用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/stanfish06/skillquarium --skill industry命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
build a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates
interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow
narrow React component prop types to match live code paths
基于 SOC 职业分类
正在显示 SKILL.md
| name | industry |
| description | Cross-company industry comparison across multiple tickers |
Perform an industry comparison across the companies named in the user's request. If no ticker or company is provided, ask for one before proceeding.
The user will provide multiple tickers separated by spaces (e.g., "AAPL MSFT GOOG AMZN").
Before starting, read ../data-access.md for data access methods and ../design-system.md for formatting conventions. Follow the data access detection logic and design system throughout this skill.
Follow these steps:
Look up all provided tickers using discover_companies. For each company, capture:
company_idlatest_calendar_quarter — use the earliest latest_calendar_quarter across all companies as the anchor for period calculations (see ../data-access.md Section 1.5)latest_fiscal_quarter../data-access.md Section 4.5Calculate 8 quarters backward from the anchor latest_calendar_quarter. For each company, find and pull these metrics:
Income Statement:
Cash Flow:
For any derived/computed metric, mark it with "(calc.)" so the reader knows it's not directly sourced.
First, think about what KPIs matter for the specific industry being compared. Use the full sector taxonomy to guide discovery:
For each company, discover and pull the most relevant KPIs. Note which KPIs are common across the group (apples-to-apples comparison) and which are unique to specific companies. For mixed-sector comparisons, focus on the KPIs that apply to the largest revenue segments of each company.
For each company, search the most recent 2 quarters of filings across multiple queries. If any search returns empty, try alternative keywords before giving up.
If a company returns sparse results across all searches, try broader single-keyword searches (e.g., just "competitive" or just "growth") and search additional periods.
For each company, extract:
Use these findings to enrich the rankings analysis — numbers tell you who's winning, filings tell you why.
Save to reports/{INDUSTRY_LABEL}_industry_comp.html (where INDUSTRY_LABEL is derived from the tickers, e.g., "AAPL_MSFT_GOOG_AMZN") using the HTML report template from ../design-system.md. Write the full analysis as styled HTML with the design system CSS inlined. This is the final deliverable — no intermediate markdown step needed.
The report should include:
All financial figures must use Daloopa citation format: <a href="https://daloopa.com/src/{fundamental_id}">$X.XX million</a>
Tell the user where the HTML report was saved.
Give a clear competitive verdict: Who is winning and who is losing? Which company has the strongest competitive position and why? Which company looks most vulnerable? Are any of the companies structurally mispriced relative to peers (too cheap or too expensive given the fundamentals)? Don't hedge — rank them honestly.