trader-analyst

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

trader-analyst

trader-analyst

Earnings move stocks more than anything else on the calendar, and the press release is written to put the best number first. This skill reads the numbers the company actually filed with the SEC, lines them up quarter by quarter, and says plainly what changed. For a day trader it answers two questions before a trade: what did the last report say, and is the next one inside this trade?
Tool in this folder (standard library Python, no keys):
bash
python3 "${CLAUDE_SKILL_DIR}/facts.py" --help
It needs the SEC User-Agent (
sec_user_agent
in
trader/config.json
, or
SEC_USER_AGENT
): "Your Name you@example.com" with the user's real name and email. It refuses to call SEC without one.
财报发布比投资日历上的任何其他事件都更能推动股价,而且新闻稿通常会把最亮眼的数字放在最前面。此 skill 会读取公司实际向 SEC 提交的数据,逐季对齐这些数字,并直截了当地说明发生了什么变化。对于日内交易者,它会在交易前回答两个问题:上一份报告说了什么?下一份报告是否会落在这次交易期间?
此文件夹中的工具(仅使用 Python 标准库,无需密钥):
bash
python3 "${CLAUDE_SKILL_DIR}/facts.py" --help
它需要 SEC User-Agent(
sec_user_agent
位于
trader/config.json
,或环境变量
SEC_USER_AGENT
):
Your Name you@example.com
,需使用用户的真实姓名和邮箱。未提供时,它会拒绝调用 SEC。

What it reads and writes

它读取和写入什么

  • Reads
    https://data.sec.gov/api/xbrl/companyfacts/CIK##########.json
    (every number the company has tagged in its filings), the company's submissions list (for the newest 10-Q or 10-K and the newest 8-K with item 2.02, "Results of Operations") and that 8-K's folder to find the press release (the EX-99.1 exhibit).
  • Writes
    trader/metrics.json
    with
    --metrics
    : one row per company (TTM revenue, net income and diluted EPS, the latest margins and growth), for your notes or a spreadsheet.
    metrics.example.json
    in this folder is a real run for AAPL, AXP, GOOGL, KO and BAC on 2026-10-13.
  • Earnings calls: the tool does not fetch transcripts. If the user pastes one (or the company's IR page has it), read it and sum up what management said changed: guidance, margins, demand, anything they declined to answer.
  • The next report date is not in SEC data. Look for it in
    /trader-news
    headlines or on the company's investor relations page, and say where it came from.
  • 读取
    https://data.sec.gov/api/xbrl/companyfacts/CIK##########.json
    (公司在申报文件中标记的所有数据)、公司的 submissions 列表(用于查找最新的 10-Q 或 10-K,以及包含 Item 2.02“Results of Operations”的最新 8-K),并读取该 8-K 所在文件夹以查找新闻稿(EX-99.1 附件)。
  • 使用
    --metrics
    写入
    trader/metrics.json
    :每家公司一行,包含 TTM 营收、净利润、稀释后 EPS、最新利润率和增长率,可用于笔记或电子表格。此文件夹中的
    metrics.example.json
    是 2026-10-13 对 AAPL、AXP、GOOGL、KO 和 BAC 的实际运行结果。
  • 财报电话会议:工具不会抓取电话会议记录。如果用户粘贴了记录(或公司投资者关系页面提供了记录),则读取并总结管理层所说的变化:业绩指引、利润率、需求,以及他们拒绝回答的问题。
  • SEC 数据中没有下一次报告日期。可在
    /trader-news
    的头条新闻或公司的投资者关系页面中查找,并说明信息来源。

The rules

规则

  • Filed numbers first. The table comes from XBRL facts the company filed. Use the press release for context (guidance, segment colour), and say which numbers came from where.
  • Compare like with like. Growth is against the same quarter a year earlier. Quarter-on-quarter changes are shown but many businesses are seasonal (Apple's December quarter is always its biggest).
  • Say what is derived. Companies do not file a Q4 10-Q. The fourth quarter is the 10-K year minus the three quarters inside it and is marked "derived"; derived EPS is approximate.
  • Say when the data lags. SEC's facts API can trail a filing. When the newest 10-Q is later than the newest quarter in the facts, the tool prints a NOTE with the link: read the 10-Q itself before summarising.
  • Flag one-offs. When net income is above operating income, gains outside the business (investment marks, tax items) are inside it. The tool says so. Banks and insurers have no gross margin: blank, not zero.
  • 已申报数据优先。 表格中的数据来自公司提交的 XBRL facts。使用新闻稿补充背景信息(如业绩指引和分部业务表现),并说明各个数字的来源。
  • 进行同类对比。 增长率以同比为准,即与上年同一季度比较。工具也会展示环比变化,但许多业务存在季节性(Apple 的 12 月季度始终是规模最大的季度)。
  • 明确说明推导数据。 公司不会提交 Q4 10-Q。第四季度数据由 10-K 全年数据减去其中三个季度的数据得出,并标记为“derived”;推导出的 EPS 是近似值。
  • 数据滞后时说明。 SEC facts API 的数据可能滞后于申报文件。当最新 10-Q 晚于 facts 中包含的最新季度时,工具会打印带链接的 NOTE;总结前应直接阅读 10-Q。
  • 标出一次性项目。 当净利润高于营业利润时,说明净利润中包含业务之外的收益(投资估值变动、税务项目等)。工具会明确指出这一点。银行和保险公司没有毛利率,应留空而不是填 0。

Steps

步骤

  1. Run it for the companies in question (or the tickers on
    trader/watchlist.json
    ):
    bash
    python3 "${CLAUDE_SKILL_DIR}/facts.py" TSLA
    python3 "${CLAUDE_SKILL_DIR}/facts.py" TSLA NVDA AMD --metrics trader/metrics.json
    --quarters 8
    shows two years,
    --json
    everything machine-readable,
    --cik
    a company without a ticker.
  2. Open the latest earnings press release (the EX-99 link) and the 10-Q when the numbers need context, and read them.
  3. Write the summary: one line on the quarter (revenue, EPS, growth), one on margins, one on anything unusual (a one-off, a derived quarter, data that lags), and the links. Plain words, real numbers, no adjectives the numbers do not support.
  4. If the next report falls inside the planned trade (an overnight hold, or a report before the open), say it before
    /trader-exit
    sets the stop: a stop does not protect against a gap, the stock can open past it.
  1. 对相关公司运行工具(或使用
    trader/watchlist.json
    中的股票代码):
    bash
    python3 "${CLAUDE_SKILL_DIR}/facts.py" TSLA
    python3 "${CLAUDE_SKILL_DIR}/facts.py" TSLA NVDA AMD --metrics trader/metrics.json
    --quarters 8
    显示两年的数据,
    --json
    输出全部机器可读数据,
    --cik
    用于没有股票代码的公司。
  2. 打开最新财报新闻稿(EX-99 链接);当数字需要背景说明时,也打开 10-Q 并阅读。
  3. 编写总结:用一行概述本季度情况(营收、EPS、增长率),用一行说明利润率,再用一行说明任何异常情况(一次性项目、推导季度、数据滞后),最后附上链接。措辞应平实,使用真实数字,不添加数据无法支持的形容词。
  4. 如果下一次报告落在计划交易期间(隔夜持仓,或开盘前发布报告),应在
    /trader-exit
    设置止损前发出提示:止损单无法防范跳空,股价开盘时可能越过止损价。

Example: the reel's stock

示例:短视频中的股票

facts.py TSLA
(run 2026-10-20): quarter ending 2026-06-30 (Q2 2026), revenue $28.24B, +25.5% against a year earlier, net income $1.11B (-4.9%), diluted EPS $0.32 (-3.0%); gross margin 16.8% (-4.3 points on the quarter before), operating margin 1.4%; last four quarters $103.6B revenue and $1.08 EPS. The tool flags that net income is above operating income, so gains outside the business are inside it. Latest 10-Q filed 2026-07-23. Monday's headlines said Tesla reports this week, so the summary ends: "The next report is days away. A day trade that closes before the bell is not exposed to it; anything held overnight is."
facts.py AAPL
(2026-10-13): revenue $109.42B, +16.4% against a year earlier, diluted EPS $2.02 (+28.7%). For Coca-Cola the tool noted that SEC's facts stopped at 2026-04-03 while the 10-Q for 2026-07-03 was already filed, so the summary read that 10-Q directly.
facts.py TSLA
(运行于 2026-10-20):截至 2026-06-30 的季度(2026 年 Q2),营收 $28.24B,同比 +25.5%,净利润 $1.11B(-4.9%),稀释后 EPS $0.32(-3.0%);毛利率 16.8%(较上一季度下降 4.3 个百分点),营业利润率 1.4%;过去四个季度营收为 $103.6B,EPS 为 $1.08。工具提示净利润高于营业利润,说明其中包含业务之外的收益。最新 10-Q 于 2026-07-23 提交。周一的头条新闻称 Tesla 本周将发布财报,因此总结最后写道:“下一份报告就在几天后。收盘前平仓的日内交易不会受到财报影响;任何隔夜持仓都会受到影响。”
facts.py AAPL
(运行于 2026-10-13):营收 $109.42B,同比 +16.4%,稀释后 EPS $2.02(+28.7%)。对于 Coca-Cola,工具注意到 SEC facts 中的数据截至 2026-04-03,而截至 2026-07-03 的 10-Q 已经提交,因此总结时直接阅读了该份 10-Q。

What it never does

它绝不会做什么

  • Never says a stock is cheap, expensive, a buy or a sell. It reports what the company filed.
  • Never invents a number the filings do not have, or estimates a quarter it cannot derive.
  • Never calls SEC without the User-Agent, and stays well under 10 requests a second.
  • 绝不会判断股票便宜、昂贵、值得买入或应当卖出。它只报告公司提交的 data。
  • 绝不编造申报文件中没有的数字,也不会估算无法推导出的季度。
  • 未设置 User-Agent 时绝不调用 SEC,并将请求速率严格控制在每秒 10 次以下。

Safety

安全

Education and tooling, not financial advice. This skill only reads filings. Nothing places an order except
/trader-broker
, after
/trader-risk
passes and the user types an explicit yes for that order.
仅供教育和工具使用,不构成财务建议。此 skill 只读取申报文件。只有
/trader-broker
会下单,但前提是
/trader-risk
检查通过,并且用户针对该订单明确输入 yes。