同行全追踪 (Peer Financial Tracker)

Purpose

Generate a comprehensive, interactive HTML dashboard for comparing a target company against its industry peers. The dashboard covers: real-time market data, multi-period financial comparisons, full announcement tracking with PDF links, news sentiment monitoring, price deviation alerts, and customizable metric charts.

When to Use

Trigger this skill when the user asks to:

• Compare a company's financials with industry peers
• Generate a financial dashboard for a specific company
• Track peer companies in an industry
• Monitor announcements and news for a company and its competitors
• Set up a "同行全追踪" (peer tracking) view

Workflow

Step 1: Gather user requirements

Collect:

• Target company name (required) — e.g. "宁德时代", "晶品特装", "比亚迪"
• Peer companies (optional) — if user doesn't specify, infer from same industry/sector
• Industry/board (optional) — e.g. "动力电池", "无人装备"

If the user doesn't provide peer companies, identify them by:

1. Query the target company's board/sector membership
2. Select 4-6 closest peers by market cap or industry relevance

Step 2: Fetch data via westock-data CLI

Use the westock-data CLI (documented in references/westock-cli.md) to fetch:

1. Search: Get the stock code for the target company
2. Quotes: Real-time prices for target + all peers (single call, comma-separated codes)
3. K-lines: 30-day daily K-line data for sparkline charts (target + peers)
4. Financials: Income statement data (--type lrb --num 4 --raw) for target + each peer
5. Notices: Latest 20 announcements for target + each peer
   • URL format: Use http://www.cninfo.com.cn/new/disclosure/stock?stockCode=XXXXXX for the stock's disclosure page, or the PDF URL from the notice endpoint if available. Never use # placeholders — every announcement must have a valid, clickable link.
6. News: Latest 10 news articles for target + each peer

Parse the JSON outputs and normalize into a unified data structure.

Step 3: Build the data model

Construct a JavaScript data structure matching the template format:

const COMPANIES = [
  {
    code: 'sz300750', name: '宁德时代', short: '宁', color: '#d61f26', own: true,
    price: 245.80, chg: -2.35, mcap: '10780亿', pe: 22.5, pb: 4.2, stars: 4,
    spark: { base: 252.0, drift: -0.08, vol: 1.2 },
    fin: {
      q1: { rev: 890.5, revYoy: 8.2, profit: 105.3, profitYoy: 12.5, gm: 22.3, nm: 11.8, roe: 4.5 },
      fy: { rev: 3620.0, revYoy: 10.1, profit: 441.2, profitYoy: 9.8, gm: 21.8, nm: 12.2, roe: 18.2 },
      q3: { rev: 2590.0, revYoy: 11.5, profit: 310.8, profitYoy: 8.5, gm: 22.0, nm: 12.0, roe: 13.0 }
    },
    // 异动监控数据
    alert: {
      dev3: 5.2, dev5: -1.8, dev10: -3.5, dev30: -8.2,
      rules: [
        { name: '单日涨跌幅超±7%', triggered: false, value: '-2.35%', threshold: '±7%' },
        { name: '连续3日同向异动', triggered: false, value: '否', threshold: '3日' },
        { name: '成交量超20日均量200%', triggered: true, value: '215%', threshold: '200%' },
        { name: '10日累计偏离值超±20%', triggered: false, value: '-3.5%', threshold: '±20%' },
        { name: '价格触及30日新高/新低', triggered: false, value: '—', threshold: '30日' }
      ]
    }
  },
  // ... peers
];

For financial data periods, use:

• q1: Latest quarterly report (or H1 if mid-year)
• fy: Latest annual report
• q3: Previous Q3 report

Step 4: Generate the HTML dashboard

Use the template in assets/dashboard-template.html as the base. The template includes:

Layout sections (top to bottom):

1. Top bar: Dashboard title + industry tag + company search/添加
2. Peer strip: Company chips with remove buttons
3. Row 1 (2-column):
   • Left: Own company compact card (price, OHLCV, deviation indicators)
   • Right: News sentiment with emotion donut chart
4. Row 2 (full-width): 异动监控 (Anomaly Monitoring)
   • Left panel: 累计偏离值监控 (Cumulative Deviation vs Index)
   • Right panel: 预警条件监控 (Alert Rules with status indicators)
5. Row 3 (full-width): Financial comparison table (period switchable)
6. Row 4 (full-width): Single-metric bar chart (7 metrics switchable via chips)
7. Row 5 (2-column): Full announcement tracking

Key design rules:

• A-share color convention: red for up (涨), green for down (跌)
• Own company always first row, highlighted with orange background
• All charts use pure SVG (no external CDN dependencies)
• Table column highlighting syncs with selected chart metric
• Period switching (Q1/FY/Q3) updates table + chart in sync
• Announcements support PDF link jumps + keyword highlighting
• Peer removal updates all panels (table, chart, peer count)

Step 5: Present and iterate

Save the generated HTML to the workspace, present it via present_files, and ask for feedback. Common adjustments:

• Add/remove specific metrics
• Adjust layout or color scheme
• Add more peer companies
• Change default period

Important Notes

• The westock-data CLI is at: C:/Program Files/WorkBuddy/resources/app.asar.unpacked/resources/builtin-skills/westock-data/scripts/index.js
• Run with the managed Node.js: C:\Users\14578\.workbuddy\binaries\node\versions\22.22.2\node.exe
• If a peer company's financial data cannot be fetched (API limitations), use reasonable estimated values and mark them as "估算值" in footnotes
• All SVG charts are self-contained — no external libraries needed
• The template supports up to 10 peer companies; beyond that, suggest limiting