股票研究

其他 社区

技能解读

当前原文的自动摘译,尚未人工审校。

股票研究技巧

这是 Hone 典型的股票研究切入点。将其用于三个密切相关的用户意图: 单一公司研究 指定公司的估值框架 基于标准的股票筛选,返回简短的比较列表

工具指南

工具调用·目的data_fetch(data_type="snapshot", symbol="ticker")·推荐。获取包含价格行为和公司概况的快照 data_fetch(data_type="quote", symbol="ticker") · 获取详细的实时报价数据,例如价格、变化和交易量 data_fetch(data_type="profile", symbol="ticker") · 获取公司详细信息,例如业务描述、行业和首席执行官 data_fetch(data_type="financials", symbol="ticker") · 获取财务报表或估值相关的基本面

模式选择

在获取数据之前,根据用户的请求选择模式: 研究模式:用户询问一家公司、股票行情、基本面、技术或最新动态 估值模式:用户询问一家公司是否看起来富有、便宜、实力雄厚、价格合理,或者想要估值桥梁/同行观点 筛选模式:用户询问与人工智能、股息收益率、价值、增长或动量等因素相匹配的候选名单

研究模式

识别用户提到的股票代码。如果不清楚,首先用data_fetch(data_type="search", symbol="...")搜索snapshot获取基线数据决定是否为新闻或原因添加web_search输出涵盖价格走势、基本面、近期事件和风险的综合答案如果用户明确要求图表、趋势线、比较视觉效果,或者答案作为图表会更清晰,则将您已经获取的具体数字交给chart_visualization

估值模式

首先解决股票代码;在未确认公司之前请勿尝试估值 Fetch financials;如果您还需要当前的市场背景,请添加quote或snapshot 使用web_search了解最新的运营更新、指导变更或同行比较背景 通过假设、同行倍数和业务质量解释估值,并说明哪些条件将使公司相对于同行看起来更富有、更平衡或更有吸引力

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
通用
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
94 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@B-M-Capital-Research · MIT
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
允许外网请求
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

## Stock Research Skill

This is the canonical equity-research entrypoint for Hone.

Use it for three closely related user intents:

1. Single-company research
2. Valuation framing for a named company
3. Criteria-based stock screening that returns a short comparison list

Prefer keeping these modes inside one skill so the model does not have to choose between overlapping prompt variants.

### Tool Guide

| Tool call | Purpose |
|---------|------|
| `data_fetch(data_type="snapshot", symbol="ticker")` | Recommended. Fetch a snapshot with price action plus company overview |
| `data_fetch(data_type="quote", symbol="ticker")` | Fetch detailed real-time quote data such as price, change, and volume |
| `data_fetch(data_type="profile", symbol="ticker")` | Fetch company details such as business description, industry, and CEO |
| `data_fetch(data_type="financials", symbol="ticker")` | Fetch financial statements or valuation-relevant fundamentals |
| `data_fetch(data_type="gainers_losers")` | Broader market scan when a screening request needs candidates |
| `data_fetch(data_type="sector_performance")` | Sector strength context for screening or relative positioning |
| `web_search(query="...")` | Search for news, analyst views, and recent events |

### Mode Selection

Choose the mode from the user's request before fetching data:

- **Research mode**: the user asks about one company, ticker, fundamentals, technicals, or recent developments
- **Valuation mode**: the user asks whether a company looks rich, cheap, stretched, fairly priced, or wants a valuation bridge / peer view
- **Screening mode**: the user asks for a shortlist that matches factors such as AI, dividend yield, value, growth, or momentum

### Research Mode

1. Identify the ticker mentioned by the user. If it is unclear, search first with `data_fetch(data_type="search", symbol="...")`
2. Call `snapshot` for the baseline data
3. Decide whether to add `web_search` for news or causes
4. Output a combined answer covering price action, fundamentals, recent events, and risks
5. If the user explicitly asks for a chart, trend line, comparison visual, or the answer would be materially clearer as a chart, hand off to `chart_visualization` with the concrete numbers you already fetched

### Valuation Mode

1. Resolve the ticker first; do not attempt valuation without confirming the company
2. Fetch `financials`; add `quote` or `snapshot` if you also need current market context
3. Use `web_search` for the latest operating updates, guidance changes, or peer-comparison context
4. Explain the valuation through assumptions, peer multiples, and business quality, and state which conditions would make the company look richer, more balanced, or more compelling relative to peers
5. Do not collapse the result into a simplistic categorical verdict with no assumptions attached

### Screening Mode

1. Extract the user's explicit criteria before naming companies
2. Use `gainers_losers`, `sector_performance`, or targeted `web_search` to form an initial candidate set
3. Narrow the result to 3-5 names and fetch `snapshot` for each final candidate
4. Return a comparison shortlist with why each name matches the screen, plus the main risk or diligence gap for each one
5. Do not output a blunt recommendation list without comparison logic or caveats

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。