Skip to content
Data
Skill

/smart-money-cluster

Workflow composite that runs manager-portfolio-diff across a curated cohort of well-known filers (Berkshire, Baupost, Renaissance, Bridgewater, Third Point, Pershing Square, Tiger Global, Scion, Appaloosa) and aggregates the initiations, adds, and exits by issuer. Surfaces

From plugin
quant-garage
761 skills
Install
$ npx -y skills add rgourley/quant-garage --skill smart-money-cluster --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/smart-money-cluster

Context preview

The summary Claude sees to decide when to auto-load this skill.

Workflow composite that runs manager-portfolio-diff across a curated cohort of well-known filers (Berkshire, Baupost, Renaissance, Bridgewater, Third Point, Pershing Square, Tiger Global, Scion, Appaloosa) and aggregates the initiations, adds, and exits by issuer. Surfaces

SKILL.md

smart-money-cluster.SKILL.md
name: smart-money-cluster
description: Workflow composite that runs manager-portfolio-diff across a curated cohort of well-known filers (Berkshire, Baupost, Renaissance, Bridgewater, Third Point, Pershing Square, Tiger Global, Scion, Appaloosa) and aggregates the initiations, adds, and exits by issuer. Surfaces cross-fund conviction: names that appeared in >= N funds' new positions this quarter. Requires Stocks Basic. Runs on the free tier.

smart-money-cluster

Runs `manager-portfolio-diff` across a curated cohort of well-known funds and aggregates the results by issuer. Surfaces names that appeared in >= N funds' new positions (initiations), adds, or exits this quarter as a "cross-fund conviction" signal.

Default cohort: Berkshire, Baupost, Renaissance, Bridgewater, Third Point, Pershing Square, Tiger Global, Scion, Appaloosa. Custom cohort via `--aliases`.

When to invoke

  • Quarterly 13-F review
  • "What did smart money buy this quarter?"
  • Screening for names with cross-fund conviction as a starting point
  • The user says "smart money", "13-F cluster", "cross-fund"

Not for: real-time (13-F is quarterly and lagged ~45 days). Not for alpha timing (crowded positions can underperform).

What you need

  • `MASSIVE_API_KEY` exported
  • Stocks Basic minimum

Optional:

  • `--aliases` (default: 9-fund cohort)
  • `--min-funds` (default 2): minimum fund count to surface a name

What you get back

**Layer 1: JSON**. Per-fund summary, clustered_initiations, clustered_adds, clustered_exits, each sorted by fund count then dollar volume.

**Layer 2: rendered note**. Per-fund one-liners + three cluster tables + Take.

Foundations used

  • Composes `manager-portfolio-diff` across N filers.

Doesn't handle (yet)

  • **Custom cohort scoring.** Each fund weighted equally. Historical

accuracy weighting would be a real extension.

  • **Price context.** No overlay of cluster picks vs current price /

RS / vol regime.

  • **Time-series cluster tracking.** Only current quarter; no

quarter-over-quarter momentum.

These are clean composite extensions.

Read more
Ships withquant-garage

Trade like a pro. Without the terminal. View the full landing page → Quant and equity research tools that run inside Claude, or behind your own UI.

Get the whole plugin
Stats
7
Stars
0
Forks
Active
Maintenance
Python
Language
7d ago
Last commit
2mo ago
Created

Repo: rgourley/quant-garage

Other skills on quant-garage.