Stock Research Desk

该工具由12个Agent组成多因子研究流程，覆盖宏观政策、公司基本面、技术分析等维度，含反方质疑、场景预测环节。支持个股深挖、主题筛选、观察名单更新场景，输入股票/主题及可选市场，输出桌面中英双语DOCX研报，通过源质量模型过滤噪音，仅提供分析，不涉及交易执行。

wd041216-bit

热度 45.03

最近更新 2026-05-11 17:44:29

分类：数据依赖：代码执行 / 联网浏览搜索 / 读写文件 / 第三方 API应用场景：市场分析 / 报告撰写 / 财务 / 研究

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add stock-research-desk

Metadata

name: stock-research-desk
description: Claude Code skill for multi-agent equity research. Produces buy-side memos with debate, scenario projection, and bilingual DOCX delivery. Use when researching a stock, screening a sector, or maintaining a watchlist.
version: 1.0.0
metadata: {"openclaw":{"requires":{"env":["OLLAMA_API_KEY"],"bins":["python3","pip"]},"primaryEnv":"OLLAMA_API_KEY","emoji":"📈","homepage":"https://github.com/wd041216-bit/stock-research-desk"}}
allowed-tools: ["Read","Write","Edit","Bash","Grep","Glob","WebSearch","WebFetch"]
model: inherit
argument-hint: <stock-name> [--market CN|US|HK] [--screen THEME] [--watchlist]

Stock Research Desk

A 12-agent multi-factor equity research desk for single-name deep dives, theme screening, recurring watchlists, and bilingual (Chinese + English) document delivery.

Quick Start

# Deep dive a single stock
research-stock 赛腾股份 中国

# Screen a theme
research-stock screen "中国机器人" --market CN --count 3

# Watchlist
research-stock watchlist add 赛腾股份 --market 中国 --interval 7d
research-stock watchlist run-due

The 12-Agent Pipeline

Step	Agent	Search?	Focus
1	market_analyst	Yes	Macro cycle, industry structure, China narrative
2	macro_policy_strategist	Yes	Interest rates, credit cycle, policy transmission
3	company_analyst	Yes	Business quality, management, financials
4	catalyst_event_tracker	Yes	Earnings dates, insider activity, M&A, regulatory
5	sentiment_simulator	Yes	Narrative temperature, participant psychology
6	technical_flow_analyst	Yes	Price action, volume, institutional flow, options
7	comparison_analyst	Yes	Peer comparison, relative valuation anchors
8	quant_factor_analyst	Yes	Factor exposure, statistical significance, regime
9	committee_red_team	No	Contrarian challenge, hidden fragility
10	guru_council	No	Multi-perspective synthesis (Buffett/Druckenmiller/Simons)
11	mirofish_scenario_engine	No	Bull/base/bear scenario projection
12	price_committee	Yes	Target prices with explicit horizons

Workflow

Install: pip install -e .[dev]
Set OLLAMA_API_KEY in .env
Run ./bin/research-stock <name> <market> for a full memo
Or ./bin/research-stock screen "<theme>" --market CN --count N for screening
Output: bilingual DOCX on desktop with Chinese section first, English section second

Source Quality Model

Domain-level source scoring filters out noise. Official filings (cninfo.com.cn, SEC) score 94-96. Quality media (yicai, caixin) score 84. Forum noise (<36) is blocked entirely.

Safety

No trading execution
No portfolio management
No backtesting engine
Target prices always tied to explicit horizons and theses