Skill
8-k-scanner
Scan SEC 8-K disclosures across a single ticker or a watchlist using Massive's pre-parsed disclosure taxonomy. Groups the underlying rows by filing (one 8-K…
@rgourleyView SkillData
Skill
/scan-and-frame
Research-tier idea generation with regime framing. Chains market-regime (context) + universe-builder (candidates) + relative-strength (rank candidates vs SPY). Optionally adds factor-research for broader factor context (heavy, off by default). Different from portfolio-review
Install
$ npx -y skills add rgourley/quant-garage --skill scan-and-frame --agent claude-codeHow 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
/scan-and-frame
Context preview
The summary Claude sees to decide when to auto-load this skill.
Research-tier idea generation with regime framing. Chains market-regime (context) + universe-builder (candidates) + relative-strength (rank candidates vs SPY). Optionally adds factor-research for broader factor context (heavy, off by default). Different from portfolio-review
SKILL.md
scan-and-frame.SKILL.mdname: scan-and-frame
description: Research-tier idea generation with regime framing. Chains market-regime (context) + universe-builder (candidates) + relative-strength (rank candidates vs SPY). Optionally adds factor-research for broader factor context (heavy, off by default). Different from portfolio-review (positions) and weekly-brief (macro-only) — this is discovery mode.
scan-and-frame
Discovery-mode composite. Runs universe-builder with the operator's filters, ranks the top N by relative strength vs SPY, and frames the whole thing with the current market regime. Optional heavy factor- research pass for factor context.
When to invoke
- Analyst says "what should I look at right now", "find me candidates
in X sector", "screen for momentum names"
- Weekly / periodic universe scan with regime context
- Different from portfolio-review (positions) and stock-one-pager
(retail single-name)
Modes
- **Fast** (default): market-regime + universe-builder + relative-
strength. Runs on Stocks Starter, ~10-30s depending on universe size.
- **Full** (`include_factor_research=True`): also runs factor-research.
Heavy — 3-year factor panel over 200-name universe. Use for weekly cadence, not per-run.
What you get back
**Layer 1 JSON** matching [`output-schema.json`](./output-schema.json). Headline: regime, universe count, top-5 RS-ranked candidates, top factor (if factor-research ran).
**Layer 2 rendered brief**. See [`references/rendering.md`](./references/rendering.md).
Read more
name: scan-and-frame description: Research-tier idea generation with regime framing. Chains market-regime (context) + universe-builder (candidates) + relative-strength (rank candidates vs SPY). Optionally adds factor-research for broader factor context (heavy, off by default). Different from portfolio-review (positions) and weekly-brief (macro-only) — this is discovery mode.
scan-and-frame
Discovery-mode composite. Runs universe-builder with the operator's filters, ranks the top N by relative strength vs SPY, and frames the whole thing with the current market regime. Optional heavy factor- research pass for factor context.
When to invoke
- Analyst says "what should I look at right now", "find me candidates
in X sector", "screen for momentum names"
- Weekly / periodic universe scan with regime context
- Different from portfolio-review (positions) and stock-one-pager
(retail single-name)
Modes
- **Fast** (default): market-regime + universe-builder + relative-
strength. Runs on Stocks Starter, ~10-30s depending on universe size.
- **Full** (`include_factor_research=True`): also runs factor-research.
Heavy — 3-year factor panel over 200-name universe. Use for weekly cadence, not per-run.
What you get back
**Layer 1 JSON** matching [`output-schema.json`](./output-schema.json). Headline: regime, universe count, top-5 RS-ranked candidates, top factor (if factor-research ran).
**Layer 2 rendered brief**. See [`references/rendering.md`](./references/rendering.md).
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
Other skills on quant-garage.
@rgourleyView SkillSkill
analyst-tracker
Track sell-side analyst positioning on a name via Benzinga Analyst Ratings. Pulls every rating event over the lookback window, classifies each as upgrade /…
@rgourleyView SkillSkill
backtest-data-prep
Build a clean, point-in-time, ready-to-backtest OHLCV dataset for a US equity universe across an arbitrary date window. Emits parquet plus a manifest plus an…
@rgourleyView SkillSkill
change-point-detector
Bayesian Online Change-Point Detection (BOCPD) on a ticker's daily log returns. Detects points in time where the return-generating distribution changed (regime…
@rgourleyView SkillSkill
commodity-cycle
Single-commodity macro read. Answers "is this commodity in a winning or losing macro setup right now" and names the macro driver that dominates it. Pulls one…
@rgourleyView SkillSkill
corp-actions-reconcile…
Reconcile a position file against splits, dividends, and spinoffs to catch breaks before they hit P&L or T+1 settlement. Use when an operator hands over a CSV…
@rgourleyView Skill