openclaw-skills/investment-memo-writer/SKILL.md
Use when turning research notes into an investment memo, writing a buy or sell thesis, or structuring catalysts, risks, and monitoring items for an IC-style document.
npx skillsauth add seaworld008/commonly-used-high-value-skills investment-memo-writerInstall 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.
将零散的研究笔记转化为能够承受投资委员会(IC)审视的决策文档。本技能专注于将事实、逻辑与前瞻性判断有机融合,生成一份包含投资论据(Thesis)、催化剂(Catalysts)、风险(Risks)及估值(Valuation)的专业投资备忘录。
# 确保已安装文档处理库
pip install markdown docx
# 下载备忘录模板
npx clawhub install investment-memo-writer
{
"ticker": "AMZN",
"recommendation": "BUY",
"target_price": 245.0,
"horizon": "12-18 Months",
"thesis": [
"AWS growth re-acceleration driven by AI workload migration",
"Advertising margins improving with high incremental EBITDA",
"Logistics optimization reducing per-package delivery cost"
],
"catalysts": [
"Q3 Cloud Revenue guidance beat",
"Prime Day record sales volume",
"Capex efficiency metrics showing lower intensity"
],
"risks": [
"Regulatory pressure on cloud dominance",
"Consumer spend softening in EU/NA markets"
]
}
### 📝 投资摘要:[AMZN] - 买入建议
**1. 核心投资逻辑 (The Thesis)**:
- 市场低估了 AWS 在生成式 AI 领域的长尾效应,随着资本支出(Capex)转化为收入,利润率有望在明年 Q1 见底回升。
**2. 为什么市场错了 (Variant Perception)**:
- 我们认为市场过度关注了短期的折旧压力,而忽略了云计算业务在垂直行业(如医疗、金融)的渗透率上限。
**3. 估值推演 (Valuation Ranges)**:
- **Base Case**: $210 (15x EV/EBITDA FY26) - **回报 +25%**。
- **Bear Case**: $165 (12x EV/EBITDA FY26) - **风险 -5%**。
**4. 关键监控项 (Key to Monitor)**:
- AWS 月度账单增长率是否维持在 12% 以上。
# 基于 JSON 模板生成 Markdown 格式的初步草案
python scripts/build_memo.py --input assets/amzn_v1.json --output draft_memo.md
investment-memo-writer 提取当初的 Thesis,并与当前的 news-feed 对比,分析是“逻辑受损”还是“市场超跌”。mermaid-tools 技能插入流程图。MEMORY.md 并在 cron 中设定自动刷新任务。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.