openclaw-skills/stock-screener-builder/SKILL.md
Use when building a stock screen, filtering a universe by valuation, growth, quality, or momentum rules, or creating a repeatable shortlist for deeper research.
npx skillsauth add seaworld008/commonly-used-high-value-skills stock-screener-builderInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
建立一个清晰的研究漏斗(Research Funnel),而不是对着成千上万的股票清单漫无目的地看。本技能旨在帮助投资者构建可重复的筛选逻辑,从全市场数千只标的中通过多维财务指标(估值、增长、质量、动量)快速筛选出具有潜力的“候选池”。
# 确保已安装金融数据接口与数据处理库
pip install pandas numpy openbb requests
# 下载筛选模板
npx clawhub install stock-screener-builder
scripts/screen_stocks.py。comps-valuation-analyst 或 sec-filing-reviewer 技能进行深度背景调查。{
"name": "GARP_Strategy_V1",
"universe": "S&P 500",
"filters": {
"market_cap_min": 5000000000,
"pe_ratio_max": 25.0,
"peg_ratio_max": 1.2,
"revenue_growth_min": 0.15,
"roe_min": 0.18,
"debt_to_equity_max": 0.5
},
"sort_by": "peg_ratio",
"ascending": true,
"limit": 20
}
### 🔎 股票筛选报告:[GARP_Strategy_V1]
**1. 筛选概述 (Execution Summary)**:
- **初选池**: 500 只 (S&P 500)
- **通过过滤器**: 18 只
- **平均分值**: 7.2/10
**2. 核心幸存标的 (Top Surviving Names)**:
| 代码 | 行业 | 市盈率 (P/E) | 营收增速 | ROE | 综合得分 |
| :--- | :--- | :--- | :--- | :--- | :--- |
| **GOOGL** | Interactive Media | 22.5 | 15% | 25% | 8.8 |
| **META** | Interactive Media | 24.2 | 22% | 28% | 8.5 |
| **KLAC** | Semiconductors | 23.5 | 18% | 35% | 8.2 |
**3. 排除说明 (Why others failed)**:
- 35% 的标的因 `ROE < 18%` 被排除。
- 15% 的标的因 `PEG > 1.2` 被排除(估值过高)。
**4. 后续动作 (Next Steps)**:
- [ ] 调用 `earnings-call-analyzer` 分析 GOOGL 最新财报。
- [ ] 使用 `sec-filing-reviewer` 检查 KLAC 的地缘政治风险披露。
# 运行预定义的筛选规则
python scripts/screen_stocks.py --config assets/garp_config.json --export output/screener_results.csv
cron 技能,每天收盘后自动运行筛选器,如果出现符合“深度价值”(如:破净且现金充足)的新标的,立即通过 question 发送提醒给投资经理。tavily-search 抓取的新闻情绪得分结合。筛选出那些“基本面极佳但近期市场情绪极度悲观”(即:跌出价值)的错杀股。MEMORY.md。development
Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.
testing
Orchestrating specialist AI agent teams as a meta-coordinator. Decomposes requests into minimum viable chains, spawns each as an independent session in AUTORUN modes, and drives to final output. Use when a task spans multiple specialist domains, requires parallel agent execution, or needs hub-and-spoke routing across the skill ecosystem.
development
Converting document formats (Markdown/Word/Excel/PDF/HTML). Converts specs from Scribe and reports from Harvest into distributable formats; generates reusable conversion scripts. Use when converting documents, building accessibility-compliant PDFs, or creating Pandoc/LibreOffice pipelines.
testing
Curating cross-agent knowledge and guarding institutional memory. Extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices, prevents organizational forgetting. Use when consolidating cross-agent insights, curating memory, or auditing knowledge decay.