两阶段流程:首先收集需求并获得大纲批准,然后进行构建。
此技能在 PowerPoint 加载项和聊天中均可使用。开始前请先识别您所处的环境——操作机制不同,但工作流程相同:
.pptx 文件(或构建到用户上传的文件中)。以下所有内容在两种环境中均适用。
竞争分析对不同的人意味着不同的事情。在进行任何研究或幻灯片构建之前,请使用 ask_user_question 来明确他们实际想要什么。不要猜测——一个 20 页的同行对标报告和一个 5 页的市场地图都是"竞争分析",但形式完全不同。
如果可能,请在一轮中收集信息(该工具最多可处理 4 个问题):
如果用户上传了包含竞争对手数据的 Excel/CSV 文件,请在开始提取数字之前确认哪些列对应哪些指标。源文件保真度很重要:严格按照给定值使用,不要重新计算或四舍五入。
在大纲获得批准之前,不要创建幻灯片。 提出幻灯片标题和一行内容说明,呈现给用户,并获得肯定答复。一份竞争分析报告是 10-20 页相互关联的内容——因为第 4 页错误而重建的成本很高。大纲是廉价的迭代点。
在提出大纲时,ask_user_question 非常适合用于结构性决策:选择哪种定位可视化(2×2 矩阵 / 雷达图 / 层级图——下面的第 5 步),如何对竞争对手进行分组(按商业模式 / 细分市场 / 市场地位——第 4 步)。这些都是用户可能有意见的品味选择。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
当用户指定某件事时,这是一个要求,而不是建议:
排版 — 明确设置,不要依赖默认值:
图表:
表格:
颜色: 最多 2-3 种颜色。柔和色调——海军蓝、灰色,一种强调色。整个报告中相同的颜色含义。
| 始终遵守 | 视情况而定 |
|---|---|
| 用户指定时的精确标题/章节 | 用户未指定时的创意标题 |
| 用户说图表时用图表;用户说表格时用表格 | 未指定时的可视化类型 |
| 他们列出的每个竞争对手/数据点 | 未指定时的竞争对手数量 |
| 指定时的精确数值 | 精度未指定时的四舍五入 |
| 标题适合不溢出 | 竞争对手类别数量 |
| 无重叠元素 | 比较哪些维度 |
在开始任何工作之前:这个行业实际依赖哪 3-5 个指标?在每个竞争对手之间一致地使用这些指标。
| 行业 | 关键指标 |
|---|---|
| SaaS | ARR, NRR, CAC 回收期, LTV/CAC, 40 法则 |
| 支付 | GPV, 费率, 附加率, 交易利润率 |
| 市场平台 | GMV, 费率, 买家/卖家比率, 复购率 |
| 零售 | 同店销售额, 库存周转率, 每平方英尺销售额 |
| 物流 | 货量, 单位成本, 准时交付率, 产能利用率 |
未列出的行业 — 选择投资者和运营者用来对标的指标。
规模、增长、驱动因素、阻力。附上来源。
正确:"嵌入式支付在 2024 年为 800-1000 亿美元,年复合增长率为 20-25%(麦肯锡 2024)" 错误:"市场庞大且增长迅速"
描绘价值如何流动。方法取决于行业结构:
| 指标 | 数值 |
|---|---|
| 收入 | $4.96B |
| 增长 | +26% 同比 |
| 毛利率 | 45% |
| 盈利能力 | $373M 调整后 EBITDA |
| 客户数 | 134K |
| 留存率 | 92% |
| 市场份额 | ~15% |
多业务公司增加细分:
| 业务板块 | 收入 | 收入同比 | 收入占比 | EBITDA | EBITDA 同比 | 利润率 |
|---|---|---|---|---|---|---|
| 板块 A | $25.1B | +26% | 57% | $6.5B | +31% | 26% |
| 板块 B | $13.8B | +31% | 31% | $2.5B | +64% | 18% |
| 板块 C | $5.1B | -2% | 12% | -$74M | -16% | -1% |
| 总计 | $44.0B | +18% | 100% | $6.5B* | - | 15% |
*如适用,注明公司成本
按适合的视角分组(如果用户未指定,这是一个很好的 ask_user_question 决策点):
| 类型 | 适用场景 |
|---|---|
| 2×2 矩阵 | 两个主导竞争因素 |
| 雷达图/蜘蛛图 | 多因素比较 |
| 层级图 | 自然聚类为战略群体 |
| 价值链图 | 垂直行业 |
| 生态系统图 | 平台市场 |
按行业查看 references/frameworks.md 获取 2×2 轴对。
每个竞争对手两个表格。
指标:
| 指标 | 数值 |
|---|---|
| 收入 | $X.XB |
| 增长 | +XX% 同比 |
| 毛利率 | XX% |
| 市值 | $X.XB |
| 盈利能力 | $XXXM EBITDA |
| 客户数 | XXK |
| 留存率 | XX% |
| 市场份额 | ~XX% |
定性分析:
| 类别 | 评估 |
|---|---|
| 业务 | 他们做什么(1 句话) |
| 优势 | 2-3 个要点 |
| 劣势 | 2-3 个要点 |
| 战略 | 当前优先事项 |
| 维度 | 公司 A | 公司 B | 公司 C |
|---|---|---|---|
| 规模 | ●●● $160B | ●●○ $45B | ●○○ $8B |
| 增长 | ●●○ +26% | ●●● +35% | ●●○ +22% |
| 利润率 | ●●○ 7.5% | ●○○ 3.2% | ●●● 15% |
并购交易(倍数、理由)、合作伙伴关系趋势、融资模式、监管动态。查看 references/schemas.md 获取并购交易表格格式。
护城河评估 — 对每个竞争对手在以下方面进行强/中/弱评级:
| 护城河 | 评估内容 |
|---|---|
| 网络效应 | 用户/供应商飞轮强度;跨边 vs 同边 |
| 转换成本 | 技术集成深度、合同锁定、行为习惯 |
| 规模经济 | 规模下的单位成本优势;最小有效规模 |
| 无形资产 | 品牌、专有数据、监管许可、专利 |
必需的合成要素:
对于投资背景(如果第一阶段范围界定说不需要,则跳过):
| 情景 | 概率 | 关键驱动因素 |
|---|---|---|
| 看涨 | 30% | 市场份额增长,利润率扩张 |
| 基准 | 50% | 当前轨迹持续 |
| 看跌 | 20% | 竞争压力,利润率压缩 |
完成前检查:
提示保真度
数据一致性
布局
内容
对每张幻灯片运行标准视觉验证检查——这可以捕获重叠、溢出和低对比度文本,这些在读取 XML 时不会显示。
每周安装次数
76
代码仓库
GitHub 星标数
5.6K
首次出现
14 天前
安全审计
安装于
gemini-cli72
opencode72
codex71
github-copilot71
kimi-cli71
amp71
Build a complete competitive analysis deck. This is a two-phase process: gather requirements and get outline approval first, then build.
This skill works in both the PowerPoint add-in and chat. Identify which you're in before starting — the mechanics differ, the workflow doesn't:
.pptx file (or build into one the user uploaded).Everything below applies in both.
Competitive analysis means different things to different people. Before any research or slide-building, use ask_user_question to pin down what they actually want. Don't guess — a 20-slide peer benchmarking deck and a 5-slide market map are both "competitive analysis" and take completely different shapes.
Gather in one round if you can (the tool takes up to 4 questions):
If they've uploaded an Excel/CSV with competitor data, confirm which columns map to which metrics before you start pulling numbers. Source-file fidelity matters: use values exactly as given, don't recalculate or re-round.
Do not create slides until the outline is approved. Propose slide titles and one-line content notes, present them to the user, get a yes. A competitive deck is 10-20 slides of interlocking content — rebuilding because slide 4 was wrong is expensive. The outline is the cheap iteration point.
When proposing the outline, ask_user_question works well for the structural decisions: which positioning visualization (2×2 matrix / radar / tier diagram — Step 5 below), how to group competitors (by business model / segment / posture — Step 4). These are taste calls the user likely has an opinion on.
When the user specifies something, that's a requirement, not a suggestion:
Typography — set explicitly, don't rely on defaults:
Charts:
Tables:
Color: 2-3 colors max. Muted — navy, gray, one accent. Same color meanings throughout.
| Always | Case-by-case |
|---|---|
| Exact titles/sections when user specifies | Creative titles when they don't |
| Chart when user says chart; table when they say table | Visualization type when unspecified |
| Every competitor/data point they list | Number of competitors when unspecified |
| Exact values when specified | Rounding when precision unspecified |
| Titles fit without overflow | Number of competitor categories |
| No overlapping elements | Which dimensions to compare |
Before anything else: what 3-5 metrics does this industry actually run on? Use these consistently across every competitor.
| Industry | Key metrics |
|---|---|
| SaaS | ARR, NRR, CAC payback, LTV/CAC, Rule of 40 |
| Payments | GPV, take rate, attach rate, transaction margin |
| Marketplaces | GMV, take rate, buyer/seller ratio, repeat rate |
| Retail | Same-store sales, inventory turns, sales per sq ft |
| Logistics | Volume, cost per unit, on-time delivery %, capacity utilization |
Industry not listed — pick the metrics investors and operators benchmark on.
Size, growth, drivers, headwinds. With sources.
Correct: "Embedded payments is $80-100B in 2024, growing 20-25% CAGR (McKinsey 2024)" Wrong: "The market is large and growing rapidly"
Map how value flows. Approach depends on industry structure:
| Metric | Value |
|---|---|
| Revenue | $4.96B |
| Growth | +26% YoY |
| Gross Margin | 45% |
| Profitability | $373M Adj. EBITDA |
| Customers | 134K |
| Retention | 92% |
| Market Share | ~15% |
Multi-segment companies add a breakdown:
| Segment | Revenue | Rev YoY | Rev % | EBITDA | EBITDA YoY | Margin |
|---|---|---|---|---|---|---|
| Seg A | $25.1B | +26% | 57% | $6.5B | +31% | 26% |
| Seg B | $13.8B | +31% | 31% | $2.5B | +64% | 18% |
| Seg C | $5.1B | -2% | 12% | -$74M | -16% | -1% |
| Total | $44.0B | +18% | 100% | $6.5B* | - | 15% |
*Note corporate costs if applicable
Group by whichever lens fits (this is a good ask_user_question decision if the user hasn't specified):
| Type | When |
|---|---|
| 2×2 matrix | Two dominant competitive factors |
| Radar/spider | Multi-factor comparison |
| Tier diagram | Natural clustering into strategic groups |
| Value chain map | Vertical industries |
| Ecosystem map | Platform markets |
See references/frameworks.md for 2×2 axis pairs by industry.
Two tables per competitor.
Metrics:
| Metric | Value |
|---|---|
| Revenue | $X.XB |
| Growth | +XX% YoY |
| Gross Margin | XX% |
| Market Cap | $X.XB |
| Profitability | $XXXM EBITDA |
| Customers | XXK |
| Retention | XX% |
| Market Share | ~XX% |
Qualitative:
| Category | Assessment |
|---|---|
| Business | What they do (1 sentence) |
| Strengths | 2-3 bullets |
| Weaknesses | 2-3 bullets |
| Strategy | Current priorities |
| Dimension | Company A | Company B | Company C |
|---|---|---|---|
| Scale | ●●● $160B | ●●○ $45B | ●○○ $8B |
| Growth | ●●○ +26% | ●●● +35% | ●●○ +22% |
| Margins | ●●○ 7.5% | ●○○ 3.2% | ●●● 15% |
M&A transactions (multiples, rationale), partnership trends, capital raising patterns, regulatory developments. See references/schemas.md for the M&A transaction table format.
Moat assessment — rate each competitor Strong / Moderate / Weak on:
| Moat | What to assess |
|---|---|
| Network effects | User/supplier flywheel strength; cross-side vs same-side |
| Switching costs | Technical integration depth, contractual lock-in, behavioral habits |
| Scale economies | Unit cost advantages at volume; minimum efficient scale |
| Intangible assets | Brand, proprietary data, regulatory licenses, patents |
Required synthesis elements:
For investment contexts (skip if the Phase 1 scoping said no):
| Scenario | Probability | Key driver |
|---|---|---|
| Bull | 30% | Market share gains, margin expansion |
| Base | 50% | Current trajectory continues |
| Bear | 20% | Competitive pressure, margin compression |
Before finishing:
Prompt fidelity
Data consistency
Layout
Content
Run standard visual verification checks on every slide — this catches overlaps, overflow, and low-contrast text that don't show up when you're reading back the XML.
Weekly Installs
76
Repository
GitHub Stars
5.6K
First Seen
14 days ago
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
gemini-cli72
opencode72
codex71
github-copilot71
kimi-cli71
amp71
Excel财务建模规范与xlsx文件处理指南:专业格式、零错误公式与数据分析
46,700 周安装