agentsclimarketplace

Book exposure

Skill blaze10011/market-flow-desk/.claude/skills/book-exposure

Per-basket dollar-beta exposure of the whole book — which sector tides actually drive the user's P&L and by how much. Use when the user asks "what's my real exposure?", "how much do I lose if SMH drops 5%?", "is my book one trade?", "what drives my P&L?", or as part of analyzing the daily brief on big sector-rotation days to size the tide's impact on the user's actual holdings. Complements portfolio-risk (which is single-bench vs SMH); this measures each name against its OWN basket and aggregates.From its SKILL.md

Install
npx -y skills add blaze10011/market-flow-desk --skill book-exposure

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.6 KB, 281 tokens by cl100k_base, as published. Nobody here has run it

Book Exposure — dollar-beta per basket

A stock's move = basket tide × beta. This engine aggregates that across the whole book: each position's beta to its OWN basket (SMH for chips, XLY for TSLA, ...), dollar-weighted, so a "-5% SMH day" becomes a $ number BEFORE it happens instead of a surprise after.

Steps

  1. Run from project root: python3 scripts/exposure.py (reads data/trading-log.xlsx — the user's real open positions)
  2. Interpret only what it prints:
    • Per-basket table: $ exposed, weight, wavg beta, and "$ per 1% basket move" / "-5% day" — the tides that matter, ranked.
    • Book beta to SPY: the whole-market sensitivity in one number.
    • ⚠ concentration flag: if one basket is >50% of total dollar-beta, the book is effectively ONE trade — say so plainly.
  3. On rotation days (one basket dumping, another rallying), lead with the dominant basket's $ impact on HIS book, then note the offsets.

If the trading log still holds the seeded example book, say so — the numbers are illustrative until he enters real holdings. Decision support, NOT advice. Data ~15-min delayed.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,736. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.