AugmentClaude

Capital Rotation Scanner

Track US market capital flows across sectors to identify which asset classes are winning today.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/capital-rotation-innei/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use when reading today's US-market capital flow across multiple sectors to identify rotation direction — e.g., "rotation map", "where is money moving today", "scan flows across sectors". Produces a cross-section snapshot of net inflows by cohort (indices / semis / software-cloud / mega-tech / AI applications), names the dominant narrative, and writes a dated journal file. Different from `market-session-tracker` (intraday live monitoring of a single watchlist) — this is a one-shot end-of-session rotation read.

What this skill does

Capital Rotation Scanner identifies winning and losing asset classes in the US market by measuring net capital flows across five standard cohorts: indices, semiconductors, software/cloud, mega-tech, and risk-off proxies. It performs a one-shot end-of-session read to determine rotation direction, names the dominant narrative (e.g., "selling chips, buying cloud"), and logs findings to a dated journal file. This differs from live intraday watchlist tracking—it's designed for end-of-day debriefs or pre-Asia-open preparation.

What it does

  • Scans five cohorts (indices, semis, software/cloud, mega-tech, risk-off) by pulling cumulative net inflow data from Longbridge for each symbol.
  • Detects distribution patterns in index behavior (e.g., institutional outflows vs. retail inflows, sector-wide selling pressure).
  • Classifies rotation by comparing net flows across cohorts to identify which sectors gained capital and which lost it.
  • Names the narrative—assigns one of seven labels like "selling semis, buying cloud" or "all sectors absorbing capital"—based on flow patterns and AI revenue maturity.
  • Writes a journal entry to ~/git/trade/journal/YYYY-MM-DD-flow.md with a snapshot, three actionable insights, and tomorrow's watch list.
  • Surfaces cross-asset signals, optionally including volatility and bond flows for confirmation.

How to use it

Invoke the skill when you want to understand capital rotation across US sectors after market close—for example, "rotation map," "where is money moving today," or "scan flows across sectors." Hand it your preferred session date. The skill confirms US market state, pulls market temperature, fetches baseline index flows, scans each cohort in parallel, ranks symbols within cohorts, and outputs a snapshot with explicit rotation labels and three concrete next-day conditions to watch.

Related skills