From stock-deep-analyzer
Performs institutional-grade comparable company analysis on a target stock, computing PE/PB/EV-EBITDA percentile rankings and implied target prices relative to a peer group.
How this command is triggered — by the user, by Claude, or both
Slash command
/stock-deep-analyzer:compsThe summary Claude sees in its command listing — used to decide when to auto-load this command
# /comps <股票代码> 对目标股票做机构级 Comparable Company Analysis,识别相对同行的估值位置。 ## 工作流 1. 拉取目标股票基础数据 + 同行列表 (`fetch_similar_stocks.py`) 2. 调用: 3. 输出: - 同行池(默认 4-10 家) - 关键倍数统计:min / p25 / median / p75 / max / mean - 目标公司在每个倍数上的百分位排名 - 中位 PE × EPS → 隐含每股价 - 中位 PB × BVPS → 隐含每股价 - 估值结论(便宜 / 合理偏低 / 合理偏高 / 昂贵) ## 展示规范 - 峰值排序:PE / EV-EBITDA / P/S 三栏为主 - 颜色:低于 p25 标绿,高于 p75 标红 - 百分位:0-25 便宜 / 25-50 合理偏低 / 50-75 合理偏高 / 75-100 昂贵
对目标股票做机构级 Comparable Company Analysis,识别相对同行的估值位置。
fetch_similar_stocks.py)from lib.fin_models import build_comps_table
comps = build_comps_table(target, peers)
npx claudepluginhub godisego/hot-money --plugin stock-deep-analyzer2plugins reuse this command
First indexed Apr 16, 2026
/compsPerforms institutional-grade comparable company analysis on a target stock, computing PE/PB/EV-EBITDA percentile rankings and implied target prices relative to a peer group.
/compsBuilds A-share comparable company analysis for a given company name or code, selecting 3-8 peers, collecting financial metrics, and outputting Excel table plus valuation summary.
/dcfBuilds a DCF valuation model with comparable company analysis to inform terminal multiples, producing Excel spreadsheets with bear/base/bull scenarios and sensitivity tables.
/compareCompares multiple stocks side by side using key metrics, valuation, growth, and performance data. Produces a comparison table and summary of relative value and risks.
/researchProduces institutional-grade equity research reports for any stock ticker, including fundamental analysis, price targets, catalyst timeline, risk assessment, and technical context.
/research-equityGenerates a structured equity research note from consensus estimates, historical fundamentals, price history, and macro data using LSEG analytics.