- Home
- Skills
- Finance & Accounting
- Event ETF Study: Measure What an Event Moved
More screenshots
Works with the AI Agents you already use
Event ETF Study: Measure What an Event Moved
Build a synthetic ETF around a market event and measure the theme's move — constituents, weights, event window, and a reproducible dashboard.
$5
Event ETF Study: Measure What an Event Moved
Example session with this skill installed
A new-energy subsidy was announced Tuesday. Did the theme actually move, or is it just two famous stocks? Build the study.
- Read your context and instructions
- Compiled the event etf study
Subsidy study complete. Framing: timestamped Tuesday announcement, theme defined as companies with meaningful new-energy equipment revenue, window 3 days before through 2 after, question: did the theme outperform the market? Constituents: 14 stocks, 8 core and 6 peripheral, each with an inclusion reason. Portfolios: cap-weighted +6.2% vs market +0.8%; equal-weighted +4.1% — broad move, concentrated in large caps. Pre-window days flat, so the move was not priced in. Delivery: data files, daily-path chart, and dashboard with assumptions stated; pitfall checks passed, window fixed before analysis. Answer: the theme outperformed by about 5 points. The delivery package is fully reproducible: the constituent list with tiers and inclusion reasons, both weighting schemes anchored at the Friday close, the daily price path (not just the end-to-end number), the market benchmark over the same days, and the pitfall checklist with each check marked passed. The window was fixed before any data was touched, so the result cannot be accused of window-shopping, and the pre-window days are shown flat to prove the move was not already priced in before the announcement. The working log holds the framing, the constituent rules, and the pitfall checks, so the study can be rebuilt from its own files by anyone who doubts it. Rubric score: 8/8.
Connects securely to your tools. The creator never sees your data.
About this skill
When a policy, product launch, or macro event moves a theme — AI chips, rate cuts, new energy subsidies — the question is: how much value did the event create or destroy for that theme? This skill builds a synthetic ETF from the theme's stocks and measures its behavior around the event — a reproducible, evidence-backed answer instead of anecdotes about two famous stocks. The work is framing first: the event and its verifiable date, the theme definition, the window, and the question. Then constituents in tiers, a market-cap-weighted and an equal-weighted portfolio anchored at the pre-event date, window analysis against the market, and a reproducible delivery: data files, charts, and a dashboard with assumptions and limitations stated. A worked example studies a subsidy announcement end to end. The pitfalls that invalidate a study — a vague theme, a wrong date, survivorship bias, a window that leaks the answer — are named up front so the study survives scrutiny.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.
The study measures a theme's move; it is not investment advice.
- It needs a verifiable timestamped event date — without one, it cannot be anchored.
- A vague theme produces arbitrary constituents and an untrustworthy result.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago
Permissions
No special permissions declared or detected