agentleFS
AtmoskunAtmoskun/claude-skills/skills/research/SKILL.md

research

Skill0 starsChanged 9 months agoMITView on GitHub

股票研究的统一入口,整合知识库、网络搜索、多 AI 验证。 3. Supply Chain Context - 查询 ~/.claude/skills/supply-chain/data/supply_chain.db: SELECT * FROM mentions WHERE mentioned_ticker = '{TICKER}' ORDER BY date DESC - 或读取 ~/Documents/Obsidian Vault/研究/供应链/{TICKER}_mentions.md - 展示:哪些公司在财报中提到了该 ticker,说了什么(前瞻性信号) 研究偏好在 CLAUDE.md 中定义: - 投资风格: Long-biased, fundamental research - 输出风格: 数据驱动,表格对比 当用户使用 /research TICKER --coverage 时: 当用户使用 /research TICKER --deep 时:

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • truongtv22Skill

    Problem-Solving Techniques

    Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

    Also in 5 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +5 more from Lambenthan
  • +1 more from skyllwt

The file

Files
SKILL.md

/research - 一键研究命令

股票研究的统一入口,整合知识库、网络搜索、多 AI 验证。

使用方式

/research TICKER                    # 快速研究(用现有知识)
/research TICKER --deep             # 深度研究(9 维度框架输出)
/research TICKER --coverage         # 框架覆盖度分析
/research TICKER "具体问题"          # 针对性研究

示例

/research NVDA                      # NVDA 快速概览
/research NVDA --deep               # NVDA 9 维度框架深度研究
/research NVDA --coverage           # NVDA 覆盖度矩阵 + 研究盲区
/research NVDA "AI 芯片竞争格局"     # 针对性问题
/research "数据中心电力"             # 主题研究(非个股)

研究流程

输入 Ticker/主题
       ↓
┌──────┴──────┐
│ 市场数据快照 │ → yfinance: 价格、估值、分析师、内部人 [YF]
└──────┬──────┘
       ↓
┌──────┴──────┐
│  知识库检索  │ → 读取 Obsidian 笔记、历史 thesis
└──────┬──────┘
       ↓
┌──────┴──────┐
│  NotebookLM │ → 查询已有研报、纪要(如有)
└──────┬──────┘
       ↓ (--deep 模式)
┌──────┴──────┐
│  网络搜索   │ → WebSearch 最新信息
└──────┬──────┘
       ↓
┌──────┴──────┐
│  生成报告   │ → 结构化输出,标注来源
└──────┬──────┘
       ↓
┌──────┴──────┐
│  保存笔记   │ → Obsidian Research Notes
└─────────────┘

输出格式

# {TICKER} 研究笔记
日期: YYYY-MM-DD

## 📋 核心观点 (TLDR)
- 一句话总结

## 🏢 公司概况
- 业务模式
- 竞争格局
- 核心指标 [YF] (市值、P/E、营收、利润率等)

## 📊 投资逻辑
- 核心假设 1 [来源: KB/WS/Thesis]
- 核心假设 2 [来源: KB/WS/Thesis]

## ⚠️ 风险因素
- 风险 1
- 风险 2

## 📈 估值参考
- 当前估值 [YF] (P/E, PEG, EV/EBITDA, P/B)
- 分析师目标价与评级 [YF]
- 历史区间
- 可比公司

## 🔗 来源
- [YF] Yahoo Finance (yfinance) 市场数据
- [KB] 知识库引用
- [WS] 网络搜索
- [Thesis] 现有 thesis 文件

执行步骤

  1. 解析输入
    • 提取 TICKER 或研究主题
    • 识别 --deep 标志
    • 提取具体问题(如有)
  2. 市场数据快照(仅个股 Ticker,主题研究跳过)
    cd ~/.claude/skills && python shared/market_snapshot.py TICKER
    • 自动拉取: 价格/52周区间/市值、估值指标(P/E/PEG/EV)、盈利能力(毛利率/ROE)、分析师目标价与评级、内部人交易、机构持仓 Top 10
    • 输出直接嵌入报告的 公司概况 和 估值参考 部分
    • 来源标注: [YF] (Yahoo Finance via yfinance)
    • 可选按模块调用: --section price, --section analysts 等
    • JSON 模式: --json 输出机器可读格式
  3. 知识库检索
    • 搜索 PORTFOLIO/portfolio_monitor/research/companies/{TICKER}/
    • 搜索 Obsidian 收件箱/ 相关文章
    • 读取现有 thesis.md(如有)
  4. Supply Chain Context
    • 查询 ~/.claude/skills/supply-chain/data/supply_chain.db: SELECT * FROM mentions WHERE mentioned_ticker = '{TICKER}' ORDER BY date DESC
    • 或读取 ~/Documents/Obsidian Vault/研究/供应链/{TICKER}_mentions.md
    • 展示:哪些公司在财报中提到了该 ticker,说了什么(前瞻性信号)
  5. 13F Institutional Activity
    • 搜索 ~/13F-CLAUDE/output/*/ 中的 CSV 文件,查找包含该 ticker 的持仓记录
    • 展示:哪些知名基金经理持有该 ticker,季度变动趋势
    • 这是 "smart money" 验证——机构是在买入还是卖出
  6. Podcast Mentions
    • 搜索 ~/Documents/Obsidian Vault/信息源/播客/ 中提到该 ticker/公司名的播客
    • 提取关键论点和数据点
  7. ChatGPT Prior Analysis
    • 搜索 ~/Documents/Obsidian Vault/ChatGPT/Investment Research/ 中提到该 ticker 的对话
    • 提取之前的分析观点,避免重复研究
  8. NotebookLM 查询(如果有相关 notebook)
    • 调用 /notebooklm 查询相关内容
    • 获取 citation-backed 答案
  9. 网络搜索(--deep 模式)
    • WebSearch 最新新闻、财报
    • 搜索竞争对手动态
  10. 生成研究报告
    • 按输出格式整合信息
    • 标注每条信息的来源
    • 标记需要进一步验证的假设
  11. 保存到 Obsidian
    • 路径: Documents/Obsidian Vault/研究/研究笔记/{TICKER}_YYYY-MM-DD.md
    • 更新 thesis 文件(如适用)

与其他 Skills 的关系

Skill关系
/thesis读取/更新 thesis 文件
/notebooklm查询已有研报知识库
/portfolio获取持仓信息
/supply-chain查询供应链提及(谁在财报中提到该 ticker)
/13f查询机构持仓变动(smart money 验证)
/podcast搜索播客中的 ticker 相关讨论
/chatgpt-organizer搜索历史 ChatGPT 投资分析
/wechat-hao导入的文章可被检索

配置

研究偏好在 CLAUDE.md 中定义:

  • 投资风格: Long-biased, fundamental research
  • 输出风格: 数据驱动,表格对比

注意事项

  • 所有结论必须标注来源 [KB]/[WS]/[Thesis]
  • 遇到矛盾信息时明确指出
  • 估值数据标注时间戳
  • 不做买卖建议,只提供分析框架

--coverage 模式:框架覆盖度分析

当用户使用 /research TICKER --coverage 时:

  1. 运行覆盖度扫描:
    cd ~/.claude/skills && python shared/framework_coverage.py scan TICKER
  2. 展示 9 维度覆盖矩阵(covered/partial/gap)
  3. 展示研究盲区和建议的研究问题:
    cd ~/.claude/skills && python shared/framework_coverage.py questions TICKER
  4. 输出覆盖度分数和下一步行动建议

--deep 模式:9 维度框架结构化输出

当用户使用 /research TICKER --deep 时:

  1. 读取中央框架定义:
    import yaml
    from pathlib import Path
    fw_path = Path.home() / ".claude" / "skills" / "shared" / "analysis_framework.yaml"
    with open(fw_path, encoding="utf-8") as f:
        framework = yaml.safe_load(f)
  2. 执行正常的数据收集步骤(KB + web + NLM + 13F + supply chain)
  3. 输出改为 9-section 结构,每个 section:
    • 使用 key_questions 作为研究引导
    • 使用 data_source_mapping 定向搜索对应数据源
    • 已回答的问题附来源标注
    • 未能回答的问题标记为 "❓ 待研究"
    • 末尾附 coverage confidence(High/Medium/Low/Gap)
  4. 报告最后附 Coverage Matrix 总结:
    ## 📐 Coverage Summary
    Score: 78% (6/9 covered, 2 partial, 1 gap)
    Gap: S5 管理层, Partial: S6 估值, S7 风险
    建议: /research TICKER "management incentives" 填补 S5
  5. 保存到 研究/研究笔记/{TICKER}_YYYY-MM-DD.md(使用 9 维度标题结构)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.