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 bull-bear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 | bull-bear |
| description | Bull/bear/base case scenario framework for a given company |
Build a bull/bear/base case scenario framework for the company named in the user's request. If no ticker or company is provided, ask for one before proceeding.
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 the company by ticker using discover_companies. Capture:
company_idlatest_calendar_quarter — anchor for all period calculations below (see ../data-access.md Section 1.5)latest_fiscal_quarter../data-access.md Section 4.5Get the current stock price using get_stock_prices (see ../data-access.md Section 1.7). Pass company_id and dates for the 3 most recent calendar days — use the most recent returned close price. This is the anchor for scenario comparison: each scenario's implied value will be compared against this price to show upside/downside.
Calculate 8 quarters backward from latest_calendar_quarter. Pull:
Compute trailing 4-quarter totals for revenue, EBITDA, net income, EPS, and FCF — these are the baseline the scenarios build from.
Flag any one-time items that distort quarters.
First, think about what the most important KPIs are for THIS specific company based on its business model and what drives its valuation. For example:
Search for those specific KPIs by name and pull them. These are the building blocks for bottoms-up scenario math.
Also pull capital allocation data: share count, buyback amounts, dividends.
Search SEC filings/documents across multiple queries. If any search returns empty, try alternative keywords before giving up.
If consensus estimates are available (see ../data-access.md Section 3), note:
If consensus data is not available, skip this section.
For each scenario, build a bottoms-up revenue model showing key segment or product-level assumptions (e.g., units x ASP, subscribers x ARPU, segment growth rates). Don't just state a revenue range — show the math that gets there.
Don't default to 25/50/25. Assign probabilities informed by the most recent data points:
Be honest about which scenario is most likely. Don't default to a bullish framing or split the difference to seem balanced. If the data suggests the bear case is more probable, say so clearly. If the bull case requires multiple things to go right simultaneously, acknowledge that compounds the risk. The reader needs your honest assessment, not diplomatic equivocation.
Save to reports/{TICKER}_bull_bear.html 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.
Highlight: which scenario you believe is most likely and why, the key swing factors between bull and bear cases, and where you think the market is currently positioned (closer to bull, base, or bear). If the current stock price implies an overly optimistic or pessimistic scenario, flag it.