analyze

allenai2014/ai-investment-advisor · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/allenai2014/ai-investment-advisor --skill analyze
0 commentsdiscussion
summary

基于宏观-行业-个股三层分析框架,数据驱动的专业投资分析。

skill.md

/analyze - 个股深度分析 v3.0

基于宏观-行业-个股三层分析框架,数据驱动的专业投资分析。

使用方式

/analyze 588000        # 分析ETF
/analyze 002594        # 分析A股
/analyze 00700         # 分析港股
/analyze 比亚迪        # 用名称也可以

核心投资框架

┌─────────────────────────────────────────────────┐
│                 投资分析框架                      │
├─────────────────────────────────────────────────┤
│  1. 宏观环境(大势)20分                          │
│     ├─ 市场周期:牛市/熊市/震荡                   │
│     ├─ 指数趋势:沪深300 vs MA20                 │
│     ├─ 资金环境:北向资金流向                     │
│     └─ 市场情绪:涨跌比例                        │
├─────────────────────────────────────────────────┤
│  2. 行业分析(中观)20分                          │
│     ├─ 板块强弱:相关板块排名                     │
│     ├─ 资金流向:板块净流入                       │
│     ├─ 相对强度:ETF横向对比                     │
│     └─ 政策催化:行业政策动向                     │
├─────────────────────────────────────────────────┤
│  3. 个股分析(微观)60分                          │
│     ├─ 趋势:均线排列+多周期共振                  │
│     ├─ 动能:MACD+RSI                           │
│     ├─ 量价:量比+量价配合+背离                   │
│     └─ 位置:ATR止损+支撑压力                    │
├─────────────────────────────────────────────────┤
│  4. 交易策略                                     │
│     ├─ 买点:理想/激进价位                       │
│     ├─ 止损:ATR动态止损                         │
│     └─ 目标:压力位参考                          │
└─────────────────────────────────────────────────┘

数据来源优先级

优先级 来源 用途
1 fetch_full_analysis.py 宏观+行业+技术全套数据
2 用户配置文件 持仓、关注方向、投资风格
3 WebSearch 仅用于财报、公告、研报

禁止行为

  • ❌ 使用WebSearch获取价格数据
  • ❌ 编造技术指标
  • ❌ 脚本失败时跳过分析
  • ❌ 没有数据支撑的模糊判断

执行步骤

第一步:运行完整分析脚本(必须)

cd "股市信息" && python3 scripts/fetch_full_analysis.py <代码>

港股:

cd "股市信息" && python3 scripts/fetch_full_analysis.py 00700 --market hk

第二步:解读脚本输出

脚本输出的核心模块:

模块 字段 说明
宏观 macro.indices 主要指数涨跌
macro.market_trend 牛市/熊市/震荡判断
macro.north_flow 北向资金流向
macro.market_sentiment 涨跌家数比
行业 sector.related_sectors 相关板块表现
sector.sector_flow 板块资金流入
sector.etf_comparison ETF横向对比
sector.relative_strength 领涨/跟涨/跟跌
技术 technical.trend 均线趋势
technical.macd MACD状态
technical.rsi RSI超买超卖
technical.atr ATR止损参考
technical.volume 量价配合
评分 score 100分制综合评分

第三步:读取用户配置

股市信息/Config/Holdings.md   → 是否已持有
股市信息/Config/Watchlist.md  → 关注方向
股市信息/Config/Profile.md    → 投资风格

第四步:WebSearch补充(仅限必要时)

只在以下情况使用:

  • 公司最新财报
  • 近期重大公告
  • 机构研报/目标价

必须标注来源和日期


分析框架详解

一、宏观环境分析(20分)

脚本输出 macro 字段:

{
  "market_trend": {
    "cycle": "牛市",
    "cycle_score": 2,
    "hs300_vs_ma20": 1.51
  },
  "north_flow": {
    "5d_total": 150.5,
    "consecutive_days": 3,
    "direction": "流入",
    "signal": "外资积极"
  },
  "market_sentiment": {
    "up_ratio": 65.2,
    "sentiment": "偏乐观"
  }
}

市场周期判断规则

条件 周期 得分
沪深300 > MA20 且 60日涨幅>0 牛市 +12
沪深300 < MA20 且 60日跌幅>10% 熊市 +4
其他 震荡 +8

北向资金信号

5日累计 方向 得分
> 50亿 持续流入 +8
< -50亿 持续流出 +2
其他 中性 +4

二、行业分析(20分)

脚本输出 sector 字段:

{
  "related_sectors": [
    {"name": "半导体概念", "change": 2.34, "turnover": 5.95},
    {"name": "存储芯片", "change": 1.13, "turnover": 4.27}
  ],
  "sector_flow": [
    {"name": "半导体概念", "net_flow": 38.8亿, "net_ratio": 0.88}
  ],
  "etf_comparison": [
    {"code": "159995", "name": "芯片ETF", "change": 1.16},
    {"code": "588000", "name": "科创50ETF", "change": -0.38}
  ],
  "relative_strength": "跟跌"
}

相对强度判断

ETF vs 同类 相对强度 得分
涨幅排名前30% 领涨 +15
涨幅接近平均 跟涨 +10
涨幅排名后30% 跟跌 +5

板块资金流向

相关板块净流入 信号 得分
多数流入 板块热度高 +5
多数流出 板块退潮 +0

三、个股技术分析(60分)

趋势分析(25分)

{
  "trend": {
    "status": "多头排列",
    "score": 2
  }
}
均线状态 得分
多头排列(MA5>MA10>MA20>MA60) +25
偏多(价格>MA20) +15
纠缠 +10
空头排列 +5

动能指标(15分)

{
  "macd": {"signal": "多头"},
  "rsi": {"value": 65, "signal": "中性"}
}
MACD状态 得分
金叉/多头 +10
死叉/空头 +5
RSI状态 得分
中性(30-70) +5
超买(>70)或超卖(<30) +3

量价分析(10分)

{
  "volume": {
    "ratio": 0.87,
    "vol_price": "量价平稳"
  }
}
量价关系 得分
放量上涨 +10
量价平稳 +6
缩量上涨 +4
放量下跌 +2

ATR止损(10分)

{
  "atr": {
    "value": 0.0382,
    "stop_loss": 1.4966,
    "stop_loss_pct": -4.86
  }
}

止损建议

  • 保守:1倍ATR
  • 标准:2倍ATR → 使用 stop_loss
  • 激进:3倍ATR

综合评分体系

维度 满分 评估内容
宏观 20 市场周期+北向资金
行业 20 相对强度+板块资金
技术 60 趋势+动能+量价+位置
总分 100

评分等级

分数 等级 建议
80-100 强势 可积极参与
65-79 偏强 可适度参与
50-64 中性 观望为主
35-49 偏弱 谨慎
0-34 弱势 回避

报告模板

# [代码] [名称] 深度分析

**分析时间**:YYYY-MM-DD HH:MM
**数据来源**:AKShare v3.0
**分析框架**:宏观-行业-个股

---

## 快速摘要

| 层级 | 判断 | 得分 |
|------|------|------|
| 宏观环境 | 牛市/熊市/震荡 | XX/20 |
| 行业强度 | 领涨/跟涨/跟跌 | XX/20 |
| 技术形态 | 多头/空头/震荡 | XX/60 |
| **综合** | **强势/偏强/中性/偏弱/弱势** | **XX/100** |

---

## 一、宏观环境(大势)

### 市场周期
- 沪深300:XXXX (+X
how to use analyze

How to use analyze on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add analyze
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/allenai2014/ai-investment-advisor --skill analyze

The skills CLI fetches analyze from GitHub repository allenai2014/ai-investment-advisor and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/analyze

Reload or restart Cursor to activate analyze. Access the skill through slash commands (e.g., /analyze) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.650 reviews
  • Dhruvi Jain· Dec 24, 2024

    Useful defaults in analyze — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Isabella Zhang· Dec 20, 2024

    Registry listing for analyze matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Camila Kim· Dec 16, 2024

    Solid pick for teams standardizing on skills: analyze is focused, and the summary matches what you get after install.

  • Zaid Wang· Dec 12, 2024

    Useful defaults in analyze — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Zaid Brown· Dec 8, 2024

    analyze fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Aisha Kim· Dec 4, 2024

    analyze is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Ishan Sanchez· Nov 23, 2024

    analyze reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Oshnikdeep· Nov 15, 2024

    analyze has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Aisha Shah· Nov 11, 2024

    Keeps context tight: analyze is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Amelia Kim· Nov 7, 2024

    I recommend analyze for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

showing 1-10 of 50

1 / 5