agentsclimarketplace

Weekly brief

Skill rgourley/quant-garage/skills/weekly-brief

Analyst workflows as Claude skills. 62+ tools and 8 workflows spanning earnings, comps, valuation, options flow, factor research, sizing, risk, TCA, and ops. Built in the garage, not the trading floor.

Install
npx -y skills add rgourley/quant-garage --skill weekly-brief

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.
  • 6 stars6 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.

What its author says it does

Copied from the file, not written here

Sunday-night briefing for the week ahead. Composes market-regime + sector-rotation-signal + macro-event-calendar (7d) + earnings-blackout (7d) into a watchlist-focused prep brief. Different from portfolio-review, which is position-focused; this one asks "what's happening this week across the names I care about." Use when the operator wants recurring weekly context, not on-demand book review.

SKILL.md

2.0 KB, 412 tokens by cl100k_base, as published. Nobody here has run it

weekly-brief

You hand over a watchlist. The skill runs the four macro/calendar sub-skills and stitches them into a briefing sized for the week ahead. Watchlist-focused, not position-focused.

When to invoke

  • "Weekly brief", "what's on the calendar this week", "prep for the week", "Sunday briefing"
  • Recurring cadence use: cron this every Sunday night with your watchlist
  • Different from portfolio-review: this is watchlist context, not portfolio decisions

What you need

  • MASSIVE_API_KEY (Stocks Basic minimum — all sub-skills run on free)

What you get back

Layer 1 JSON matching output-schema.json. Headline block distills the regime, rotation theme, this-week's top-3 macro events, and this-week's earnings prints. Full sections below.

Layer 2 rendered brief with the same shape as portfolio-review: headline block + 4 titled sections. See references/rendering.md.

How it works

Pure composition. Runs sub-skills in order:

  1. market-regime
  2. sector-rotation-signal (30d default)
  3. macro-event-calendar (window_days=7 by default)
  4. earnings-blackout (watchlist, same window)

Shares a single MassiveClient. Failures in any single section leave its sections[<name>] null and appear in the errors block.

Endpoints used

  • Union of the 4 sub-skills' endpoints (daily-aggs for SPY + sector ETFs, EDGAR for earnings fallback, no options)

Doesn't handle (yet)

  • No positions. This is watchlist-focused. For book-level review use portfolio-review.
  • No news scan. For a daily open with fresh news, use morning-brief.

What ships with it: 4 files

3.6 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most plan spec skills give in 412 tokens

Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 51 of 1099
  • Break plans into vertical slicesin 29 of 1099, across 11 files
  • Publish issues in dependency orderin 27 of 1099, across 9 files
  • Iterate until user approves the breakdownin 25 of 1099, across 7 files
  • Explore the repository to understand the codebase statein 24 of 1099, across 7 files
  • Use domain glossary vocabularyin 23 of 1099, across 5 files
  • Apply correct triage labels to published issuesin 23 of 1099, across 5 files
  • Prefer AFK slices over HITLin 22 of 1099, across 7 files
  • Write a specification before writing any codein 22 of 1099, across 14 files
  • Write failing tests before implementation codein 22 of 1099, across 20 files
  • Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
  • Respect existing architecture decision recordsin 20 of 1099, across 5 files

Said here and by no other author read

  • run four sub-skills in order
  • share a single MassiveClient
  • null failed sections
  • report failures in errors block
  • distill regime rotation events earnings
  • match output schema

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,970. 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.